mirror of
https://github.com/kohya-ss/sd-scripts.git
synced 2026-04-16 17:02:45 +00:00
Merge e7b8e9a778 into f5d44fd487
This commit is contained in:
Kohya S.
GitHub
@@ -29,7 +29,9 @@ koo="koo"
|
||||
yos="yos"
|
||||
wn="wn"
|
||||
hime="hime"
|
||||
|
||||
OT="OT"
|
||||
byt="byt"
|
||||
tak="tak"
|
||||
|
||||
[files]
|
||||
extend-exclude = ["_typos.toml", "venv"]
|
||||
|
||||
514
docs/hunyuan_image_train_network.md
Normal file
514
docs/hunyuan_image_train_network.md
Normal file
@@ -0,0 +1,514 @@
|
||||
Status: reviewed
|
||||
|
||||
# LoRA Training Guide for HunyuanImage-2.1 using `hunyuan_image_train_network.py` / `hunyuan_image_train_network.py` を用いたHunyuanImage-2.1モデルのLoRA学習ガイド
|
||||
|
||||
This document explains how to train LoRA models for the HunyuanImage-2.1 model using `hunyuan_image_train_network.py` included in the `sd-scripts` repository.
|
||||
|
||||
<details>
|
||||
<summary>日本語</summary>
|
||||
|
||||
このドキュメントでは、`sd-scripts`リポジトリに含まれる`hunyuan_image_train_network.py`を使用して、HunyuanImage-2.1モデルに対するLoRA (Low-Rank Adaptation) モデルを学習する基本的な手順について解説します。
|
||||
|
||||
</details>
|
||||
|
||||
## 1. Introduction / はじめに
|
||||
|
||||
`hunyuan_image_train_network.py` trains additional networks such as LoRA on the HunyuanImage-2.1 model, which uses a transformer-based architecture (DiT) different from Stable Diffusion. Two text encoders, Qwen2.5-VL and byT5, and a dedicated VAE are used.
|
||||
|
||||
This guide assumes you know the basics of LoRA training. For common options see [train_network.py](train_network.md) and [sdxl_train_network.py](sdxl_train_network.md).
|
||||
|
||||
**Prerequisites:**
|
||||
|
||||
* The repository is cloned and the Python environment is ready.
|
||||
* A training dataset is prepared. See the dataset configuration guide.
|
||||
|
||||
<details>
|
||||
<summary>日本語</summary>
|
||||
|
||||
`hunyuan_image_train_network.py`はHunyuanImage-2.1モデルに対してLoRAなどの追加ネットワークを学習させるためのスクリプトです。HunyuanImage-2.1はStable Diffusionとは異なるDiT (Diffusion Transformer) アーキテクチャを持つ画像生成モデルであり、このスクリプトを使用することで、特定のキャラクターや画風を再現するLoRAモデルを作成できます。
|
||||
|
||||
このガイドは、基本的なLoRA学習の手順を理解しているユーザーを対象としています。基本的な使い方や共通のオプションについては、[`train_network.py`のガイド](train_network.md)を参照してください。また一部のパラメータは [`sdxl_train_network.py`](sdxl_train_network.md) や [`flux_train_network.py`](flux_train_network.md) と同様のものがあるため、そちらも参考にしてください。
|
||||
|
||||
**前提条件:**
|
||||
|
||||
* `sd-scripts`リポジトリのクローンとPython環境のセットアップが完了していること。
|
||||
* 学習用データセットの準備が完了していること。（データセットの準備については[データセット設定ガイド](config_README-ja.md)を参照してください）
|
||||
|
||||
</details>
|
||||
|
||||
## 2. Differences from `train_network.py` / `train_network.py` との違い
|
||||
|
||||
`hunyuan_image_train_network.py` is based on `train_network.py` but adapted for HunyuanImage-2.1. Main differences include:
|
||||
|
||||
* **Target model:** HunyuanImage-2.1 model.
|
||||
* **Model structure:** HunyuanImage-2.1 uses a Transformer-based architecture (DiT). It uses two text encoders (Qwen2.5-VL and byT5) and a dedicated VAE.
|
||||
* **Required arguments:** Additional arguments for the DiT model, Qwen2.5-VL, byT5, and VAE model files.
|
||||
* **Incompatible options:** Some Stable Diffusion-specific arguments (e.g., `--v2`, `--clip_skip`, `--max_token_length`) are not used.
|
||||
* **HunyuanImage-2.1-specific arguments:** Additional arguments for specific training parameters like flow matching.
|
||||
|
||||
<details>
|
||||
<summary>日本語</summary>
|
||||
|
||||
`hunyuan_image_train_network.py`は`train_network.py`をベースに、HunyuanImage-2.1モデルに対応するための変更が加えられています。主な違いは以下の通りです。
|
||||
|
||||
* **対象モデル:** HunyuanImage-2.1モデルを対象とします。
|
||||
* **モデル構造:** HunyuanImage-2.1はDiTベースのアーキテクチャを持ちます。Text EncoderとしてQwen2.5-VLとbyT5の二つを使用し、専用のVAEを使用します。
|
||||
* **必須の引数:** DiTモデル、Qwen2.5-VL、byT5、VAEの各モデルファイルを指定する引数が追加されています。
|
||||
* **一部引数の非互換性:** Stable Diffusion向けの引数の一部（例: `--v2`, `--clip_skip`, `--max_token_length`）は使用されません。
|
||||
* **HunyuanImage-2.1特有の引数:** Flow Matchingなど、特有の学習パラメータを指定する引数が追加されています。
|
||||
|
||||
</details>
|
||||
|
||||
## 3. Preparation / 準備
|
||||
|
||||
Before starting training you need:
|
||||
|
||||
1. **Training script:** `hunyuan_image_train_network.py`
|
||||
2. **HunyuanImage-2.1 DiT model file:** Base DiT model `.safetensors` file.
|
||||
3. **Text Encoder model files:**
|
||||
- Qwen2.5-VL model file (`--text_encoder`).
|
||||
- byT5 model file (`--byt5`).
|
||||
4. **VAE model file:** HunyuanImage-2.1-compatible VAE model `.safetensors` file (`--vae`).
|
||||
5. **Dataset definition file (.toml):** TOML format file describing training dataset configuration.
|
||||
|
||||
### Downloading Required Models
|
||||
|
||||
To train HunyuanImage-2.1 models, you need to download the following model files:
|
||||
|
||||
- **DiT Model**: Download from the [Tencent HunyuanImage-2.1](https://huggingface.co/tencent/HunyuanImage-2.1/) repository. Use `dit/hunyuanimage2.1.safetensors`.
|
||||
- **Text Encoders and VAE**: Download from the [Comfy-Org/HunyuanImage_2.1_ComfyUI](https://huggingface.co/Comfy-Org/HunyuanImage_2.1_ComfyUI) repository:
|
||||
- Qwen2.5-VL: `split_files/text_encoders/qwen_2.5_vl_7b.safetensors`
|
||||
- byT5: `split_files/text_encoders/byt5_small_glyphxl_fp16.safetensors`
|
||||
- VAE: `split_files/vae/hunyuan_image_2.1_vae_fp16.safetensors`
|
||||
|
||||
<details>
|
||||
<summary>日本語</summary>
|
||||
|
||||
学習を開始する前に、以下のファイルが必要です。
|
||||
|
||||
1. **学習スクリプト:** `hunyuan_image_train_network.py`
|
||||
2. **HunyuanImage-2.1 DiTモデルファイル:** 学習のベースとなるDiTモデルの`.safetensors`ファイル。
|
||||
3. **Text Encoderモデルファイル:**
|
||||
- Qwen2.5-VLモデルファイル (`--text_encoder`)。
|
||||
- byT5モデルファイル (`--byt5`)。
|
||||
4. **VAEモデルファイル:** HunyuanImage-2.1に対応するVAEモデルの`.safetensors`ファイル (`--vae`)。
|
||||
5. **データセット定義ファイル (.toml):** 学習データセットの設定を記述したTOML形式のファイル。（詳細は[データセット設定ガイド](config_README-ja.md)を参照してください）。
|
||||
|
||||
**必要なモデルのダウンロード**
|
||||
|
||||
HunyuanImage-2.1モデルを学習するためには、以下のモデルファイルをダウンロードする必要があります：
|
||||
|
||||
- **DiTモデル**: [Tencent HunyuanImage-2.1](https://huggingface.co/tencent/HunyuanImage-2.1/) リポジトリから `dit/hunyuanimage2.1.safetensors` をダウンロードします。
|
||||
- **Text EncoderとVAE**: [Comfy-Org/HunyuanImage_2.1_ComfyUI](https://huggingface.co/Comfy-Org/HunyuanImage_2.1_ComfyUI) リポジトリから以下をダウンロードします：
|
||||
- Qwen2.5-VL: `split_files/text_encoders/qwen_2.5_vl_7b.safetensors`
|
||||
- byT5: `split_files/text_encoders/byt5_small_glyphxl_fp16.safetensors`
|
||||
- VAE: `split_files/vae/hunyuan_image_2.1_vae_fp16.safetensors`
|
||||
|
||||
</details>
|
||||
|
||||
## 4. Running the Training / 学習の実行
|
||||
|
||||
Run `hunyuan_image_train_network.py` from the terminal with HunyuanImage-2.1 specific arguments. Here's a basic command example:
|
||||
|
||||
```bash
|
||||
accelerate launch --num_cpu_threads_per_process 1 hunyuan_image_train_network.py \
|
||||
--pretrained_model_name_or_path="<path to HunyuanDiT model>" \
|
||||
--text_encoder="<path to Qwen2.5-VL model>" \
|
||||
--byt5="<path to byT5 model>" \
|
||||
--vae="<path to VAE model>" \
|
||||
--dataset_config="my_hunyuan_dataset_config.toml" \
|
||||
--output_dir="<output directory>" \
|
||||
--output_name="my_hunyuan_lora" \
|
||||
--save_model_as=safetensors \
|
||||
--network_module=networks.lora_hunyuan_image \
|
||||
--network_dim=16 \
|
||||
--network_alpha=1 \
|
||||
--learning_rate=1e-4 \
|
||||
--optimizer_type="AdamW8bit" \
|
||||
--lr_scheduler="constant" \
|
||||
--attn_mode="torch" \
|
||||
--split_attn \
|
||||
--max_train_epochs=10 \
|
||||
--save_every_n_epochs=1 \
|
||||
--mixed_precision="bf16" \
|
||||
--gradient_checkpointing \
|
||||
--model_prediction_type="raw" \
|
||||
--discrete_flow_shift=5.0 \
|
||||
--blocks_to_swap=18 \
|
||||
--cache_text_encoder_outputs \
|
||||
--cache_latents
|
||||
```
|
||||
|
||||
<details>
|
||||
<summary>日本語</summary>
|
||||
|
||||
学習は、ターミナルから`hunyuan_image_train_network.py`を実行することで開始します。基本的なコマンドラインの構造は`train_network.py`と同様ですが、HunyuanImage-2.1特有の引数を指定する必要があります。
|
||||
|
||||
コマンドラインの例は英語のドキュメントを参照してください。
|
||||
|
||||
</details>
|
||||
|
||||
### 4.1. Explanation of Key Options / 主要なコマンドライン引数の解説
|
||||
|
||||
The script adds HunyuanImage-2.1 specific arguments. For common arguments (like `--output_dir`, `--output_name`, `--network_module`, etc.), see the [`train_network.py` guide](train_network.md).
|
||||
|
||||
#### Model-related [Required]
|
||||
|
||||
* `--pretrained_model_name_or_path="<path to HunyuanDiT model>"` **[Required]**
|
||||
- Specifies the path to the base DiT model `.safetensors` file.
|
||||
* `--text_encoder="<path to Qwen2.5-VL model>"` **[Required]**
|
||||
- Specifies the path to the Qwen2.5-VL Text Encoder model file. Should be `bfloat16`.
|
||||
* `--byt5="<path to byT5 model>"` **[Required]**
|
||||
- Specifies the path to the byT5 Text Encoder model file. Should be `float16`.
|
||||
* `--vae="<path to VAE model>"` **[Required]**
|
||||
- Specifies the path to the HunyuanImage-2.1-compatible VAE model `.safetensors` file.
|
||||
|
||||
#### HunyuanImage-2.1 Training Parameters
|
||||
|
||||
* `--discrete_flow_shift=<float>`
|
||||
- Specifies the shift value for the scheduler used in Flow Matching. Default is `5.0`.
|
||||
* `--model_prediction_type=<choice>`
|
||||
- Specifies what the model predicts. Choose from `raw`, `additive`, `sigma_scaled`. Default and recommended is `raw`.
|
||||
* `--timestep_sampling=<choice>`
|
||||
- Specifies the sampling method for timesteps (noise levels) during training. Choose from `sigma`, `uniform`, `sigmoid`, `shift`, `flux_shift`. Default is `sigma`.
|
||||
* `--sigmoid_scale=<float>`
|
||||
- Scale factor when `timestep_sampling` is set to `sigmoid`, `shift`, or `flux_shift`. Default is `1.0`.
|
||||
|
||||
#### Memory/Speed Related
|
||||
|
||||
* `--attn_mode=<choice>`
|
||||
- Specifies the attention implementation to use. Options are `torch`, `xformers`, `flash`, `sageattn`. Default is `torch` (use scaled dot product attention). Each library must be installed separately other than `torch`. If using `xformers`, also specify `--split_attn` if the batch size is more than 1.
|
||||
* `--split_attn`
|
||||
- Splits the batch during attention computation to process one item at a time, reducing VRAM usage by avoiding attention mask computation. Can improve speed when using `torch`. Required when using `xformers` with batch size greater than 1.
|
||||
* `--fp8_scaled`
|
||||
- Enables training the DiT model in scaled FP8 format. This can significantly reduce VRAM usage (can run with as little as 8GB VRAM when combined with `--blocks_to_swap`), but the training results may vary. This is a newer alternative to the unsupported `--fp8_base` option.
|
||||
* `--fp8_vl`
|
||||
- Use FP8 for the VLM (Qwen2.5-VL) text encoder.
|
||||
* `--text_encoder_cpu`
|
||||
- Runs the text encoders on CPU to reduce VRAM usage. This is useful when VRAM is insufficient (less than 12GB). Encoding one text may take a few minutes (depending on CPU). It is highly recommended to use this option with `--cache_text_encoder_outputs_to_disk` to avoid repeated encoding every time training starts.
|
||||
* `--blocks_to_swap=<integer>` **[Experimental Feature]**
|
||||
- Setting to reduce VRAM usage by swapping parts of the model (Transformer blocks) between CPU and GPU. Specify the number of blocks to swap as an integer (e.g., `18`). Larger values reduce VRAM usage but decrease training speed. Adjust according to your GPU's VRAM capacity. Can be used with `gradient_checkpointing`.
|
||||
* `--cache_text_encoder_outputs`
|
||||
- Caches the outputs of Qwen2.5-VL and byT5. This reduces memory usage.
|
||||
* `--cache_latents`, `--cache_latents_to_disk`
|
||||
- Caches the outputs of VAE. Similar functionality to [sdxl_train_network.py](sdxl_train_network.md).
|
||||
* `--vae_chunk_size=<integer>`
|
||||
- Enables chunked processing in the VAE to reduce VRAM usage during encoding and decoding. Specify the chunk size as an integer (e.g., `16`). Larger values use more VRAM but are faster. Default is `None` (no chunking). This option is useful when VRAM is limited (e.g., 8GB or 12GB).
|
||||
|
||||
<details>
|
||||
<summary>日本語</summary>
|
||||
|
||||
[`train_network.py`のガイド](train_network.md)で説明されている引数に加え、以下のHunyuanImage-2.1特有の引数を指定します。共通の引数（`--output_dir`, `--output_name`, `--network_module`, `--network_dim`, `--network_alpha`, `--learning_rate`など）については、上記ガイドを参照してください。
|
||||
|
||||
コマンドラインの例と詳細な引数の説明は英語のドキュメントを参照してください。
|
||||
|
||||
</details>
|
||||
|
||||
## 5. Using the Trained Model / 学習済みモデルの利用
|
||||
|
||||
After training, a LoRA model file is saved in `output_dir` and can be used in inference environments supporting HunyuanImage-2.1.
|
||||
|
||||
<details>
|
||||
<summary>日本語</summary>
|
||||
|
||||
学習が完了すると、指定した`output_dir`にLoRAモデルファイル（例: `my_hunyuan_lora.safetensors`）が保存されます。このファイルは、HunyuanImage-2.1モデルに対応した推論環境で使用できます。
|
||||
|
||||
</details>
|
||||
|
||||
## 6. Advanced Settings / 高度な設定
|
||||
|
||||
### 6.1. VRAM Usage Optimization / VRAM使用量の最適化
|
||||
|
||||
HunyuanImage-2.1 is a large model, so GPUs without sufficient VRAM require optimization.
|
||||
|
||||
#### Recommended Settings by GPU Memory
|
||||
|
||||
Based on testing with the pull request, here are recommended VRAM optimization settings:
|
||||
|
||||
| GPU Memory | Recommended Settings |
|
||||
|------------|---------------------|
|
||||
| 40GB+ VRAM | Standard settings (no special optimization needed) |
|
||||
| 24GB VRAM | `--fp8_scaled --blocks_to_swap 9` |
|
||||
| 12GB VRAM | `--fp8_scaled --blocks_to_swap 32` |
|
||||
| 8GB VRAM | `--fp8_scaled --blocks_to_swap 37` |
|
||||
|
||||
#### Key VRAM Reduction Options
|
||||
|
||||
- **`--fp8_scaled`**: Enables training the DiT in scaled FP8 format. This is the recommended FP8 option for HunyuanImage-2.1, replacing the unsupported `--fp8_base` option. Essential for <40GB VRAM environments.
|
||||
- **`--fp8_vl`**: Use FP8 for the VLM (Qwen2.5-VL) text encoder.
|
||||
- **`--blocks_to_swap <number>`**: Swaps blocks between CPU and GPU to reduce VRAM usage. Higher numbers save more VRAM but reduce training speed. Up to 37 blocks can be swapped for HunyuanImage-2.1.
|
||||
- **`--cpu_offload_checkpointing`**: Offloads gradient checkpoints to CPU. Can reduce VRAM usage but decreases training speed. Cannot be used with `--blocks_to_swap`.
|
||||
- **Using Adafactor optimizer**: Can reduce VRAM usage more than 8bit AdamW:
|
||||
```
|
||||
--optimizer_type adafactor --optimizer_args "relative_step=False" "scale_parameter=False" "warmup_init=False" --lr_scheduler constant_with_warmup --max_grad_norm 0.0
|
||||
```
|
||||
|
||||
<details>
|
||||
<summary>日本語</summary>
|
||||
|
||||
HunyuanImage-2.1は大きなモデルであるため、十分なVRAMを持たないGPUでは工夫が必要です。
|
||||
|
||||
#### GPU別推奨設定
|
||||
|
||||
Pull Requestのテスト結果に基づく推奨VRAM最適化設定：
|
||||
|
||||
| GPU Memory | 推奨設定 |
|
||||
|------------|---------|
|
||||
| 40GB+ VRAM | 標準設定（特別な最適化不要） |
|
||||
| 24GB VRAM | `--fp8_scaled --blocks_to_swap 9` |
|
||||
| 12GB VRAM | `--fp8_scaled --blocks_to_swap 32` |
|
||||
| 8GB VRAM | `--fp8_scaled --blocks_to_swap 37` |
|
||||
|
||||
主要なVRAM削減オプション：
|
||||
- `--fp8_scaled`: DiTをスケールされたFP8形式で学習（推奨されるFP8オプション、40GB VRAM未満の環境では必須）
|
||||
- `--fp8_vl`: VLMテキストエンコーダにFP8を使用
|
||||
- `--blocks_to_swap`: CPUとGPU間でブロックをスワップ（最大37ブロック）
|
||||
- `--cpu_offload_checkpointing`: 勾配チェックポイントをCPUにオフロード
|
||||
- Adafactorオプティマイザの使用
|
||||
|
||||
</details>
|
||||
|
||||
### 6.2. Important HunyuanImage-2.1 LoRA Training Settings / HunyuanImage-2.1 LoRA学習の重要な設定
|
||||
|
||||
HunyuanImage-2.1 training has several settings that can be specified with arguments:
|
||||
|
||||
#### Timestep Sampling Methods
|
||||
|
||||
The `--timestep_sampling` option specifies how timesteps (0-1) are sampled:
|
||||
|
||||
- `sigma`: Sigma-based like SD3 (Default)
|
||||
- `uniform`: Uniform random
|
||||
- `sigmoid`: Sigmoid of normal distribution random
|
||||
- `shift`: Sigmoid value of normal distribution random with shift.
|
||||
- `flux_shift`: Shift sigmoid value of normal distribution random according to resolution.
|
||||
|
||||
#### Model Prediction Processing
|
||||
|
||||
The `--model_prediction_type` option specifies how to interpret and process model predictions:
|
||||
|
||||
- `raw`: Use as-is **[Recommended, Default]**
|
||||
- `additive`: Add to noise input
|
||||
- `sigma_scaled`: Apply sigma scaling
|
||||
|
||||
#### Recommended Settings
|
||||
|
||||
Based on experiments, the default settings work well:
|
||||
```
|
||||
--model_prediction_type raw --discrete_flow_shift 5.0
|
||||
```
|
||||
|
||||
<details>
|
||||
<summary>日本語</summary>
|
||||
|
||||
HunyuanImage-2.1の学習には、引数で指定できるいくつかの設定があります。詳細な説明とコマンドラインの例は英語のドキュメントを参照してください。
|
||||
|
||||
主要な設定オプション：
|
||||
- タイムステップのサンプリング方法（`--timestep_sampling`）
|
||||
- モデル予測の処理方法（`--model_prediction_type`）
|
||||
- 推奨設定の組み合わせ
|
||||
|
||||
</details>
|
||||
|
||||
### 6.3. Regular Expression-based Rank/LR Configuration / 正規表現によるランク・学習率の指定
|
||||
|
||||
You can specify ranks (dims) and learning rates for LoRA modules using regular expressions. This allows for more flexible and fine-grained control.
|
||||
|
||||
These settings are specified via the `network_args` argument.
|
||||
|
||||
* `network_reg_dims`: Specify ranks for modules matching a regular expression. The format is a comma-separated string of `pattern=rank`.
|
||||
* Example: `--network_args "network_reg_dims=attn.*.q_proj=4,attn.*.k_proj=4"`
|
||||
* `network_reg_lrs`: Specify learning rates for modules matching a regular expression. The format is a comma-separated string of `pattern=lr`.
|
||||
* Example: `--network_args "network_reg_lrs=down_blocks.1=1e-4,up_blocks.2=2e-4"`
|
||||
|
||||
**Notes:**
|
||||
|
||||
* To find the correct module names for the patterns, you may need to inspect the model structure.
|
||||
* Settings via `network_reg_dims` and `network_reg_lrs` take precedence over the global `--network_dim` and `--learning_rate` settings.
|
||||
* If a module name matches multiple patterns, the setting from the last matching pattern in the string will be applied.
|
||||
|
||||
<details>
|
||||
<summary>日本語</summary>
|
||||
|
||||
正規表現を用いて、LoRAのモジュールごとにランク（dim）や学習率を指定することができます。これにより、柔軟できめ細やかな制御が可能になります。
|
||||
|
||||
これらの設定は `network_args` 引数で指定します。
|
||||
|
||||
* `network_reg_dims`: 正規表現にマッチするモジュールに対してランクを指定します。
|
||||
* `network_reg_lrs`: 正規表現にマッチするモジュールに対して学習率を指定します。
|
||||
|
||||
**注意点:**
|
||||
|
||||
* パターンのための正確なモジュール名を見つけるには、モデルの構造を調べる必要があるかもしれません。
|
||||
* `network_reg_dims` および `network_reg_lrs` での設定は、全体設定である `--network_dim` や `--learning_rate` よりも優先されます。
|
||||
* あるモジュール名が複数のパターンにマッチした場合、文字列の中で後方にあるパターンの設定が適用されます。
|
||||
|
||||
</details>
|
||||
|
||||
### 6.4. Multi-Resolution Training / マルチ解像度トレーニング
|
||||
|
||||
You can define multiple resolutions in the dataset configuration file, with different batch sizes for each resolution.
|
||||
|
||||
**Note:** This feature is available, but it is **not recommended** as the HunyuanImage-2.1 base model was not trained with multi-resolution capabilities. Using it may lead to unexpected results.
|
||||
|
||||
Configuration file example:
|
||||
```toml
|
||||
[general]
|
||||
shuffle_caption = true
|
||||
caption_extension = ".txt"
|
||||
|
||||
[[datasets]]
|
||||
batch_size = 2
|
||||
enable_bucket = true
|
||||
resolution = [1024, 1024]
|
||||
|
||||
[[datasets.subsets]]
|
||||
image_dir = "path/to/image/directory"
|
||||
num_repeats = 1
|
||||
|
||||
[[datasets]]
|
||||
batch_size = 1
|
||||
enable_bucket = true
|
||||
resolution = [1280, 768]
|
||||
|
||||
[[datasets.subsets]]
|
||||
image_dir = "path/to/another/directory"
|
||||
num_repeats = 1
|
||||
```
|
||||
|
||||
<details>
|
||||
<summary>日本語</summary>
|
||||
|
||||
データセット設定ファイルで複数の解像度を定義できます。各解像度に対して異なるバッチサイズを指定することができます。
|
||||
|
||||
**注意:** この機能は利用可能ですが、HunyuanImage-2.1のベースモデルはマルチ解像度で学習されていないため、**非推奨**です。使用すると予期しない結果になる可能性があります。
|
||||
|
||||
設定ファイルの例は英語のドキュメントを参照してください。
|
||||
|
||||
</details>
|
||||
|
||||
### 6.5. Validation / 検証
|
||||
|
||||
You can calculate validation loss during training using a validation dataset to evaluate model generalization performance. This feature works the same as in other training scripts. For details, please refer to the [Validation Guide](validation.md).
|
||||
|
||||
<details>
|
||||
<summary>日本語</summary>
|
||||
|
||||
学習中に検証データセットを使用して損失 (Validation Loss) を計算し、モデルの汎化性能を評価できます。この機能は他の学習スクリプトと同様に動作します。詳細は[検証ガイド](validation.md)を参照してください。
|
||||
|
||||
</details>
|
||||
|
||||
## 7. Other Training Options / その他の学習オプション
|
||||
|
||||
- **`--ip_noise_gamma`**: Use `--ip_noise_gamma` and `--ip_noise_gamma_random_strength` to adjust Input Perturbation noise gamma values during training. See Stable Diffusion 3 training options for details.
|
||||
|
||||
- **`--loss_type`**: Specifies the loss function for training. The default is `l2`.
|
||||
- `l1`: L1 loss.
|
||||
- `l2`: L2 loss (mean squared error).
|
||||
- `huber`: Huber loss.
|
||||
- `smooth_l1`: Smooth L1 loss.
|
||||
|
||||
- **`--huber_schedule`**, **`--huber_c`**, **`--huber_scale`**: These are parameters for Huber loss. They are used when `--loss_type` is `huber` or `smooth_l1`.
|
||||
|
||||
- **`--weighting_scheme`**, **`--logit_mean`**, **`--logit_std`**, **`--mode_scale`**: These options allow you to adjust the loss weighting for each timestep. For details, refer to the [`sd3_train_network.md` guide](sd3_train_network.md).
|
||||
|
||||
- **`--fused_backward_pass`**: Fuses the backward pass and optimizer step to reduce VRAM usage.
|
||||
|
||||
<details>
|
||||
<summary>日本語</summary>
|
||||
|
||||
- **`--ip_noise_gamma`**: Input Perturbationノイズのガンマ値を調整します。
|
||||
- **`--loss_type`**: 学習に用いる損失関数を指定します。
|
||||
- **`--huber_schedule`**, **`--huber_c`**, **`--huber_scale`**: Huber損失のパラメータです。
|
||||
- **`--weighting_scheme`**, **`--logit_mean`**, **`--logit_std`**, **`--mode_scale`**: 各タイムステップの損失の重み付けを調整します。
|
||||
- **`--fused_backward_pass`**: バックワードパスとオプティマイザステップを融合してVRAM使用量を削減します。
|
||||
|
||||
</details>
|
||||
|
||||
## 8. Using the Inference Script / 推論スクリプトの使用法
|
||||
|
||||
The `hunyuan_image_minimal_inference.py` script allows you to generate images using trained LoRA models. Here's a basic usage example:
|
||||
|
||||
```bash
|
||||
python hunyuan_image_minimal_inference.py \
|
||||
--dit "<path to hunyuanimage2.1.safetensors>" \
|
||||
--text_encoder "<path to qwen_2.5_vl_7b.safetensors>" \
|
||||
--byt5 "<path to byt5_small_glyphxl_fp16.safetensors>" \
|
||||
--vae "<path to hunyuan_image_2.1_vae_fp16.safetensors>" \
|
||||
--lora_weight "<path to your trained LoRA>" \
|
||||
--lora_multiplier 1.0 \
|
||||
--attn_mode "torch" \
|
||||
--prompt "A cute cartoon penguin in a snowy landscape" \
|
||||
--image_size 2048 2048 \
|
||||
--infer_steps 50 \
|
||||
--guidance_scale 3.5 \
|
||||
--flow_shift 5.0 \
|
||||
--seed 542017 \
|
||||
--save_path "output_image.png"
|
||||
```
|
||||
|
||||
**Key Options:**
|
||||
- `--fp8_scaled`: Use scaled FP8 format for reduced VRAM usage during inference
|
||||
- `--blocks_to_swap`: Swap blocks to CPU to reduce VRAM usage
|
||||
- `--image_size`: Resolution (inference is most stable at 2048x2048)
|
||||
- `--guidance_scale`: CFG scale (default: 3.5)
|
||||
- `--flow_shift`: Flow matching shift parameter (default: 5.0)
|
||||
- `--text_encoder_cpu`: Run the text encoders on CPU to reduce VRAM usage
|
||||
- `--vae_chunk_size`: Chunk size for VAE decoding to reduce memory usage (default: None, no chunking). 16 is recommended if enabled.
|
||||
|
||||
`--split_attn` is not supported (since inference is done one at a time). `--fp8_vl` is not supported, please use CPU for the text encoder if VRAM is insufficient.
|
||||
|
||||
<details>
|
||||
<summary>日本語</summary>
|
||||
|
||||
`hunyuan_image_minimal_inference.py`スクリプトを使用して、学習したLoRAモデルで画像を生成できます。基本的な使用例は英語のドキュメントを参照してください。
|
||||
|
||||
**主要なオプション:**
|
||||
- `--fp8_scaled`: VRAM使用量削減のためのスケールFP8形式
|
||||
- `--blocks_to_swap`: VRAM使用量削減のためのブロックスワップ
|
||||
- `--image_size`: 解像度（2048x2048で最も安定）
|
||||
- `--guidance_scale`: CFGスケール（推奨: 3.5）
|
||||
- `--flow_shift`: Flow Matchingシフトパラメータ（デフォルト: 5.0）
|
||||
- `--text_encoder_cpu`: テキストエンコーダをCPUで実行してVRAM使用量削減
|
||||
- `--vae_chunk_size`: VAEデコーディングのチャンクサイズ（デフォルト: None、チャンク処理なし）。有効にする場合は16を推奨。
|
||||
|
||||
`--split_attn`はサポートされていません（1件ずつ推論するため）。`--fp8_vl`もサポートされていません。VRAMが不足する場合はテキストエンコーダをCPUで実行してください。
|
||||
|
||||
</details>
|
||||
|
||||
## 9. Related Tools / 関連ツール
|
||||
|
||||
### `networks/convert_hunyuan_image_lora_to_comfy.py`
|
||||
|
||||
A script to convert LoRA models to ComfyUI-compatible format. The formats differ slightly, so conversion is necessary. You can convert from the sd-scripts format to ComfyUI format with:
|
||||
|
||||
```bash
|
||||
python networks/convert_hunyuan_image_lora_to_comfy.py path/to/source.safetensors path/to/destination.safetensors
|
||||
```
|
||||
|
||||
Using the `--reverse` option allows conversion in the opposite direction (ComfyUI format to sd-scripts format). However, reverse conversion is only possible for LoRAs converted by this script. LoRAs created with other training tools cannot be converted.
|
||||
|
||||
<details>
|
||||
<summary>日本語</summary>
|
||||
|
||||
**`networks/convert_hunyuan_image_lora_to_comfy.py`**
|
||||
|
||||
LoRAモデルをComfyUI互換形式に変換するスクリプト。わずかに形式が異なるため、変換が必要です。以下の指定で、sd-scriptsの形式からComfyUI形式に変換できます。
|
||||
|
||||
```bash
|
||||
python networks/convert_hunyuan_image_lora_to_comfy.py path/to/source.safetensors path/to/destination.safetensors
|
||||
```
|
||||
|
||||
`--reverse`オプションを付けると、逆変換（ComfyUI形式からsd-scripts形式）も可能です。ただし、逆変換ができるのはこのスクリプトで変換したLoRAに限ります。他の学習ツールで作成したLoRAは変換できません。
|
||||
|
||||
</details>
|
||||
|
||||
## 10. Others / その他
|
||||
|
||||
`hunyuan_image_train_network.py` includes many features common with `train_network.py`, such as sample image generation (`--sample_prompts`, etc.) and detailed optimizer settings. For these features, refer to the [`train_network.py` guide](train_network.md#5-other-features--その他の機能) or the script help (`python hunyuan_image_train_network.py --help`).
|
||||
|
||||
<details>
|
||||
<summary>日本語</summary>
|
||||
|
||||
`hunyuan_image_train_network.py`には、サンプル画像の生成 (`--sample_prompts`など) や詳細なオプティマイザ設定など、`train_network.py`と共通の機能も多く存在します。これらについては、[`train_network.py`のガイド](train_network.md#5-other-features--その他の機能)やスクリプトのヘルプ (`python hunyuan_image_train_network.py --help`) を参照してください。
|
||||
|
||||
</details>
|
||||
1233
hunyuan_image_minimal_inference.py
Normal file
1233
hunyuan_image_minimal_inference.py
Normal file
File diff suppressed because it is too large
Load Diff
710
hunyuan_image_train_network.py
Normal file
710
hunyuan_image_train_network.py
Normal file
@@ -0,0 +1,710 @@
|
||||
import argparse
|
||||
import copy
|
||||
import gc
|
||||
from typing import Any, Optional, Union, cast
|
||||
import argparse
|
||||
import os
|
||||
import time
|
||||
from types import SimpleNamespace
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from PIL import Image
|
||||
from accelerate import Accelerator, PartialState
|
||||
|
||||
from library import flux_utils, hunyuan_image_models, hunyuan_image_vae, strategy_base, train_util
|
||||
from library.device_utils import clean_memory_on_device, init_ipex
|
||||
|
||||
init_ipex()
|
||||
|
||||
import train_network
|
||||
from library import (
|
||||
flux_train_utils,
|
||||
hunyuan_image_models,
|
||||
hunyuan_image_text_encoder,
|
||||
hunyuan_image_utils,
|
||||
hunyuan_image_vae,
|
||||
sd3_train_utils,
|
||||
strategy_base,
|
||||
strategy_hunyuan_image,
|
||||
train_util,
|
||||
)
|
||||
from library.utils import setup_logging
|
||||
|
||||
setup_logging()
|
||||
import logging
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
# region sampling
|
||||
|
||||
|
||||
# TODO commonize with flux_utils
|
||||
def sample_images(
|
||||
accelerator: Accelerator,
|
||||
args: argparse.Namespace,
|
||||
epoch,
|
||||
steps,
|
||||
dit: hunyuan_image_models.HYImageDiffusionTransformer,
|
||||
vae,
|
||||
text_encoders,
|
||||
sample_prompts_te_outputs,
|
||||
prompt_replacement=None,
|
||||
):
|
||||
if steps == 0:
|
||||
if not args.sample_at_first:
|
||||
return
|
||||
else:
|
||||
if args.sample_every_n_steps is None and args.sample_every_n_epochs is None:
|
||||
return
|
||||
if args.sample_every_n_epochs is not None:
|
||||
# sample_every_n_steps は無視する
|
||||
if epoch is None or epoch % args.sample_every_n_epochs != 0:
|
||||
return
|
||||
else:
|
||||
if steps % args.sample_every_n_steps != 0 or epoch is not None: # steps is not divisible or end of epoch
|
||||
return
|
||||
|
||||
logger.info("")
|
||||
logger.info(f"generating sample images at step / サンプル画像生成 ステップ: {steps}")
|
||||
if not os.path.isfile(args.sample_prompts) and sample_prompts_te_outputs is None:
|
||||
logger.error(f"No prompt file / プロンプトファイルがありません: {args.sample_prompts}")
|
||||
return
|
||||
|
||||
distributed_state = PartialState() # for multi gpu distributed inference. this is a singleton, so it's safe to use it here
|
||||
|
||||
# unwrap unet and text_encoder(s)
|
||||
dit = accelerator.unwrap_model(dit)
|
||||
dit = cast(hunyuan_image_models.HYImageDiffusionTransformer, dit)
|
||||
dit.switch_block_swap_for_inference()
|
||||
if text_encoders is not None:
|
||||
text_encoders = [(accelerator.unwrap_model(te) if te is not None else None) for te in text_encoders]
|
||||
# print([(te.parameters().__next__().device if te is not None else None) for te in text_encoders])
|
||||
|
||||
prompts = train_util.load_prompts(args.sample_prompts)
|
||||
|
||||
save_dir = args.output_dir + "/sample"
|
||||
os.makedirs(save_dir, exist_ok=True)
|
||||
|
||||
# save random state to restore later
|
||||
rng_state = torch.get_rng_state()
|
||||
cuda_rng_state = None
|
||||
try:
|
||||
cuda_rng_state = torch.cuda.get_rng_state() if torch.cuda.is_available() else None
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
if distributed_state.num_processes <= 1:
|
||||
# If only one device is available, just use the original prompt list. We don't need to care about the distribution of prompts.
|
||||
with torch.no_grad(), accelerator.autocast():
|
||||
for prompt_dict in prompts:
|
||||
sample_image_inference(
|
||||
accelerator,
|
||||
args,
|
||||
dit,
|
||||
text_encoders,
|
||||
vae,
|
||||
save_dir,
|
||||
prompt_dict,
|
||||
epoch,
|
||||
steps,
|
||||
sample_prompts_te_outputs,
|
||||
prompt_replacement,
|
||||
)
|
||||
else:
|
||||
# Creating list with N elements, where each element is a list of prompt_dicts, and N is the number of processes available (number of devices available)
|
||||
# prompt_dicts are assigned to lists based on order of processes, to attempt to time the image creation time to match enum order. Probably only works when steps and sampler are identical.
|
||||
per_process_prompts = [] # list of lists
|
||||
for i in range(distributed_state.num_processes):
|
||||
per_process_prompts.append(prompts[i :: distributed_state.num_processes])
|
||||
|
||||
with torch.no_grad():
|
||||
with distributed_state.split_between_processes(per_process_prompts) as prompt_dict_lists:
|
||||
for prompt_dict in prompt_dict_lists[0]:
|
||||
sample_image_inference(
|
||||
accelerator,
|
||||
args,
|
||||
dit,
|
||||
text_encoders,
|
||||
vae,
|
||||
save_dir,
|
||||
prompt_dict,
|
||||
epoch,
|
||||
steps,
|
||||
sample_prompts_te_outputs,
|
||||
prompt_replacement,
|
||||
)
|
||||
|
||||
torch.set_rng_state(rng_state)
|
||||
if cuda_rng_state is not None:
|
||||
torch.cuda.set_rng_state(cuda_rng_state)
|
||||
|
||||
dit.switch_block_swap_for_training()
|
||||
clean_memory_on_device(accelerator.device)
|
||||
|
||||
|
||||
def sample_image_inference(
|
||||
accelerator: Accelerator,
|
||||
args: argparse.Namespace,
|
||||
dit: hunyuan_image_models.HYImageDiffusionTransformer,
|
||||
text_encoders: Optional[list[nn.Module]],
|
||||
vae: hunyuan_image_vae.HunyuanVAE2D,
|
||||
save_dir,
|
||||
prompt_dict,
|
||||
epoch,
|
||||
steps,
|
||||
sample_prompts_te_outputs,
|
||||
prompt_replacement,
|
||||
):
|
||||
assert isinstance(prompt_dict, dict)
|
||||
negative_prompt = prompt_dict.get("negative_prompt")
|
||||
sample_steps = prompt_dict.get("sample_steps", 20)
|
||||
width = prompt_dict.get("width", 512)
|
||||
height = prompt_dict.get("height", 512)
|
||||
cfg_scale = prompt_dict.get("scale", 3.5)
|
||||
seed = prompt_dict.get("seed")
|
||||
prompt: str = prompt_dict.get("prompt", "")
|
||||
flow_shift: float = prompt_dict.get("flow_shift", 5.0)
|
||||
# sampler_name: str = prompt_dict.get("sample_sampler", args.sample_sampler)
|
||||
|
||||
if prompt_replacement is not None:
|
||||
prompt = prompt.replace(prompt_replacement[0], prompt_replacement[1])
|
||||
if negative_prompt is not None:
|
||||
negative_prompt = negative_prompt.replace(prompt_replacement[0], prompt_replacement[1])
|
||||
|
||||
if seed is not None:
|
||||
torch.manual_seed(seed)
|
||||
torch.cuda.manual_seed(seed)
|
||||
else:
|
||||
# True random sample image generation
|
||||
torch.seed()
|
||||
torch.cuda.seed()
|
||||
|
||||
if negative_prompt is None:
|
||||
negative_prompt = ""
|
||||
height = max(64, height - height % 16) # round to divisible by 16
|
||||
width = max(64, width - width % 16) # round to divisible by 16
|
||||
logger.info(f"prompt: {prompt}")
|
||||
if cfg_scale != 1.0:
|
||||
logger.info(f"negative_prompt: {negative_prompt}")
|
||||
elif negative_prompt != "":
|
||||
logger.info(f"negative prompt is ignored because scale is 1.0")
|
||||
logger.info(f"height: {height}")
|
||||
logger.info(f"width: {width}")
|
||||
logger.info(f"sample_steps: {sample_steps}")
|
||||
if cfg_scale != 1.0:
|
||||
logger.info(f"CFG scale: {cfg_scale}")
|
||||
logger.info(f"flow_shift: {flow_shift}")
|
||||
# logger.info(f"sample_sampler: {sampler_name}")
|
||||
if seed is not None:
|
||||
logger.info(f"seed: {seed}")
|
||||
|
||||
# encode prompts
|
||||
tokenize_strategy = strategy_base.TokenizeStrategy.get_strategy()
|
||||
encoding_strategy = strategy_base.TextEncodingStrategy.get_strategy()
|
||||
|
||||
def encode_prompt(prpt):
|
||||
text_encoder_conds = []
|
||||
if sample_prompts_te_outputs and prpt in sample_prompts_te_outputs:
|
||||
text_encoder_conds = sample_prompts_te_outputs[prpt]
|
||||
# print(f"Using cached text encoder outputs for prompt: {prpt}")
|
||||
if text_encoders is not None:
|
||||
# print(f"Encoding prompt: {prpt}")
|
||||
tokens_and_masks = tokenize_strategy.tokenize(prpt)
|
||||
encoded_text_encoder_conds = encoding_strategy.encode_tokens(tokenize_strategy, text_encoders, tokens_and_masks)
|
||||
|
||||
# if text_encoder_conds is not cached, use encoded_text_encoder_conds
|
||||
if len(text_encoder_conds) == 0:
|
||||
text_encoder_conds = encoded_text_encoder_conds
|
||||
else:
|
||||
# if encoded_text_encoder_conds is not None, update cached text_encoder_conds
|
||||
for i in range(len(encoded_text_encoder_conds)):
|
||||
if encoded_text_encoder_conds[i] is not None:
|
||||
text_encoder_conds[i] = encoded_text_encoder_conds[i]
|
||||
return text_encoder_conds
|
||||
|
||||
vl_embed, vl_mask, byt5_embed, byt5_mask, ocr_mask = encode_prompt(prompt)
|
||||
arg_c = {
|
||||
"embed": vl_embed,
|
||||
"mask": vl_mask,
|
||||
"embed_byt5": byt5_embed,
|
||||
"mask_byt5": byt5_mask,
|
||||
"ocr_mask": ocr_mask,
|
||||
"prompt": prompt,
|
||||
}
|
||||
|
||||
# encode negative prompts
|
||||
if cfg_scale != 1.0:
|
||||
neg_vl_embed, neg_vl_mask, neg_byt5_embed, neg_byt5_mask, neg_ocr_mask = encode_prompt(negative_prompt)
|
||||
arg_c_null = {
|
||||
"embed": neg_vl_embed,
|
||||
"mask": neg_vl_mask,
|
||||
"embed_byt5": neg_byt5_embed,
|
||||
"mask_byt5": neg_byt5_mask,
|
||||
"ocr_mask": neg_ocr_mask,
|
||||
"prompt": negative_prompt,
|
||||
}
|
||||
else:
|
||||
arg_c_null = None
|
||||
|
||||
gen_args = SimpleNamespace(
|
||||
image_size=(height, width), infer_steps=sample_steps, flow_shift=flow_shift, guidance_scale=cfg_scale, fp8=args.fp8_scaled
|
||||
)
|
||||
|
||||
from hunyuan_image_minimal_inference import generate_body # import here to avoid circular import
|
||||
|
||||
dit_is_training = dit.training
|
||||
dit.eval()
|
||||
x = generate_body(gen_args, dit, arg_c, arg_c_null, accelerator.device, seed)
|
||||
if dit_is_training:
|
||||
dit.train()
|
||||
clean_memory_on_device(accelerator.device)
|
||||
|
||||
# latent to image
|
||||
org_vae_device = vae.device # will be on cpu
|
||||
vae.to(accelerator.device) # distributed_state.device is same as accelerator.device
|
||||
with torch.no_grad():
|
||||
x = x / vae.scaling_factor
|
||||
x = vae.decode(x.to(vae.device, dtype=vae.dtype))
|
||||
vae.to(org_vae_device)
|
||||
|
||||
clean_memory_on_device(accelerator.device)
|
||||
|
||||
x = x.clamp(-1, 1)
|
||||
x = x.permute(0, 2, 3, 1)
|
||||
image = Image.fromarray((127.5 * (x + 1.0)).float().cpu().numpy().astype(np.uint8)[0])
|
||||
|
||||
# adding accelerator.wait_for_everyone() here should sync up and ensure that sample images are saved in the same order as the original prompt list
|
||||
# but adding 'enum' to the filename should be enough
|
||||
|
||||
ts_str = time.strftime("%Y%m%d%H%M%S", time.localtime())
|
||||
num_suffix = f"e{epoch:06d}" if epoch is not None else f"{steps:06d}"
|
||||
seed_suffix = "" if seed is None else f"_{seed}"
|
||||
i: int = prompt_dict["enum"]
|
||||
img_filename = f"{'' if args.output_name is None else args.output_name + '_'}{num_suffix}_{i:02d}_{ts_str}{seed_suffix}.png"
|
||||
image.save(os.path.join(save_dir, img_filename))
|
||||
|
||||
# send images to wandb if enabled
|
||||
if "wandb" in [tracker.name for tracker in accelerator.trackers]:
|
||||
wandb_tracker = accelerator.get_tracker("wandb")
|
||||
|
||||
import wandb
|
||||
|
||||
# not to commit images to avoid inconsistency between training and logging steps
|
||||
wandb_tracker.log({f"sample_{i}": wandb.Image(image, caption=prompt)}, commit=False) # positive prompt as a caption
|
||||
|
||||
|
||||
# endregion
|
||||
|
||||
|
||||
class HunyuanImageNetworkTrainer(train_network.NetworkTrainer):
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.sample_prompts_te_outputs = None
|
||||
self.is_swapping_blocks: bool = False
|
||||
self.rotary_pos_emb_cache = {}
|
||||
|
||||
def assert_extra_args(
|
||||
self,
|
||||
args,
|
||||
train_dataset_group: Union[train_util.DatasetGroup, train_util.MinimalDataset],
|
||||
val_dataset_group: Optional[train_util.DatasetGroup],
|
||||
):
|
||||
super().assert_extra_args(args, train_dataset_group, val_dataset_group)
|
||||
# sdxl_train_util.verify_sdxl_training_args(args)
|
||||
|
||||
if args.mixed_precision == "fp16":
|
||||
logger.warning(
|
||||
"mixed_precision bf16 is recommended for HunyuanImage-2.1 / HunyuanImage-2.1ではmixed_precision bf16が推奨されます"
|
||||
)
|
||||
|
||||
if (args.fp8_base or args.fp8_base_unet) and not args.fp8_scaled:
|
||||
logger.warning(
|
||||
"fp8_base and fp8_base_unet are not supported. Use fp8_scaled instead / fp8_baseとfp8_base_unetはサポートされていません。代わりにfp8_scaledを使用してください"
|
||||
)
|
||||
if args.fp8_scaled and (args.fp8_base or args.fp8_base_unet):
|
||||
logger.info(
|
||||
"fp8_scaled is used, so fp8_base and fp8_base_unet are ignored / fp8_scaledが使われているので、fp8_baseとfp8_base_unetは無視されます"
|
||||
)
|
||||
args.fp8_base = False
|
||||
args.fp8_base_unet = False
|
||||
|
||||
if args.cache_text_encoder_outputs_to_disk and not args.cache_text_encoder_outputs:
|
||||
logger.warning(
|
||||
"cache_text_encoder_outputs_to_disk is enabled, so cache_text_encoder_outputs is also enabled / cache_text_encoder_outputs_to_diskが有効になっているため、cache_text_encoder_outputsも有効になります"
|
||||
)
|
||||
args.cache_text_encoder_outputs = True
|
||||
|
||||
if args.cache_text_encoder_outputs:
|
||||
assert (
|
||||
train_dataset_group.is_text_encoder_output_cacheable()
|
||||
), "when caching Text Encoder output, either caption_dropout_rate, shuffle_caption, token_warmup_step or caption_tag_dropout_rate cannot be used / Text Encoderの出力をキャッシュするときはcaption_dropout_rate, shuffle_caption, token_warmup_step, caption_tag_dropout_rateは使えません"
|
||||
|
||||
train_dataset_group.verify_bucket_reso_steps(32)
|
||||
if val_dataset_group is not None:
|
||||
val_dataset_group.verify_bucket_reso_steps(32)
|
||||
|
||||
def load_target_model(self, args, weight_dtype, accelerator):
|
||||
self.is_swapping_blocks = args.blocks_to_swap is not None and args.blocks_to_swap > 0
|
||||
|
||||
vl_dtype = torch.float8_e4m3fn if args.fp8_vl else torch.bfloat16
|
||||
vl_device = "cpu" # loading to cpu and move to gpu later in cache_text_encoder_outputs_if_needed
|
||||
_, text_encoder_vlm = hunyuan_image_text_encoder.load_qwen2_5_vl(
|
||||
args.text_encoder, dtype=vl_dtype, device=vl_device, disable_mmap=args.disable_mmap_load_safetensors
|
||||
)
|
||||
_, text_encoder_byt5 = hunyuan_image_text_encoder.load_byt5(
|
||||
args.byt5, dtype=torch.float16, device=vl_device, disable_mmap=args.disable_mmap_load_safetensors
|
||||
)
|
||||
|
||||
vae = hunyuan_image_vae.load_vae(
|
||||
args.vae, "cpu", disable_mmap=args.disable_mmap_load_safetensors, chunk_size=args.vae_chunk_size
|
||||
)
|
||||
vae.to(dtype=torch.float16) # VAE is always fp16
|
||||
vae.eval()
|
||||
|
||||
model_version = hunyuan_image_utils.MODEL_VERSION_2_1
|
||||
return model_version, [text_encoder_vlm, text_encoder_byt5], vae, None # unet will be loaded later
|
||||
|
||||
def load_unet_lazily(self, args, weight_dtype, accelerator, text_encoders) -> tuple[nn.Module, list[nn.Module]]:
|
||||
if args.cache_text_encoder_outputs:
|
||||
logger.info("Replace text encoders with dummy models to save memory")
|
||||
|
||||
# This doesn't free memory, so we move text encoders to meta device in cache_text_encoder_outputs_if_needed
|
||||
text_encoders = [flux_utils.dummy_clip_l() for _ in text_encoders]
|
||||
clean_memory_on_device(accelerator.device)
|
||||
gc.collect()
|
||||
|
||||
loading_dtype = None if args.fp8_scaled else weight_dtype
|
||||
loading_device = "cpu" if self.is_swapping_blocks else accelerator.device
|
||||
|
||||
attn_mode = "torch"
|
||||
if args.xformers:
|
||||
attn_mode = "xformers"
|
||||
if args.attn_mode is not None:
|
||||
attn_mode = args.attn_mode
|
||||
|
||||
logger.info(f"Loading DiT model with attn_mode: {attn_mode}, split_attn: {args.split_attn}, fp8_scaled: {args.fp8_scaled}")
|
||||
model = hunyuan_image_models.load_hunyuan_image_model(
|
||||
accelerator.device,
|
||||
args.pretrained_model_name_or_path,
|
||||
attn_mode,
|
||||
args.split_attn,
|
||||
loading_device,
|
||||
loading_dtype,
|
||||
args.fp8_scaled,
|
||||
)
|
||||
|
||||
if self.is_swapping_blocks:
|
||||
# Swap blocks between CPU and GPU to reduce memory usage, in forward and backward passes.
|
||||
logger.info(f"enable block swap: blocks_to_swap={args.blocks_to_swap}")
|
||||
model.enable_block_swap(args.blocks_to_swap, accelerator.device, supports_backward=True)
|
||||
|
||||
return model, text_encoders
|
||||
|
||||
def get_tokenize_strategy(self, args):
|
||||
return strategy_hunyuan_image.HunyuanImageTokenizeStrategy(args.tokenizer_cache_dir)
|
||||
|
||||
def get_tokenizers(self, tokenize_strategy: strategy_hunyuan_image.HunyuanImageTokenizeStrategy):
|
||||
return [tokenize_strategy.vlm_tokenizer, tokenize_strategy.byt5_tokenizer]
|
||||
|
||||
def get_latents_caching_strategy(self, args):
|
||||
return strategy_hunyuan_image.HunyuanImageLatentsCachingStrategy(args.cache_latents_to_disk, args.vae_batch_size, False)
|
||||
|
||||
def get_text_encoding_strategy(self, args):
|
||||
return strategy_hunyuan_image.HunyuanImageTextEncodingStrategy()
|
||||
|
||||
def post_process_network(self, args, accelerator, network, text_encoders, unet):
|
||||
pass
|
||||
|
||||
def get_models_for_text_encoding(self, args, accelerator, text_encoders):
|
||||
if args.cache_text_encoder_outputs:
|
||||
return None # no text encoders are needed for encoding because both are cached
|
||||
else:
|
||||
return text_encoders
|
||||
|
||||
def get_text_encoders_train_flags(self, args, text_encoders):
|
||||
# HunyuanImage-2.1 does not support training VLM or byT5
|
||||
return [False, False]
|
||||
|
||||
def get_text_encoder_outputs_caching_strategy(self, args):
|
||||
if args.cache_text_encoder_outputs:
|
||||
return strategy_hunyuan_image.HunyuanImageTextEncoderOutputsCachingStrategy(
|
||||
args.cache_text_encoder_outputs_to_disk, args.text_encoder_batch_size, args.skip_cache_check, False
|
||||
)
|
||||
else:
|
||||
return None
|
||||
|
||||
def cache_text_encoder_outputs_if_needed(
|
||||
self, args, accelerator: Accelerator, unet, vae, text_encoders, dataset: train_util.DatasetGroup, weight_dtype
|
||||
):
|
||||
vlm_device = "cpu" if args.text_encoder_cpu else accelerator.device
|
||||
if args.cache_text_encoder_outputs:
|
||||
if not args.lowram:
|
||||
# メモリ消費を減らす
|
||||
logger.info("move vae to cpu to save memory")
|
||||
org_vae_device = vae.device
|
||||
vae.to("cpu")
|
||||
clean_memory_on_device(accelerator.device)
|
||||
|
||||
logger.info(f"move text encoders to {vlm_device} to encode and cache text encoder outputs")
|
||||
text_encoders[0].to(vlm_device)
|
||||
text_encoders[1].to(vlm_device)
|
||||
|
||||
# VLM (bf16) and byT5 (fp16) are used for encoding, so we cannot use autocast here
|
||||
dataset.new_cache_text_encoder_outputs(text_encoders, accelerator)
|
||||
|
||||
# cache sample prompts
|
||||
if args.sample_prompts is not None:
|
||||
logger.info(f"cache Text Encoder outputs for sample prompt: {args.sample_prompts}")
|
||||
|
||||
tokenize_strategy: strategy_hunyuan_image.HunyuanImageTokenizeStrategy = (
|
||||
strategy_base.TokenizeStrategy.get_strategy()
|
||||
)
|
||||
text_encoding_strategy: strategy_hunyuan_image.HunyuanImageTextEncodingStrategy = (
|
||||
strategy_base.TextEncodingStrategy.get_strategy()
|
||||
)
|
||||
|
||||
prompts = train_util.load_prompts(args.sample_prompts)
|
||||
sample_prompts_te_outputs = {} # key: prompt, value: text encoder outputs
|
||||
with accelerator.autocast(), torch.no_grad():
|
||||
for prompt_dict in prompts:
|
||||
for p in [prompt_dict.get("prompt", ""), prompt_dict.get("negative_prompt", "")]:
|
||||
if p not in sample_prompts_te_outputs:
|
||||
logger.info(f"cache Text Encoder outputs for prompt: {p}")
|
||||
tokens_and_masks = tokenize_strategy.tokenize(p)
|
||||
sample_prompts_te_outputs[p] = text_encoding_strategy.encode_tokens(
|
||||
tokenize_strategy, text_encoders, tokens_and_masks
|
||||
)
|
||||
self.sample_prompts_te_outputs = sample_prompts_te_outputs
|
||||
|
||||
accelerator.wait_for_everyone()
|
||||
|
||||
# text encoders are not needed for training, so we move to meta device
|
||||
logger.info("move text encoders to meta device to save memory")
|
||||
text_encoders = [te.to("meta") for te in text_encoders]
|
||||
clean_memory_on_device(accelerator.device)
|
||||
|
||||
if not args.lowram:
|
||||
logger.info("move vae back to original device")
|
||||
vae.to(org_vae_device)
|
||||
else:
|
||||
# Text Encoderから毎回出力を取得するので、GPUに乗せておく
|
||||
text_encoders[0].to(vlm_device)
|
||||
text_encoders[1].to(vlm_device)
|
||||
|
||||
def sample_images(self, accelerator, args, epoch, global_step, device, ae, tokenizer, text_encoder, flux):
|
||||
text_encoders = text_encoder # for compatibility
|
||||
text_encoders = self.get_models_for_text_encoding(args, accelerator, text_encoders)
|
||||
|
||||
sample_images(accelerator, args, epoch, global_step, flux, ae, text_encoders, self.sample_prompts_te_outputs)
|
||||
|
||||
def get_noise_scheduler(self, args: argparse.Namespace, device: torch.device) -> Any:
|
||||
noise_scheduler = sd3_train_utils.FlowMatchEulerDiscreteScheduler(num_train_timesteps=1000, shift=args.discrete_flow_shift)
|
||||
self.noise_scheduler_copy = copy.deepcopy(noise_scheduler)
|
||||
return noise_scheduler
|
||||
|
||||
def encode_images_to_latents(self, args, vae: hunyuan_image_vae.HunyuanVAE2D, images):
|
||||
return vae.encode(images).sample()
|
||||
|
||||
def shift_scale_latents(self, args, latents):
|
||||
# for encoding, we need to scale the latents
|
||||
return latents * hunyuan_image_vae.LATENT_SCALING_FACTOR
|
||||
|
||||
def get_noise_pred_and_target(
|
||||
self,
|
||||
args,
|
||||
accelerator,
|
||||
noise_scheduler,
|
||||
latents,
|
||||
batch,
|
||||
text_encoder_conds,
|
||||
unet: hunyuan_image_models.HYImageDiffusionTransformer,
|
||||
network,
|
||||
weight_dtype,
|
||||
train_unet,
|
||||
is_train=True,
|
||||
):
|
||||
# Sample noise that we'll add to the latents
|
||||
noise = torch.randn_like(latents)
|
||||
|
||||
# get noisy model input and timesteps
|
||||
noisy_model_input, _, sigmas = flux_train_utils.get_noisy_model_input_and_timesteps(
|
||||
args, noise_scheduler, latents, noise, accelerator.device, weight_dtype
|
||||
)
|
||||
# bfloat16 is too low precision for 0-1000 TODO fix get_noisy_model_input_and_timesteps
|
||||
timesteps = (sigmas[:, 0, 0, 0] * 1000).to(torch.int64)
|
||||
# print(
|
||||
# f"timestep: {timesteps}, noisy_model_input shape: {noisy_model_input.shape}, mean: {noisy_model_input.mean()}, std: {noisy_model_input.std()}"
|
||||
# )
|
||||
|
||||
if args.gradient_checkpointing:
|
||||
noisy_model_input.requires_grad_(True)
|
||||
for t in text_encoder_conds:
|
||||
if t is not None and t.dtype.is_floating_point:
|
||||
t.requires_grad_(True)
|
||||
|
||||
# Predict the noise residual
|
||||
# ocr_mask is for inference only, so it is not used here
|
||||
vlm_embed, vlm_mask, byt5_embed, byt5_mask, ocr_mask = text_encoder_conds
|
||||
|
||||
# print(f"embed shape: {vlm_embed.shape}, mean: {vlm_embed.mean()}, std: {vlm_embed.std()}")
|
||||
# print(f"embed_byt5 shape: {byt5_embed.shape}, mean: {byt5_embed.mean()}, std: {byt5_embed.std()}")
|
||||
# print(f"latents shape: {latents.shape}, mean: {latents.mean()}, std: {latents.std()}")
|
||||
# print(f"mask shape: {vlm_mask.shape}, sum: {vlm_mask.sum()}")
|
||||
# print(f"mask_byt5 shape: {byt5_mask.shape}, sum: {byt5_mask.sum()}")
|
||||
with torch.set_grad_enabled(is_train), accelerator.autocast():
|
||||
model_pred = unet(
|
||||
noisy_model_input, timesteps, vlm_embed, vlm_mask, byt5_embed, byt5_mask # , self.rotary_pos_emb_cache
|
||||
)
|
||||
|
||||
# apply model prediction type
|
||||
model_pred, weighting = flux_train_utils.apply_model_prediction_type(args, model_pred, noisy_model_input, sigmas)
|
||||
|
||||
# flow matching loss
|
||||
target = noise - latents
|
||||
|
||||
# differential output preservation is not used for HunyuanImage-2.1 currently
|
||||
|
||||
return model_pred, target, timesteps, weighting
|
||||
|
||||
def post_process_loss(self, loss, args, timesteps, noise_scheduler):
|
||||
return loss
|
||||
|
||||
def get_sai_model_spec(self, args):
|
||||
return train_util.get_sai_model_spec_dataclass(None, args, False, True, False, hunyuan_image="2.1").to_metadata_dict()
|
||||
|
||||
def update_metadata(self, metadata, args):
|
||||
metadata["ss_logit_mean"] = args.logit_mean
|
||||
metadata["ss_logit_std"] = args.logit_std
|
||||
metadata["ss_mode_scale"] = args.mode_scale
|
||||
metadata["ss_timestep_sampling"] = args.timestep_sampling
|
||||
metadata["ss_sigmoid_scale"] = args.sigmoid_scale
|
||||
metadata["ss_model_prediction_type"] = args.model_prediction_type
|
||||
metadata["ss_discrete_flow_shift"] = args.discrete_flow_shift
|
||||
|
||||
def is_text_encoder_not_needed_for_training(self, args):
|
||||
return args.cache_text_encoder_outputs and not self.is_train_text_encoder(args)
|
||||
|
||||
def prepare_text_encoder_grad_ckpt_workaround(self, index, text_encoder):
|
||||
# do not support text encoder training for HunyuanImage-2.1
|
||||
pass
|
||||
|
||||
def cast_text_encoder(self, args):
|
||||
return False # VLM is bf16, byT5 is fp16, so do not cast to other dtype
|
||||
|
||||
def cast_vae(self, args):
|
||||
return False # VAE is fp16, so do not cast to other dtype
|
||||
|
||||
def cast_unet(self, args):
|
||||
return not args.fp8_scaled # if fp8_scaled is used, do not cast to other dtype
|
||||
|
||||
def prepare_text_encoder_fp8(self, index, text_encoder, te_weight_dtype, weight_dtype):
|
||||
# fp8 text encoder for HunyuanImage-2.1 is not supported currently
|
||||
pass
|
||||
|
||||
def on_validation_step_end(self, args, accelerator, network, text_encoders, unet, batch, weight_dtype):
|
||||
if self.is_swapping_blocks:
|
||||
# prepare for next forward: because backward pass is not called, we need to prepare it here
|
||||
accelerator.unwrap_model(unet).prepare_block_swap_before_forward()
|
||||
|
||||
def prepare_unet_with_accelerator(
|
||||
self, args: argparse.Namespace, accelerator: Accelerator, unet: torch.nn.Module
|
||||
) -> torch.nn.Module:
|
||||
if not self.is_swapping_blocks:
|
||||
return super().prepare_unet_with_accelerator(args, accelerator, unet)
|
||||
|
||||
# if we doesn't swap blocks, we can move the model to device
|
||||
model: hunyuan_image_models.HYImageDiffusionTransformer = unet
|
||||
model = accelerator.prepare(model, device_placement=[not self.is_swapping_blocks])
|
||||
accelerator.unwrap_model(model).move_to_device_except_swap_blocks(accelerator.device) # reduce peak memory usage
|
||||
accelerator.unwrap_model(model).prepare_block_swap_before_forward()
|
||||
|
||||
return model
|
||||
|
||||
|
||||
def setup_parser() -> argparse.ArgumentParser:
|
||||
parser = train_network.setup_parser()
|
||||
train_util.add_dit_training_arguments(parser)
|
||||
|
||||
parser.add_argument(
|
||||
"--text_encoder",
|
||||
type=str,
|
||||
help="path to Qwen2.5-VL (*.sft or *.safetensors), should be bfloat16 / Qwen2.5-VLのパス（*.sftまたは*.safetensors）、bfloat16が前提",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--byt5",
|
||||
type=str,
|
||||
help="path to byt5 (*.sft or *.safetensors), should be float16 / byt5のパス（*.sftまたは*.safetensors）、float16が前提",
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"--timestep_sampling",
|
||||
choices=["sigma", "uniform", "sigmoid", "shift", "flux_shift"],
|
||||
default="sigma",
|
||||
help="Method to sample timesteps: sigma-based, uniform random, sigmoid of random normal, shift of sigmoid and FLUX.1 shifting."
|
||||
" / タイムステップをサンプリングする方法：sigma、random uniform、random normalのsigmoid、sigmoidのシフト、FLUX.1のシフト。",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--sigmoid_scale",
|
||||
type=float,
|
||||
default=1.0,
|
||||
help='Scale factor for sigmoid timestep sampling (only used when timestep-sampling is "sigmoid"). / sigmoidタイムステップサンプリングの倍率（timestep-samplingが"sigmoid"の場合のみ有効）。',
|
||||
)
|
||||
parser.add_argument(
|
||||
"--model_prediction_type",
|
||||
choices=["raw", "additive", "sigma_scaled"],
|
||||
default="raw",
|
||||
help="How to interpret and process the model prediction: "
|
||||
"raw (use as is), additive (add to noisy input), sigma_scaled (apply sigma scaling). Default is raw unlike FLUX.1."
|
||||
" / モデル予測の解釈と処理方法："
|
||||
"raw（そのまま使用）、additive（ノイズ入力に加算）、sigma_scaled（シグマスケーリングを適用）。デフォルトはFLUX.1とは異なりrawです。",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--discrete_flow_shift",
|
||||
type=float,
|
||||
default=5.0,
|
||||
help="Discrete flow shift for the Euler Discrete Scheduler, default is 5.0. / Euler Discrete Schedulerの離散フローシフト、デフォルトは5.0。",
|
||||
)
|
||||
parser.add_argument("--fp8_scaled", action="store_true", help="Use scaled fp8 for DiT / DiTにスケーリングされたfp8を使う")
|
||||
parser.add_argument("--fp8_vl", action="store_true", help="Use fp8 for VLM text encoder / VLMテキストエンコーダにfp8を使用する")
|
||||
parser.add_argument(
|
||||
"--text_encoder_cpu", action="store_true", help="Inference on CPU for Text Encoders / テキストエンコーダをCPUで推論する"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--vae_chunk_size",
|
||||
type=int,
|
||||
default=None, # default is None (no chunking)
|
||||
help="Chunk size for VAE decoding to reduce memory usage. Default is None (no chunking). 16 is recommended if enabled"
|
||||
" / メモリ使用量を減らすためのVAEデコードのチャンクサイズ。デフォルトはNone（チャンクなし）。有効にする場合は16程度を推奨。",
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"--attn_mode",
|
||||
choices=["torch", "xformers", "flash", "sageattn", "sdpa"], # "sdpa" is for backward compatibility
|
||||
default=None,
|
||||
help="Attention implementation to use. Default is None (torch). xformers requires --split_attn. sageattn does not support training (inference only). This option overrides --xformers or --sdpa."
|
||||
" / 使用するAttentionの実装。デフォルトはNone（torch）です。xformersは--split_attnの指定が必要です。sageattnはトレーニングをサポートしていません（推論のみ）。このオプションは--xformersまたは--sdpaを上書きします。",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--split_attn",
|
||||
action="store_true",
|
||||
help="split attention computation to reduce memory usage / メモリ使用量を減らすためにattention時にバッチを分割する",
|
||||
)
|
||||
|
||||
return parser
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = setup_parser()
|
||||
|
||||
args = parser.parse_args()
|
||||
train_util.verify_command_line_training_args(args)
|
||||
args = train_util.read_config_from_file(args, parser)
|
||||
|
||||
if args.attn_mode == "sdpa":
|
||||
args.attn_mode = "torch" # backward compatibility
|
||||
|
||||
trainer = HunyuanImageNetworkTrainer()
|
||||
trainer.train(args)
|
||||
260
library/attention.py
Normal file
260
library/attention.py
Normal file
@@ -0,0 +1,260 @@
|
||||
# Unified attention function supporting various implementations
|
||||
|
||||
from dataclasses import dataclass
|
||||
import torch
|
||||
from typing import Optional, Union
|
||||
|
||||
try:
|
||||
import flash_attn
|
||||
from flash_attn.flash_attn_interface import _flash_attn_forward
|
||||
from flash_attn.flash_attn_interface import flash_attn_varlen_func
|
||||
from flash_attn.flash_attn_interface import flash_attn_func
|
||||
except ImportError:
|
||||
flash_attn = None
|
||||
flash_attn_varlen_func = None
|
||||
_flash_attn_forward = None
|
||||
flash_attn_func = None
|
||||
|
||||
try:
|
||||
from sageattention import sageattn_varlen, sageattn
|
||||
except ImportError:
|
||||
sageattn_varlen = None
|
||||
sageattn = None
|
||||
|
||||
try:
|
||||
import xformers.ops as xops
|
||||
except ImportError:
|
||||
xops = None
|
||||
|
||||
|
||||
@dataclass
|
||||
class AttentionParams:
|
||||
attn_mode: Optional[str] = None
|
||||
split_attn: bool = False
|
||||
img_len: Optional[int] = None
|
||||
attention_mask: Optional[torch.Tensor] = None
|
||||
seqlens: Optional[torch.Tensor] = None
|
||||
cu_seqlens: Optional[torch.Tensor] = None
|
||||
max_seqlen: Optional[int] = None
|
||||
|
||||
@staticmethod
|
||||
def create_attention_params(attn_mode: Optional[str], split_attn: bool) -> "AttentionParams":
|
||||
return AttentionParams(attn_mode, split_attn)
|
||||
|
||||
@staticmethod
|
||||
def create_attention_params_from_mask(
|
||||
attn_mode: Optional[str], split_attn: bool, img_len: Optional[int], attention_mask: Optional[torch.Tensor]
|
||||
) -> "AttentionParams":
|
||||
if attention_mask is None:
|
||||
# No attention mask provided: assume all tokens are valid
|
||||
return AttentionParams(attn_mode, split_attn, None, None, None, None, None)
|
||||
else:
|
||||
# Note: attention_mask is only for text tokens, not including image tokens
|
||||
seqlens = attention_mask.sum(dim=1).to(torch.int32) + img_len # [B]
|
||||
max_seqlen = attention_mask.shape[1] + img_len
|
||||
|
||||
if split_attn:
|
||||
# cu_seqlens is not needed for split attention
|
||||
return AttentionParams(attn_mode, split_attn, img_len, attention_mask, seqlens, None, max_seqlen)
|
||||
|
||||
# Convert attention mask to cumulative sequence lengths for flash attention
|
||||
batch_size = attention_mask.shape[0]
|
||||
cu_seqlens = torch.zeros([2 * batch_size + 1], dtype=torch.int32, device=attention_mask.device)
|
||||
for i in range(batch_size):
|
||||
cu_seqlens[2 * i + 1] = i * max_seqlen + seqlens[i] # end of valid tokens for query
|
||||
cu_seqlens[2 * i + 2] = (i + 1) * max_seqlen # end of all tokens for query
|
||||
|
||||
# Expand attention mask to include image tokens
|
||||
attention_mask = torch.nn.functional.pad(attention_mask, (img_len, 0), value=1) # [B, img_len + L]
|
||||
|
||||
if attn_mode == "xformers":
|
||||
seqlens_list = seqlens.cpu().tolist()
|
||||
attention_mask = xops.fmha.attn_bias.BlockDiagonalMask.from_seqlens(
|
||||
seqlens_list, seqlens_list, device=attention_mask.device
|
||||
)
|
||||
elif attn_mode == "torch":
|
||||
attention_mask = attention_mask[:, None, None, :].to(torch.bool) # [B, 1, 1, img_len + L]
|
||||
|
||||
return AttentionParams(attn_mode, split_attn, img_len, attention_mask, seqlens, cu_seqlens, max_seqlen)
|
||||
|
||||
|
||||
def attention(
|
||||
qkv_or_q: Union[torch.Tensor, list],
|
||||
k: Optional[torch.Tensor] = None,
|
||||
v: Optional[torch.Tensor] = None,
|
||||
attn_params: Optional[AttentionParams] = None,
|
||||
drop_rate: float = 0.0,
|
||||
) -> torch.Tensor:
|
||||
"""
|
||||
Compute scaled dot-product attention with variable sequence lengths.
|
||||
|
||||
Handles batches with different sequence lengths by splitting and
|
||||
processing each sequence individually.
|
||||
|
||||
Args:
|
||||
qkv_or_q: Query tensor [B, L, H, D]. or list of such tensors.
|
||||
k: Key tensor [B, L, H, D].
|
||||
v: Value tensor [B, L, H, D].
|
||||
attn_param: Attention parameters including mask and sequence lengths.
|
||||
drop_rate: Attention dropout rate.
|
||||
|
||||
Returns:
|
||||
Attention output tensor [B, L, H*D].
|
||||
"""
|
||||
if isinstance(qkv_or_q, list):
|
||||
q, k, v = qkv_or_q
|
||||
q: torch.Tensor = q
|
||||
qkv_or_q.clear()
|
||||
del qkv_or_q
|
||||
else:
|
||||
q: torch.Tensor = qkv_or_q
|
||||
del qkv_or_q
|
||||
assert k is not None and v is not None, "k and v must be provided if qkv_or_q is a tensor"
|
||||
if attn_params is None:
|
||||
attn_params = AttentionParams.create_attention_params("torch", False)
|
||||
|
||||
# If split attn is False, attention mask is provided and all sequence lengths are same, we can trim the sequence
|
||||
seqlen_trimmed = False
|
||||
if not attn_params.split_attn and attn_params.attention_mask is not None and attn_params.seqlens is not None:
|
||||
if torch.all(attn_params.seqlens == attn_params.seqlens[0]):
|
||||
seqlen = attn_params.seqlens[0].item()
|
||||
q = q[:, :seqlen]
|
||||
k = k[:, :seqlen]
|
||||
v = v[:, :seqlen]
|
||||
max_seqlen = attn_params.max_seqlen
|
||||
attn_params = AttentionParams.create_attention_params(attn_params.attn_mode, False) # do not in-place modify
|
||||
attn_params.max_seqlen = max_seqlen # keep max_seqlen for padding
|
||||
seqlen_trimmed = True
|
||||
|
||||
# Determine tensor layout based on attention implementation
|
||||
if attn_params.attn_mode == "torch" or (
|
||||
attn_params.attn_mode == "sageattn" and (attn_params.split_attn or attn_params.cu_seqlens is None)
|
||||
):
|
||||
transpose_fn = lambda x: x.transpose(1, 2) # [B, H, L, D] for SDPA and sageattn with fixed length
|
||||
# pad on sequence length dimension
|
||||
pad_fn = lambda x, pad_to: torch.nn.functional.pad(x, (0, 0, 0, pad_to - x.shape[-2]), value=0)
|
||||
else:
|
||||
transpose_fn = lambda x: x # [B, L, H, D] for other implementations
|
||||
# pad on sequence length dimension
|
||||
pad_fn = lambda x, pad_to: torch.nn.functional.pad(x, (0, 0, 0, 0, 0, pad_to - x.shape[-3]), value=0)
|
||||
|
||||
# Process each batch element with its valid sequence lengths
|
||||
if attn_params.split_attn:
|
||||
if attn_params.seqlens is None:
|
||||
# If no seqlens provided, assume all tokens are valid
|
||||
attn_params = AttentionParams.create_attention_params(attn_params.attn_mode, True) # do not in-place modify
|
||||
attn_params.seqlens = torch.tensor([q.shape[1]] * q.shape[0], device=q.device)
|
||||
attn_params.max_seqlen = q.shape[1]
|
||||
q = [transpose_fn(q[i : i + 1, : attn_params.seqlens[i]]) for i in range(len(q))]
|
||||
k = [transpose_fn(k[i : i + 1, : attn_params.seqlens[i]]) for i in range(len(k))]
|
||||
v = [transpose_fn(v[i : i + 1, : attn_params.seqlens[i]]) for i in range(len(v))]
|
||||
else:
|
||||
q = transpose_fn(q)
|
||||
k = transpose_fn(k)
|
||||
v = transpose_fn(v)
|
||||
|
||||
if attn_params.attn_mode == "torch":
|
||||
if attn_params.split_attn:
|
||||
x = []
|
||||
for i in range(len(q)):
|
||||
x_i = torch.nn.functional.scaled_dot_product_attention(q[i], k[i], v[i], dropout_p=drop_rate)
|
||||
q[i] = None
|
||||
k[i] = None
|
||||
v[i] = None
|
||||
x.append(pad_fn(x_i, attn_params.max_seqlen)) # B, H, L, D
|
||||
x = torch.cat(x, dim=0)
|
||||
del q, k, v
|
||||
|
||||
else:
|
||||
x = torch.nn.functional.scaled_dot_product_attention(q, k, v, attn_mask=attn_params.attention_mask, dropout_p=drop_rate)
|
||||
del q, k, v
|
||||
|
||||
elif attn_params.attn_mode == "xformers":
|
||||
if attn_params.split_attn:
|
||||
x = []
|
||||
for i in range(len(q)):
|
||||
x_i = xops.memory_efficient_attention(q[i], k[i], v[i], p=drop_rate)
|
||||
q[i] = None
|
||||
k[i] = None
|
||||
v[i] = None
|
||||
x.append(pad_fn(x_i, attn_params.max_seqlen)) # B, L, H, D
|
||||
x = torch.cat(x, dim=0)
|
||||
del q, k, v
|
||||
|
||||
else:
|
||||
x = xops.memory_efficient_attention(q, k, v, attn_bias=attn_params.attention_mask, p=drop_rate)
|
||||
del q, k, v
|
||||
|
||||
elif attn_params.attn_mode == "sageattn":
|
||||
if attn_params.split_attn:
|
||||
x = []
|
||||
for i in range(len(q)):
|
||||
# HND seems to cause an error
|
||||
x_i = sageattn(q[i], k[i], v[i]) # B, H, L, D. No dropout support
|
||||
q[i] = None
|
||||
k[i] = None
|
||||
v[i] = None
|
||||
x.append(pad_fn(x_i, attn_params.max_seqlen)) # B, H, L, D
|
||||
x = torch.cat(x, dim=0)
|
||||
del q, k, v
|
||||
elif attn_params.cu_seqlens is None: # all tokens are valid
|
||||
x = sageattn(q, k, v) # B, L, H, D. No dropout support
|
||||
del q, k, v
|
||||
else:
|
||||
# Reshape to [(bxs), a, d]
|
||||
batch_size, seqlen = q.shape[0], q.shape[1]
|
||||
q = q.view(q.shape[0] * q.shape[1], *q.shape[2:]) # [B*L, H, D]
|
||||
k = k.view(k.shape[0] * k.shape[1], *k.shape[2:]) # [B*L, H, D]
|
||||
v = v.view(v.shape[0] * v.shape[1], *v.shape[2:]) # [B*L, H, D]
|
||||
|
||||
# Assume cu_seqlens_q == cu_seqlens_kv and max_seqlen_q == max_seqlen_kv. No dropout support
|
||||
x = sageattn_varlen(
|
||||
q, k, v, attn_params.cu_seqlens, attn_params.cu_seqlens, attn_params.max_seqlen, attn_params.max_seqlen
|
||||
)
|
||||
del q, k, v
|
||||
|
||||
# Reshape x with shape [(bxs), a, d] to [b, s, a, d]
|
||||
x = x.view(batch_size, seqlen, x.shape[-2], x.shape[-1]) # B, L, H, D
|
||||
|
||||
elif attn_params.attn_mode == "flash":
|
||||
if attn_params.split_attn:
|
||||
x = []
|
||||
for i in range(len(q)):
|
||||
# HND seems to cause an error
|
||||
x_i = flash_attn_func(q[i], k[i], v[i], drop_rate) # B, L, H, D
|
||||
q[i] = None
|
||||
k[i] = None
|
||||
v[i] = None
|
||||
x.append(pad_fn(x_i, attn_params.max_seqlen)) # B, L, H, D
|
||||
x = torch.cat(x, dim=0)
|
||||
del q, k, v
|
||||
elif attn_params.cu_seqlens is None: # all tokens are valid
|
||||
x = flash_attn_func(q, k, v, drop_rate) # B, L, H, D
|
||||
del q, k, v
|
||||
else:
|
||||
# Reshape to [(bxs), a, d]
|
||||
batch_size, seqlen = q.shape[0], q.shape[1]
|
||||
q = q.view(q.shape[0] * q.shape[1], *q.shape[2:]) # [B*L, H, D]
|
||||
k = k.view(k.shape[0] * k.shape[1], *k.shape[2:]) # [B*L, H, D]
|
||||
v = v.view(v.shape[0] * v.shape[1], *v.shape[2:]) # [B*L, H, D]
|
||||
|
||||
# Assume cu_seqlens_q == cu_seqlens_kv and max_seqlen_q == max_seqlen_kv
|
||||
x = flash_attn_varlen_func(
|
||||
q, k, v, attn_params.cu_seqlens, attn_params.cu_seqlens, attn_params.max_seqlen, attn_params.max_seqlen, drop_rate
|
||||
)
|
||||
del q, k, v
|
||||
|
||||
# Reshape x with shape [(bxs), a, d] to [b, s, a, d]
|
||||
x = x.view(batch_size, seqlen, x.shape[-2], x.shape[-1]) # B, L, H, D
|
||||
|
||||
else:
|
||||
# Currently only PyTorch SDPA and xformers are implemented
|
||||
raise ValueError(f"Unsupported attention mode: {attn_params.attn_mode}")
|
||||
|
||||
x = transpose_fn(x) # [B, L, H, D]
|
||||
x = x.reshape(x.shape[0], x.shape[1], -1) # [B, L, H*D]
|
||||
|
||||
if seqlen_trimmed:
|
||||
x = torch.nn.functional.pad(x, (0, 0, 0, attn_params.max_seqlen - x.shape[1]), value=0) # pad back to max_seqlen
|
||||
|
||||
return x
|
||||
@@ -1,7 +1,7 @@
|
||||
from concurrent.futures import ThreadPoolExecutor
|
||||
import gc
|
||||
import time
|
||||
from typing import Optional, Union, Callable, Tuple
|
||||
from typing import Any, Optional, Union, Callable, Tuple
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
|
||||
@@ -136,7 +136,7 @@ class Offloader:
|
||||
self.swap_weight_devices(block_to_cpu, block_to_cuda)
|
||||
|
||||
if self.debug:
|
||||
print(f"Moved blocks {bidx_to_cpu} and {bidx_to_cuda} in {time.perf_counter()-start_time:.2f}s")
|
||||
print(f"Moved blocks {bidx_to_cpu} and {bidx_to_cuda} in {time.perf_counter() - start_time:.2f}s")
|
||||
return bidx_to_cpu, bidx_to_cuda # , event
|
||||
|
||||
block_to_cpu = blocks[block_idx_to_cpu]
|
||||
@@ -160,7 +160,7 @@ class Offloader:
|
||||
assert block_idx == bidx_to_cuda, f"Block index mismatch: {block_idx} != {bidx_to_cuda}"
|
||||
|
||||
if self.debug:
|
||||
print(f"Waited for block {block_idx}: {time.perf_counter()-start_time:.2f}s")
|
||||
print(f"Waited for block {block_idx}: {time.perf_counter() - start_time:.2f}s")
|
||||
|
||||
|
||||
# Gradient tensors
|
||||
@@ -173,21 +173,34 @@ class ModelOffloader(Offloader):
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self, blocks: Union[list[nn.Module], nn.ModuleList], blocks_to_swap: int, device: torch.device, debug: bool = False
|
||||
self,
|
||||
blocks: Union[list[nn.Module], nn.ModuleList],
|
||||
blocks_to_swap: int,
|
||||
device: torch.device,
|
||||
supports_backward: bool = True,
|
||||
debug: bool = False,
|
||||
):
|
||||
super().__init__(len(blocks), blocks_to_swap, device, debug)
|
||||
|
||||
# register backward hooks
|
||||
self.remove_handles = []
|
||||
for i, block in enumerate(blocks):
|
||||
hook = self.create_backward_hook(blocks, i)
|
||||
if hook is not None:
|
||||
handle = block.register_full_backward_hook(hook)
|
||||
self.remove_handles.append(handle)
|
||||
self.supports_backward = supports_backward
|
||||
self.forward_only = not supports_backward # forward only offloading: can be changed to True for inference
|
||||
|
||||
if self.supports_backward:
|
||||
# register backward hooks
|
||||
self.remove_handles = []
|
||||
for i, block in enumerate(blocks):
|
||||
hook = self.create_backward_hook(blocks, i)
|
||||
if hook is not None:
|
||||
handle = block.register_full_backward_hook(hook)
|
||||
self.remove_handles.append(handle)
|
||||
|
||||
def set_forward_only(self, forward_only: bool):
|
||||
self.forward_only = forward_only
|
||||
|
||||
def __del__(self):
|
||||
for handle in self.remove_handles:
|
||||
handle.remove()
|
||||
if self.supports_backward:
|
||||
for handle in self.remove_handles:
|
||||
handle.remove()
|
||||
|
||||
def create_backward_hook(
|
||||
self, blocks: Union[list[nn.Module], nn.ModuleList], block_index: int
|
||||
@@ -222,14 +235,14 @@ class ModelOffloader(Offloader):
|
||||
return
|
||||
|
||||
if self.debug:
|
||||
print("Prepare block devices before forward")
|
||||
print(f"Prepare block devices before forward")
|
||||
|
||||
for b in blocks[0 : self.num_blocks - self.blocks_to_swap]:
|
||||
b.to(self.device)
|
||||
weighs_to_device(b, self.device) # make sure weights are on device
|
||||
|
||||
for b in blocks[self.num_blocks - self.blocks_to_swap :]:
|
||||
b.to(self.device) # move block to device first
|
||||
b.to(self.device) # move block to device first. this makes sure that buffers (non weights) are on the device
|
||||
weighs_to_device(b, torch.device("cpu")) # make sure weights are on cpu
|
||||
|
||||
_synchronize_device(self.device)
|
||||
@@ -241,10 +254,87 @@ class ModelOffloader(Offloader):
|
||||
self._wait_blocks_move(block_idx)
|
||||
|
||||
def submit_move_blocks(self, blocks: Union[list[nn.Module], nn.ModuleList], block_idx: int):
|
||||
# check if blocks_to_swap is enabled
|
||||
if self.blocks_to_swap is None or self.blocks_to_swap == 0:
|
||||
return
|
||||
if block_idx >= self.blocks_to_swap:
|
||||
|
||||
# if backward is enabled, we do not swap blocks in forward pass more than blocks_to_swap, because it should be on GPU
|
||||
if not self.forward_only and block_idx >= self.blocks_to_swap:
|
||||
return
|
||||
|
||||
block_idx_to_cpu = block_idx
|
||||
block_idx_to_cuda = self.num_blocks - self.blocks_to_swap + block_idx
|
||||
|
||||
# this works for forward-only offloading. move upstream blocks to cuda
|
||||
block_idx_to_cuda = block_idx_to_cuda % self.num_blocks
|
||||
|
||||
self._submit_move_blocks(blocks, block_idx_to_cpu, block_idx_to_cuda)
|
||||
|
||||
|
||||
# endregion
|
||||
|
||||
# region cpu offload utils
|
||||
|
||||
|
||||
def to_device(x: Any, device: torch.device) -> Any:
|
||||
if isinstance(x, torch.Tensor):
|
||||
return x.to(device)
|
||||
elif isinstance(x, list):
|
||||
return [to_device(elem, device) for elem in x]
|
||||
elif isinstance(x, tuple):
|
||||
return tuple(to_device(elem, device) for elem in x)
|
||||
elif isinstance(x, dict):
|
||||
return {k: to_device(v, device) for k, v in x.items()}
|
||||
else:
|
||||
return x
|
||||
|
||||
|
||||
def to_cpu(x: Any) -> Any:
|
||||
"""
|
||||
Recursively moves torch.Tensor objects (and containers thereof) to CPU.
|
||||
|
||||
Args:
|
||||
x: A torch.Tensor, or a (possibly nested) list, tuple, or dict containing tensors.
|
||||
|
||||
Returns:
|
||||
The same structure as x, with all torch.Tensor objects moved to CPU.
|
||||
Non-tensor objects are returned unchanged.
|
||||
"""
|
||||
if isinstance(x, torch.Tensor):
|
||||
return x.cpu()
|
||||
elif isinstance(x, list):
|
||||
return [to_cpu(elem) for elem in x]
|
||||
elif isinstance(x, tuple):
|
||||
return tuple(to_cpu(elem) for elem in x)
|
||||
elif isinstance(x, dict):
|
||||
return {k: to_cpu(v) for k, v in x.items()}
|
||||
else:
|
||||
return x
|
||||
|
||||
|
||||
def create_cpu_offloading_wrapper(func: Callable, device: torch.device) -> Callable:
|
||||
"""
|
||||
Create a wrapper function that offloads inputs to CPU before calling the original function
|
||||
and moves outputs back to the specified device.
|
||||
|
||||
Args:
|
||||
func: The original function to wrap.
|
||||
device: The device to move outputs back to.
|
||||
|
||||
Returns:
|
||||
A wrapped function that offloads inputs to CPU and moves outputs back to the specified device.
|
||||
"""
|
||||
|
||||
def wrapper(orig_func: Callable) -> Callable:
|
||||
def custom_forward(*inputs):
|
||||
nonlocal device, orig_func
|
||||
cuda_inputs = to_device(inputs, device)
|
||||
outputs = orig_func(*cuda_inputs)
|
||||
return to_cpu(outputs)
|
||||
|
||||
return custom_forward
|
||||
|
||||
return wrapper(func)
|
||||
|
||||
|
||||
# endregion
|
||||
|
||||
@@ -4,6 +4,7 @@ from typing import Optional, Union
|
||||
|
||||
import torch
|
||||
|
||||
|
||||
try:
|
||||
# intel gpu support for pytorch older than 2.5
|
||||
# ipex is not needed after pytorch 2.5
|
||||
|
||||
473
library/fp8_optimization_utils.py
Normal file
473
library/fp8_optimization_utils.py
Normal file
@@ -0,0 +1,473 @@
|
||||
import os
|
||||
from typing import List, Optional, Union
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
|
||||
import logging
|
||||
|
||||
from tqdm import tqdm
|
||||
|
||||
from library.device_utils import clean_memory_on_device
|
||||
from library.safetensors_utils import MemoryEfficientSafeOpen
|
||||
from library.utils import setup_logging
|
||||
|
||||
setup_logging()
|
||||
import logging
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def calculate_fp8_maxval(exp_bits=4, mantissa_bits=3, sign_bits=1):
|
||||
"""
|
||||
Calculate the maximum representable value in FP8 format.
|
||||
Default is E4M3 format (4-bit exponent, 3-bit mantissa, 1-bit sign). Only supports E4M3 and E5M2 with sign bit.
|
||||
|
||||
Args:
|
||||
exp_bits (int): Number of exponent bits
|
||||
mantissa_bits (int): Number of mantissa bits
|
||||
sign_bits (int): Number of sign bits (0 or 1)
|
||||
|
||||
Returns:
|
||||
float: Maximum value representable in FP8 format
|
||||
"""
|
||||
assert exp_bits + mantissa_bits + sign_bits == 8, "Total bits must be 8"
|
||||
if exp_bits == 4 and mantissa_bits == 3 and sign_bits == 1:
|
||||
return torch.finfo(torch.float8_e4m3fn).max
|
||||
elif exp_bits == 5 and mantissa_bits == 2 and sign_bits == 1:
|
||||
return torch.finfo(torch.float8_e5m2).max
|
||||
else:
|
||||
raise ValueError(f"Unsupported FP8 format: E{exp_bits}M{mantissa_bits} with sign_bits={sign_bits}")
|
||||
|
||||
|
||||
# The following is a manual calculation method (wrong implementation for E5M2), kept for reference.
|
||||
"""
|
||||
# Calculate exponent bias
|
||||
bias = 2 ** (exp_bits - 1) - 1
|
||||
|
||||
# Calculate maximum mantissa value
|
||||
mantissa_max = 1.0
|
||||
for i in range(mantissa_bits - 1):
|
||||
mantissa_max += 2 ** -(i + 1)
|
||||
|
||||
# Calculate maximum value
|
||||
max_value = mantissa_max * (2 ** (2**exp_bits - 1 - bias))
|
||||
|
||||
return max_value
|
||||
"""
|
||||
|
||||
|
||||
def quantize_fp8(tensor, scale, fp8_dtype, max_value, min_value):
|
||||
"""
|
||||
Quantize a tensor to FP8 format using PyTorch's native FP8 dtype support.
|
||||
|
||||
Args:
|
||||
tensor (torch.Tensor): Tensor to quantize
|
||||
scale (float or torch.Tensor): Scale factor
|
||||
fp8_dtype (torch.dtype): Target FP8 dtype (torch.float8_e4m3fn or torch.float8_e5m2)
|
||||
max_value (float): Maximum representable value in FP8
|
||||
min_value (float): Minimum representable value in FP8
|
||||
|
||||
Returns:
|
||||
torch.Tensor: Quantized tensor in FP8 format
|
||||
"""
|
||||
tensor = tensor.to(torch.float32) # ensure tensor is in float32 for division
|
||||
|
||||
# Create scaled tensor
|
||||
tensor = torch.div(tensor, scale).nan_to_num_(0.0) # handle NaN values, equivalent to nonzero_mask in previous function
|
||||
|
||||
# Clamp tensor to range
|
||||
tensor = tensor.clamp_(min=min_value, max=max_value)
|
||||
|
||||
# Convert to FP8 dtype
|
||||
tensor = tensor.to(fp8_dtype)
|
||||
|
||||
return tensor
|
||||
|
||||
|
||||
def optimize_state_dict_with_fp8(
|
||||
state_dict: dict,
|
||||
calc_device: Union[str, torch.device],
|
||||
target_layer_keys: Optional[list[str]] = None,
|
||||
exclude_layer_keys: Optional[list[str]] = None,
|
||||
exp_bits: int = 4,
|
||||
mantissa_bits: int = 3,
|
||||
move_to_device: bool = False,
|
||||
quantization_mode: str = "block",
|
||||
block_size: Optional[int] = 64,
|
||||
):
|
||||
"""
|
||||
Optimize Linear layer weights in a model's state dict to FP8 format. The state dict is modified in-place.
|
||||
This function is a static version of load_safetensors_with_fp8_optimization without loading from files.
|
||||
|
||||
Args:
|
||||
state_dict (dict): State dict to optimize, replaced in-place
|
||||
calc_device (str): Device to quantize tensors on
|
||||
target_layer_keys (list, optional): Layer key patterns to target (None for all Linear layers)
|
||||
exclude_layer_keys (list, optional): Layer key patterns to exclude
|
||||
exp_bits (int): Number of exponent bits
|
||||
mantissa_bits (int): Number of mantissa bits
|
||||
move_to_device (bool): Move optimized tensors to the calculating device
|
||||
|
||||
Returns:
|
||||
dict: FP8 optimized state dict
|
||||
"""
|
||||
if exp_bits == 4 and mantissa_bits == 3:
|
||||
fp8_dtype = torch.float8_e4m3fn
|
||||
elif exp_bits == 5 and mantissa_bits == 2:
|
||||
fp8_dtype = torch.float8_e5m2
|
||||
else:
|
||||
raise ValueError(f"Unsupported FP8 format: E{exp_bits}M{mantissa_bits}")
|
||||
|
||||
# Calculate FP8 max value
|
||||
max_value = calculate_fp8_maxval(exp_bits, mantissa_bits)
|
||||
min_value = -max_value # this function supports only signed FP8
|
||||
|
||||
# Create optimized state dict
|
||||
optimized_count = 0
|
||||
|
||||
# Enumerate tarket keys
|
||||
target_state_dict_keys = []
|
||||
for key in state_dict.keys():
|
||||
# Check if it's a weight key and matches target patterns
|
||||
is_target = (target_layer_keys is None or any(pattern in key for pattern in target_layer_keys)) and key.endswith(".weight")
|
||||
is_excluded = exclude_layer_keys is not None and any(pattern in key for pattern in exclude_layer_keys)
|
||||
is_target = is_target and not is_excluded
|
||||
|
||||
if is_target and isinstance(state_dict[key], torch.Tensor):
|
||||
target_state_dict_keys.append(key)
|
||||
|
||||
# Process each key
|
||||
for key in tqdm(target_state_dict_keys):
|
||||
value = state_dict[key]
|
||||
|
||||
# Save original device and dtype
|
||||
original_device = value.device
|
||||
original_dtype = value.dtype
|
||||
|
||||
# Move to calculation device
|
||||
if calc_device is not None:
|
||||
value = value.to(calc_device)
|
||||
|
||||
quantized_weight, scale_tensor = quantize_weight(key, value, fp8_dtype, max_value, min_value, quantization_mode, block_size)
|
||||
|
||||
# Add to state dict using original key for weight and new key for scale
|
||||
fp8_key = key # Maintain original key
|
||||
scale_key = key.replace(".weight", ".scale_weight")
|
||||
|
||||
if not move_to_device:
|
||||
quantized_weight = quantized_weight.to(original_device)
|
||||
|
||||
# keep scale shape: [1] or [out,1] or [out, num_blocks, 1]. We can determine the quantization mode from the shape of scale_weight in the patched model.
|
||||
scale_tensor = scale_tensor.to(dtype=original_dtype, device=quantized_weight.device)
|
||||
|
||||
state_dict[fp8_key] = quantized_weight
|
||||
state_dict[scale_key] = scale_tensor
|
||||
|
||||
optimized_count += 1
|
||||
|
||||
if calc_device is not None: # optimized_count % 10 == 0 and
|
||||
# free memory on calculation device
|
||||
clean_memory_on_device(calc_device)
|
||||
|
||||
logger.info(f"Number of optimized Linear layers: {optimized_count}")
|
||||
return state_dict
|
||||
|
||||
|
||||
def quantize_weight(
|
||||
key: str,
|
||||
tensor: torch.Tensor,
|
||||
fp8_dtype: torch.dtype,
|
||||
max_value: float,
|
||||
min_value: float,
|
||||
quantization_mode: str = "block",
|
||||
block_size: int = 64,
|
||||
):
|
||||
original_shape = tensor.shape
|
||||
|
||||
# Determine quantization mode
|
||||
if quantization_mode == "block":
|
||||
if tensor.ndim != 2:
|
||||
quantization_mode = "tensor" # fallback to per-tensor
|
||||
else:
|
||||
out_features, in_features = tensor.shape
|
||||
if in_features % block_size != 0:
|
||||
quantization_mode = "channel" # fallback to per-channel
|
||||
logger.warning(
|
||||
f"Layer {key} with shape {tensor.shape} is not divisible by block_size {block_size}, fallback to per-channel quantization."
|
||||
)
|
||||
else:
|
||||
num_blocks = in_features // block_size
|
||||
tensor = tensor.contiguous().view(out_features, num_blocks, block_size) # [out, num_blocks, block_size]
|
||||
elif quantization_mode == "channel":
|
||||
if tensor.ndim != 2:
|
||||
quantization_mode = "tensor" # fallback to per-tensor
|
||||
|
||||
# Calculate scale factor (per-tensor or per-output-channel with percentile or max)
|
||||
# value shape is expected to be [out_features, in_features] for Linear weights
|
||||
if quantization_mode == "channel" or quantization_mode == "block":
|
||||
# row-wise percentile to avoid being dominated by outliers
|
||||
# result shape: [out_features, 1] or [out_features, num_blocks, 1]
|
||||
scale_dim = 1 if quantization_mode == "channel" else 2
|
||||
abs_w = torch.abs(tensor)
|
||||
|
||||
# shape: [out_features, 1] or [out_features, num_blocks, 1]
|
||||
row_max = torch.max(abs_w, dim=scale_dim, keepdim=True).values
|
||||
scale = row_max / max_value
|
||||
|
||||
else:
|
||||
# per-tensor
|
||||
tensor_max = torch.max(torch.abs(tensor).view(-1))
|
||||
scale = tensor_max / max_value
|
||||
|
||||
# Calculate scale factor
|
||||
scale = torch.max(torch.abs(tensor.flatten())) / max_value
|
||||
# print(f"Optimizing {key} with scale: {scale}")
|
||||
|
||||
# numerical safety
|
||||
scale = torch.clamp(scale, min=1e-8)
|
||||
scale = scale.to(torch.float32) # ensure scale is in float32 for division
|
||||
|
||||
# Quantize weight to FP8 (scale can be scalar or [out,1], broadcasting works)
|
||||
quantized_weight = quantize_fp8(tensor, scale, fp8_dtype, max_value, min_value)
|
||||
|
||||
# If block-wise, restore original shape
|
||||
if quantization_mode == "block":
|
||||
quantized_weight = quantized_weight.view(original_shape) # restore to original shape [out, in]
|
||||
|
||||
return quantized_weight, scale
|
||||
|
||||
|
||||
def load_safetensors_with_fp8_optimization(
|
||||
model_files: List[str],
|
||||
calc_device: Union[str, torch.device],
|
||||
target_layer_keys=None,
|
||||
exclude_layer_keys=None,
|
||||
exp_bits=4,
|
||||
mantissa_bits=3,
|
||||
move_to_device=False,
|
||||
weight_hook=None,
|
||||
quantization_mode: str = "block",
|
||||
block_size: Optional[int] = 64,
|
||||
) -> dict:
|
||||
"""
|
||||
Load weight tensors from safetensors files and merge LoRA weights into the state dict with explicit FP8 optimization.
|
||||
|
||||
Args:
|
||||
model_files (list[str]): List of model files to load
|
||||
calc_device (str or torch.device): Device to quantize tensors on
|
||||
target_layer_keys (list, optional): Layer key patterns to target for optimization (None for all Linear layers)
|
||||
exclude_layer_keys (list, optional): Layer key patterns to exclude from optimization
|
||||
exp_bits (int): Number of exponent bits
|
||||
mantissa_bits (int): Number of mantissa bits
|
||||
move_to_device (bool): Move optimized tensors to the calculating device
|
||||
weight_hook (callable, optional): Function to apply to each weight tensor before optimization
|
||||
quantization_mode (str): Quantization mode, "tensor", "channel", or "block"
|
||||
block_size (int, optional): Block size for block-wise quantization (used if quantization_mode is "block")
|
||||
|
||||
Returns:
|
||||
dict: FP8 optimized state dict
|
||||
"""
|
||||
if exp_bits == 4 and mantissa_bits == 3:
|
||||
fp8_dtype = torch.float8_e4m3fn
|
||||
elif exp_bits == 5 and mantissa_bits == 2:
|
||||
fp8_dtype = torch.float8_e5m2
|
||||
else:
|
||||
raise ValueError(f"Unsupported FP8 format: E{exp_bits}M{mantissa_bits}")
|
||||
|
||||
# Calculate FP8 max value
|
||||
max_value = calculate_fp8_maxval(exp_bits, mantissa_bits)
|
||||
min_value = -max_value # this function supports only signed FP8
|
||||
|
||||
# Define function to determine if a key is a target key. target means fp8 optimization, not for weight hook.
|
||||
def is_target_key(key):
|
||||
# Check if weight key matches target patterns and does not match exclude patterns
|
||||
is_target = (target_layer_keys is None or any(pattern in key for pattern in target_layer_keys)) and key.endswith(".weight")
|
||||
is_excluded = exclude_layer_keys is not None and any(pattern in key for pattern in exclude_layer_keys)
|
||||
return is_target and not is_excluded
|
||||
|
||||
# Create optimized state dict
|
||||
optimized_count = 0
|
||||
|
||||
# Process each file
|
||||
state_dict = {}
|
||||
for model_file in model_files:
|
||||
with MemoryEfficientSafeOpen(model_file) as f:
|
||||
keys = f.keys()
|
||||
for key in tqdm(keys, desc=f"Loading {os.path.basename(model_file)}", unit="key"):
|
||||
value = f.get_tensor(key)
|
||||
|
||||
# Save original device
|
||||
original_device = value.device # usually cpu
|
||||
|
||||
if weight_hook is not None:
|
||||
# Apply weight hook if provided
|
||||
value = weight_hook(key, value, keep_on_calc_device=(calc_device is not None))
|
||||
|
||||
if not is_target_key(key):
|
||||
target_device = calc_device if (calc_device is not None and move_to_device) else original_device
|
||||
value = value.to(target_device)
|
||||
state_dict[key] = value
|
||||
continue
|
||||
|
||||
# Move to calculation device
|
||||
if calc_device is not None:
|
||||
value = value.to(calc_device)
|
||||
|
||||
original_dtype = value.dtype
|
||||
quantized_weight, scale_tensor = quantize_weight(
|
||||
key, value, fp8_dtype, max_value, min_value, quantization_mode, block_size
|
||||
)
|
||||
|
||||
# Add to state dict using original key for weight and new key for scale
|
||||
fp8_key = key # Maintain original key
|
||||
scale_key = key.replace(".weight", ".scale_weight")
|
||||
assert fp8_key != scale_key, "FP8 key and scale key must be different"
|
||||
|
||||
if not move_to_device:
|
||||
quantized_weight = quantized_weight.to(original_device)
|
||||
|
||||
# keep scale shape: [1] or [out,1] or [out, num_blocks, 1]. We can determine the quantization mode from the shape of scale_weight in the patched model.
|
||||
scale_tensor = scale_tensor.to(dtype=original_dtype, device=quantized_weight.device)
|
||||
|
||||
state_dict[fp8_key] = quantized_weight
|
||||
state_dict[scale_key] = scale_tensor
|
||||
|
||||
optimized_count += 1
|
||||
|
||||
if calc_device is not None and optimized_count % 10 == 0:
|
||||
# free memory on calculation device
|
||||
clean_memory_on_device(calc_device)
|
||||
|
||||
logger.info(f"Number of optimized Linear layers: {optimized_count}")
|
||||
return state_dict
|
||||
|
||||
|
||||
def fp8_linear_forward_patch(self: nn.Linear, x, use_scaled_mm=False, max_value=None):
|
||||
"""
|
||||
Patched forward method for Linear layers with FP8 weights.
|
||||
|
||||
Args:
|
||||
self: Linear layer instance
|
||||
x (torch.Tensor): Input tensor
|
||||
use_scaled_mm (bool): Use scaled_mm for FP8 Linear layers, requires SM 8.9+ (RTX 40 series)
|
||||
max_value (float): Maximum value for FP8 quantization. If None, no quantization is applied for input tensor.
|
||||
|
||||
Returns:
|
||||
torch.Tensor: Result of linear transformation
|
||||
"""
|
||||
if use_scaled_mm:
|
||||
# **not tested**
|
||||
# _scaled_mm only works for per-tensor scale for now (per-channel scale does not work in certain cases)
|
||||
if self.scale_weight.ndim != 1:
|
||||
raise ValueError("scaled_mm only supports per-tensor scale_weight for now.")
|
||||
|
||||
input_dtype = x.dtype
|
||||
original_weight_dtype = self.scale_weight.dtype
|
||||
target_dtype = self.weight.dtype
|
||||
# assert x.ndim == 3, "Input tensor must be 3D (batch_size, seq_len, hidden_dim)"
|
||||
|
||||
if max_value is None:
|
||||
# no input quantization
|
||||
scale_x = torch.tensor(1.0, dtype=torch.float32, device=x.device)
|
||||
else:
|
||||
# calculate scale factor for input tensor
|
||||
scale_x = (torch.max(torch.abs(x.flatten())) / max_value).to(torch.float32)
|
||||
|
||||
# quantize input tensor to FP8: this seems to consume a lot of memory
|
||||
fp8_max_value = torch.finfo(target_dtype).max
|
||||
fp8_min_value = torch.finfo(target_dtype).min
|
||||
x = quantize_fp8(x, scale_x, target_dtype, fp8_max_value, fp8_min_value)
|
||||
|
||||
original_shape = x.shape
|
||||
x = x.reshape(-1, x.shape[-1]).to(target_dtype)
|
||||
|
||||
weight = self.weight.t()
|
||||
scale_weight = self.scale_weight.to(torch.float32)
|
||||
|
||||
if self.bias is not None:
|
||||
# float32 is not supported with bias in scaled_mm
|
||||
o = torch._scaled_mm(x, weight, out_dtype=original_weight_dtype, bias=self.bias, scale_a=scale_x, scale_b=scale_weight)
|
||||
else:
|
||||
o = torch._scaled_mm(x, weight, out_dtype=input_dtype, scale_a=scale_x, scale_b=scale_weight)
|
||||
|
||||
o = o.reshape(original_shape[0], original_shape[1], -1) if x.ndim == 3 else o.reshape(original_shape[0], -1)
|
||||
return o.to(input_dtype)
|
||||
|
||||
else:
|
||||
# Dequantize the weight
|
||||
original_dtype = self.scale_weight.dtype
|
||||
if self.scale_weight.ndim < 3:
|
||||
# per-tensor or per-channel quantization, we can broadcast
|
||||
dequantized_weight = self.weight.to(original_dtype) * self.scale_weight
|
||||
else:
|
||||
# block-wise quantization, need to reshape weight to match scale shape for broadcasting
|
||||
out_features, num_blocks, _ = self.scale_weight.shape
|
||||
dequantized_weight = self.weight.to(original_dtype).contiguous().view(out_features, num_blocks, -1)
|
||||
dequantized_weight = dequantized_weight * self.scale_weight
|
||||
dequantized_weight = dequantized_weight.view(self.weight.shape)
|
||||
|
||||
# Perform linear transformation
|
||||
if self.bias is not None:
|
||||
output = F.linear(x, dequantized_weight, self.bias)
|
||||
else:
|
||||
output = F.linear(x, dequantized_weight)
|
||||
|
||||
return output
|
||||
|
||||
|
||||
def apply_fp8_monkey_patch(model, optimized_state_dict, use_scaled_mm=False):
|
||||
"""
|
||||
Apply monkey patching to a model using FP8 optimized state dict.
|
||||
|
||||
Args:
|
||||
model (nn.Module): Model instance to patch
|
||||
optimized_state_dict (dict): FP8 optimized state dict
|
||||
use_scaled_mm (bool): Use scaled_mm for FP8 Linear layers, requires SM 8.9+ (RTX 40 series)
|
||||
|
||||
Returns:
|
||||
nn.Module: The patched model (same instance, modified in-place)
|
||||
"""
|
||||
# # Calculate FP8 float8_e5m2 max value
|
||||
# max_value = calculate_fp8_maxval(5, 2)
|
||||
max_value = None # do not quantize input tensor
|
||||
|
||||
# Find all scale keys to identify FP8-optimized layers
|
||||
scale_keys = [k for k in optimized_state_dict.keys() if k.endswith(".scale_weight")]
|
||||
|
||||
# Enumerate patched layers
|
||||
patched_module_paths = set()
|
||||
scale_shape_info = {}
|
||||
for scale_key in scale_keys:
|
||||
# Extract module path from scale key (remove .scale_weight)
|
||||
module_path = scale_key.rsplit(".scale_weight", 1)[0]
|
||||
patched_module_paths.add(module_path)
|
||||
|
||||
# Store scale shape information
|
||||
scale_shape_info[module_path] = optimized_state_dict[scale_key].shape
|
||||
|
||||
patched_count = 0
|
||||
|
||||
# Apply monkey patch to each layer with FP8 weights
|
||||
for name, module in model.named_modules():
|
||||
# Check if this module has a corresponding scale_weight
|
||||
has_scale = name in patched_module_paths
|
||||
|
||||
# Apply patch if it's a Linear layer with FP8 scale
|
||||
if isinstance(module, nn.Linear) and has_scale:
|
||||
# register the scale_weight as a buffer to load the state_dict
|
||||
# module.register_buffer("scale_weight", torch.tensor(1.0, dtype=module.weight.dtype))
|
||||
scale_shape = scale_shape_info[name]
|
||||
module.register_buffer("scale_weight", torch.ones(scale_shape, dtype=module.weight.dtype))
|
||||
|
||||
# Create a new forward method with the patched version.
|
||||
def new_forward(self, x):
|
||||
return fp8_linear_forward_patch(self, x, use_scaled_mm, max_value)
|
||||
|
||||
# Bind method to module
|
||||
module.forward = new_forward.__get__(module, type(module))
|
||||
|
||||
patched_count += 1
|
||||
|
||||
logger.info(f"Number of monkey-patched Linear layers: {patched_count}")
|
||||
return model
|
||||
489
library/hunyuan_image_models.py
Normal file
489
library/hunyuan_image_models.py
Normal file
@@ -0,0 +1,489 @@
|
||||
# Original work: https://github.com/Tencent-Hunyuan/HunyuanImage-2.1
|
||||
# Re-implemented for license compliance for sd-scripts.
|
||||
|
||||
from typing import Dict, Optional, Tuple, Union
|
||||
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from accelerate import init_empty_weights
|
||||
|
||||
from library import custom_offloading_utils
|
||||
from library.attention import AttentionParams
|
||||
from library.fp8_optimization_utils import apply_fp8_monkey_patch
|
||||
from library.lora_utils import load_safetensors_with_lora_and_fp8
|
||||
from library.utils import setup_logging
|
||||
|
||||
setup_logging()
|
||||
import logging
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
from library.hunyuan_image_modules import (
|
||||
SingleTokenRefiner,
|
||||
ByT5Mapper,
|
||||
PatchEmbed2D,
|
||||
TimestepEmbedder,
|
||||
MMDoubleStreamBlock,
|
||||
MMSingleStreamBlock,
|
||||
FinalLayer,
|
||||
)
|
||||
from library.hunyuan_image_utils import get_nd_rotary_pos_embed
|
||||
|
||||
FP8_OPTIMIZATION_TARGET_KEYS = ["double_blocks", "single_blocks"]
|
||||
# FP8_OPTIMIZATION_EXCLUDE_KEYS = ["norm", "_mod", "_emb"] # , "modulation"
|
||||
FP8_OPTIMIZATION_EXCLUDE_KEYS = ["norm", "_emb"] # , "modulation", "_mod"
|
||||
|
||||
# full exclude 24.2GB
|
||||
# norm and _emb 19.7GB
|
||||
# fp8 cast 19.7GB
|
||||
|
||||
|
||||
# region DiT Model
|
||||
class HYImageDiffusionTransformer(nn.Module):
|
||||
"""
|
||||
HunyuanImage-2.1 Diffusion Transformer.
|
||||
|
||||
A multimodal transformer for image generation with text conditioning,
|
||||
featuring separate double-stream and single-stream processing blocks.
|
||||
|
||||
Args:
|
||||
attn_mode: Attention implementation mode ("torch" or "sageattn").
|
||||
"""
|
||||
|
||||
def __init__(self, attn_mode: str = "torch", split_attn: bool = False):
|
||||
super().__init__()
|
||||
|
||||
# Fixed architecture parameters for HunyuanImage-2.1
|
||||
self.patch_size = [1, 1] # 1x1 patch size (no spatial downsampling)
|
||||
self.in_channels = 64 # Input latent channels
|
||||
self.out_channels = 64 # Output latent channels
|
||||
self.unpatchify_channels = self.out_channels
|
||||
self.guidance_embed = False # Guidance embedding disabled
|
||||
self.rope_dim_list = [64, 64] # RoPE dimensions for 2D positional encoding
|
||||
self.rope_theta = 256 # RoPE frequency scaling
|
||||
self.use_attention_mask = True
|
||||
self.text_projection = "single_refiner"
|
||||
self.hidden_size = 3584 # Model dimension
|
||||
self.heads_num = 28 # Number of attention heads
|
||||
|
||||
# Architecture configuration
|
||||
mm_double_blocks_depth = 20 # Double-stream transformer blocks
|
||||
mm_single_blocks_depth = 40 # Single-stream transformer blocks
|
||||
mlp_width_ratio = 4 # MLP expansion ratio
|
||||
text_states_dim = 3584 # Text encoder output dimension
|
||||
guidance_embed = False # No guidance embedding
|
||||
|
||||
# Layer configuration
|
||||
mlp_act_type: str = "gelu_tanh" # MLP activation function
|
||||
qkv_bias: bool = True # Use bias in QKV projections
|
||||
qk_norm: bool = True # Apply QK normalization
|
||||
qk_norm_type: str = "rms" # RMS normalization type
|
||||
|
||||
self.attn_mode = attn_mode
|
||||
self.split_attn = split_attn
|
||||
|
||||
# ByT5 character-level text encoder mapping
|
||||
self.byt5_in = ByT5Mapper(in_dim=1472, out_dim=2048, hidden_dim=2048, out_dim1=self.hidden_size, use_residual=False)
|
||||
|
||||
# Image latent patch embedding
|
||||
self.img_in = PatchEmbed2D(self.patch_size, self.in_channels, self.hidden_size)
|
||||
|
||||
# Text token refinement with cross-attention
|
||||
self.txt_in = SingleTokenRefiner(text_states_dim, self.hidden_size, self.heads_num, depth=2)
|
||||
|
||||
# Timestep embedding for diffusion process
|
||||
self.time_in = TimestepEmbedder(self.hidden_size, nn.SiLU)
|
||||
|
||||
# MeanFlow not supported in this implementation
|
||||
self.time_r_in = None
|
||||
|
||||
# Guidance embedding (disabled for non-distilled model)
|
||||
self.guidance_in = TimestepEmbedder(self.hidden_size, nn.SiLU) if guidance_embed else None
|
||||
|
||||
# Double-stream blocks: separate image and text processing
|
||||
self.double_blocks = nn.ModuleList(
|
||||
[
|
||||
MMDoubleStreamBlock(
|
||||
self.hidden_size,
|
||||
self.heads_num,
|
||||
mlp_width_ratio=mlp_width_ratio,
|
||||
mlp_act_type=mlp_act_type,
|
||||
qk_norm=qk_norm,
|
||||
qk_norm_type=qk_norm_type,
|
||||
qkv_bias=qkv_bias,
|
||||
)
|
||||
for _ in range(mm_double_blocks_depth)
|
||||
]
|
||||
)
|
||||
|
||||
# Single-stream blocks: joint processing of concatenated features
|
||||
self.single_blocks = nn.ModuleList(
|
||||
[
|
||||
MMSingleStreamBlock(
|
||||
self.hidden_size,
|
||||
self.heads_num,
|
||||
mlp_width_ratio=mlp_width_ratio,
|
||||
mlp_act_type=mlp_act_type,
|
||||
qk_norm=qk_norm,
|
||||
qk_norm_type=qk_norm_type,
|
||||
)
|
||||
for _ in range(mm_single_blocks_depth)
|
||||
]
|
||||
)
|
||||
|
||||
self.final_layer = FinalLayer(self.hidden_size, self.patch_size, self.out_channels, nn.SiLU)
|
||||
|
||||
self.gradient_checkpointing = False
|
||||
self.cpu_offload_checkpointing = False
|
||||
self.blocks_to_swap = None
|
||||
|
||||
self.offloader_double = None
|
||||
self.offloader_single = None
|
||||
self.num_double_blocks = len(self.double_blocks)
|
||||
self.num_single_blocks = len(self.single_blocks)
|
||||
|
||||
@property
|
||||
def device(self):
|
||||
return next(self.parameters()).device
|
||||
|
||||
@property
|
||||
def dtype(self):
|
||||
return next(self.parameters()).dtype
|
||||
|
||||
def enable_gradient_checkpointing(self, cpu_offload: bool = False):
|
||||
self.gradient_checkpointing = True
|
||||
self.cpu_offload_checkpointing = cpu_offload
|
||||
|
||||
for block in self.double_blocks + self.single_blocks:
|
||||
block.enable_gradient_checkpointing(cpu_offload=cpu_offload)
|
||||
|
||||
print(f"HunyuanImage-2.1: Gradient checkpointing enabled. CPU offload: {cpu_offload}")
|
||||
|
||||
def disable_gradient_checkpointing(self):
|
||||
self.gradient_checkpointing = False
|
||||
self.cpu_offload_checkpointing = False
|
||||
|
||||
for block in self.double_blocks + self.single_blocks:
|
||||
block.disable_gradient_checkpointing()
|
||||
|
||||
print("HunyuanImage-2.1: Gradient checkpointing disabled.")
|
||||
|
||||
def enable_block_swap(self, num_blocks: int, device: torch.device, supports_backward: bool = False):
|
||||
self.blocks_to_swap = num_blocks
|
||||
double_blocks_to_swap = num_blocks // 2
|
||||
single_blocks_to_swap = (num_blocks - double_blocks_to_swap) * 2
|
||||
|
||||
assert double_blocks_to_swap <= self.num_double_blocks - 2 and single_blocks_to_swap <= self.num_single_blocks - 2, (
|
||||
f"Cannot swap more than {self.num_double_blocks - 2} double blocks and {self.num_single_blocks - 2} single blocks. "
|
||||
f"Requested {double_blocks_to_swap} double blocks and {single_blocks_to_swap} single blocks."
|
||||
)
|
||||
|
||||
self.offloader_double = custom_offloading_utils.ModelOffloader(
|
||||
self.double_blocks, double_blocks_to_swap, device, supports_backward=supports_backward
|
||||
)
|
||||
self.offloader_single = custom_offloading_utils.ModelOffloader(
|
||||
self.single_blocks, single_blocks_to_swap, device, supports_backward=supports_backward
|
||||
)
|
||||
# , debug=True
|
||||
print(
|
||||
f"HunyuanImage-2.1: Block swap enabled. Swapping {num_blocks} blocks, double blocks: {double_blocks_to_swap}, single blocks: {single_blocks_to_swap}."
|
||||
)
|
||||
|
||||
def switch_block_swap_for_inference(self):
|
||||
if self.blocks_to_swap:
|
||||
self.offloader_double.set_forward_only(True)
|
||||
self.offloader_single.set_forward_only(True)
|
||||
self.prepare_block_swap_before_forward()
|
||||
print(f"HunyuanImage-2.1: Block swap set to forward only.")
|
||||
|
||||
def switch_block_swap_for_training(self):
|
||||
if self.blocks_to_swap:
|
||||
self.offloader_double.set_forward_only(False)
|
||||
self.offloader_single.set_forward_only(False)
|
||||
self.prepare_block_swap_before_forward()
|
||||
print(f"HunyuanImage-2.1: Block swap set to forward and backward.")
|
||||
|
||||
def move_to_device_except_swap_blocks(self, device: torch.device):
|
||||
# assume model is on cpu. do not move blocks to device to reduce temporary memory usage
|
||||
if self.blocks_to_swap:
|
||||
save_double_blocks = self.double_blocks
|
||||
save_single_blocks = self.single_blocks
|
||||
self.double_blocks = nn.ModuleList()
|
||||
self.single_blocks = nn.ModuleList()
|
||||
|
||||
self.to(device)
|
||||
|
||||
if self.blocks_to_swap:
|
||||
self.double_blocks = save_double_blocks
|
||||
self.single_blocks = save_single_blocks
|
||||
|
||||
def prepare_block_swap_before_forward(self):
|
||||
if self.blocks_to_swap is None or self.blocks_to_swap == 0:
|
||||
return
|
||||
self.offloader_double.prepare_block_devices_before_forward(self.double_blocks)
|
||||
self.offloader_single.prepare_block_devices_before_forward(self.single_blocks)
|
||||
|
||||
def get_rotary_pos_embed(self, rope_sizes):
|
||||
"""
|
||||
Generate 2D rotary position embeddings for image tokens.
|
||||
|
||||
Args:
|
||||
rope_sizes: Tuple of (height, width) for spatial dimensions.
|
||||
|
||||
Returns:
|
||||
Tuple of (freqs_cos, freqs_sin) tensors for rotary position encoding.
|
||||
"""
|
||||
freqs_cos, freqs_sin = get_nd_rotary_pos_embed(self.rope_dim_list, rope_sizes, theta=self.rope_theta)
|
||||
return freqs_cos, freqs_sin
|
||||
|
||||
def reorder_txt_token(
|
||||
self, byt5_txt: torch.Tensor, txt: torch.Tensor, byt5_text_mask: torch.Tensor, text_mask: torch.Tensor
|
||||
) -> Tuple[torch.Tensor, torch.Tensor, list[int]]:
|
||||
"""
|
||||
Combine and reorder ByT5 character-level and word-level text embeddings.
|
||||
|
||||
Concatenates valid tokens from both encoders and creates appropriate masks.
|
||||
|
||||
Args:
|
||||
byt5_txt: ByT5 character-level embeddings [B, L1, D].
|
||||
txt: Word-level text embeddings [B, L2, D].
|
||||
byt5_text_mask: Valid token mask for ByT5 [B, L1].
|
||||
text_mask: Valid token mask for word tokens [B, L2].
|
||||
|
||||
Returns:
|
||||
Tuple of (reordered_embeddings, combined_mask, sequence_lengths).
|
||||
"""
|
||||
# Process each batch element separately to handle variable sequence lengths
|
||||
|
||||
reorder_txt = []
|
||||
reorder_mask = []
|
||||
|
||||
txt_lens = []
|
||||
for i in range(text_mask.shape[0]):
|
||||
byt5_text_mask_i = byt5_text_mask[i].bool()
|
||||
text_mask_i = text_mask[i].bool()
|
||||
byt5_text_length = byt5_text_mask_i.sum()
|
||||
text_length = text_mask_i.sum()
|
||||
assert byt5_text_length == byt5_text_mask_i[:byt5_text_length].sum()
|
||||
assert text_length == text_mask_i[:text_length].sum()
|
||||
|
||||
byt5_txt_i = byt5_txt[i]
|
||||
txt_i = txt[i]
|
||||
reorder_txt_i = torch.cat(
|
||||
[byt5_txt_i[:byt5_text_length], txt_i[:text_length], byt5_txt_i[byt5_text_length:], txt_i[text_length:]], dim=0
|
||||
)
|
||||
|
||||
reorder_mask_i = torch.zeros(
|
||||
byt5_text_mask_i.shape[0] + text_mask_i.shape[0], dtype=torch.bool, device=byt5_text_mask_i.device
|
||||
)
|
||||
reorder_mask_i[: byt5_text_length + text_length] = True
|
||||
|
||||
reorder_txt.append(reorder_txt_i)
|
||||
reorder_mask.append(reorder_mask_i)
|
||||
txt_lens.append(byt5_text_length + text_length)
|
||||
|
||||
reorder_txt = torch.stack(reorder_txt)
|
||||
reorder_mask = torch.stack(reorder_mask).to(dtype=torch.int64)
|
||||
|
||||
return reorder_txt, reorder_mask, txt_lens
|
||||
|
||||
def forward(
|
||||
self,
|
||||
hidden_states: torch.Tensor,
|
||||
timestep: torch.LongTensor,
|
||||
text_states: torch.Tensor,
|
||||
encoder_attention_mask: torch.Tensor,
|
||||
byt5_text_states: Optional[torch.Tensor] = None,
|
||||
byt5_text_mask: Optional[torch.Tensor] = None,
|
||||
rotary_pos_emb_cache: Optional[Dict[Tuple[int, int], Tuple[torch.Tensor, torch.Tensor]]] = None,
|
||||
) -> torch.Tensor:
|
||||
"""
|
||||
Forward pass through the HunyuanImage diffusion transformer.
|
||||
|
||||
Args:
|
||||
hidden_states: Input image latents [B, C, H, W].
|
||||
timestep: Diffusion timestep [B].
|
||||
text_states: Word-level text embeddings [B, L, D].
|
||||
encoder_attention_mask: Text attention mask [B, L].
|
||||
byt5_text_states: ByT5 character-level embeddings [B, L_byt5, D_byt5].
|
||||
byt5_text_mask: ByT5 attention mask [B, L_byt5].
|
||||
|
||||
Returns:
|
||||
Tuple of (denoised_image, spatial_shape).
|
||||
"""
|
||||
img = x = hidden_states
|
||||
text_mask = encoder_attention_mask
|
||||
t = timestep
|
||||
txt = text_states
|
||||
|
||||
# Calculate spatial dimensions for rotary position embeddings
|
||||
_, _, oh, ow = x.shape
|
||||
th, tw = oh, ow # Height and width (patch_size=[1,1] means no spatial downsampling)
|
||||
if rotary_pos_emb_cache is not None:
|
||||
if (th, tw) in rotary_pos_emb_cache:
|
||||
freqs_cis = rotary_pos_emb_cache[(th, tw)]
|
||||
freqs_cis = (freqs_cis[0].to(img.device), freqs_cis[1].to(img.device))
|
||||
else:
|
||||
freqs_cis = self.get_rotary_pos_embed((th, tw))
|
||||
rotary_pos_emb_cache[(th, tw)] = (freqs_cis[0].cpu(), freqs_cis[1].cpu())
|
||||
else:
|
||||
freqs_cis = self.get_rotary_pos_embed((th, tw))
|
||||
|
||||
# Reshape image latents to sequence format: [B, C, H, W] -> [B, H*W, C]
|
||||
img = self.img_in(img)
|
||||
|
||||
# Generate timestep conditioning vector
|
||||
vec = self.time_in(t)
|
||||
|
||||
# MeanFlow and guidance embedding not used in this configuration
|
||||
|
||||
# Process text tokens through refinement layers
|
||||
txt_attn_params = AttentionParams.create_attention_params_from_mask(self.attn_mode, self.split_attn, 0, text_mask)
|
||||
txt = self.txt_in(txt, t, txt_attn_params)
|
||||
|
||||
# Integrate character-level ByT5 features with word-level tokens
|
||||
# Use variable length sequences with sequence lengths
|
||||
byt5_txt = self.byt5_in(byt5_text_states)
|
||||
txt, text_mask, txt_lens = self.reorder_txt_token(byt5_txt, txt, byt5_text_mask, text_mask)
|
||||
|
||||
# Trim sequences to maximum length in the batch
|
||||
img_seq_len = img.shape[1]
|
||||
max_txt_len = max(txt_lens)
|
||||
txt = txt[:, :max_txt_len, :]
|
||||
text_mask = text_mask[:, :max_txt_len]
|
||||
|
||||
attn_params = AttentionParams.create_attention_params_from_mask(self.attn_mode, self.split_attn, img_seq_len, text_mask)
|
||||
|
||||
input_device = img.device
|
||||
|
||||
# Process through double-stream blocks (separate image/text attention)
|
||||
for index, block in enumerate(self.double_blocks):
|
||||
if self.blocks_to_swap:
|
||||
self.offloader_double.wait_for_block(index)
|
||||
img, txt = block(img, txt, vec, freqs_cis, attn_params)
|
||||
if self.blocks_to_swap:
|
||||
self.offloader_double.submit_move_blocks(self.double_blocks, index)
|
||||
|
||||
# Concatenate image and text tokens for joint processing
|
||||
x = torch.cat((img, txt), 1)
|
||||
|
||||
# Process through single-stream blocks (joint attention)
|
||||
for index, block in enumerate(self.single_blocks):
|
||||
if self.blocks_to_swap:
|
||||
self.offloader_single.wait_for_block(index)
|
||||
x = block(x, vec, freqs_cis, attn_params)
|
||||
if self.blocks_to_swap:
|
||||
self.offloader_single.submit_move_blocks(self.single_blocks, index)
|
||||
|
||||
x = x.to(input_device)
|
||||
vec = vec.to(input_device)
|
||||
|
||||
img = x[:, :img_seq_len, ...]
|
||||
del x
|
||||
|
||||
# Apply final projection to output space
|
||||
img = self.final_layer(img, vec)
|
||||
del vec
|
||||
|
||||
# Reshape from sequence to spatial format: [B, L, C] -> [B, C, H, W]
|
||||
img = self.unpatchify_2d(img, th, tw)
|
||||
return img
|
||||
|
||||
def unpatchify_2d(self, x, h, w):
|
||||
"""
|
||||
Convert sequence format back to spatial image format.
|
||||
|
||||
Args:
|
||||
x: Input tensor [B, H*W, C].
|
||||
h: Height dimension.
|
||||
w: Width dimension.
|
||||
|
||||
Returns:
|
||||
Spatial tensor [B, C, H, W].
|
||||
"""
|
||||
c = self.unpatchify_channels
|
||||
|
||||
x = x.reshape(shape=(x.shape[0], h, w, c))
|
||||
imgs = x.permute(0, 3, 1, 2)
|
||||
return imgs
|
||||
|
||||
|
||||
# endregion
|
||||
|
||||
# region Model Utils
|
||||
|
||||
|
||||
def create_model(attn_mode: str, split_attn: bool, dtype: Optional[torch.dtype]) -> HYImageDiffusionTransformer:
|
||||
with init_empty_weights():
|
||||
model = HYImageDiffusionTransformer(attn_mode=attn_mode, split_attn=split_attn)
|
||||
if dtype is not None:
|
||||
model.to(dtype)
|
||||
return model
|
||||
|
||||
|
||||
def load_hunyuan_image_model(
|
||||
device: Union[str, torch.device],
|
||||
dit_path: str,
|
||||
attn_mode: str,
|
||||
split_attn: bool,
|
||||
loading_device: Union[str, torch.device],
|
||||
dit_weight_dtype: Optional[torch.dtype],
|
||||
fp8_scaled: bool = False,
|
||||
lora_weights_list: Optional[Dict[str, torch.Tensor]] = None,
|
||||
lora_multipliers: Optional[list[float]] = None,
|
||||
) -> HYImageDiffusionTransformer:
|
||||
"""
|
||||
Load a HunyuanImage model from the specified checkpoint.
|
||||
|
||||
Args:
|
||||
device (Union[str, torch.device]): Device for optimization or merging
|
||||
dit_path (str): Path to the DiT model checkpoint.
|
||||
attn_mode (str): Attention mode to use, e.g., "torch", "flash", etc.
|
||||
split_attn (bool): Whether to use split attention.
|
||||
loading_device (Union[str, torch.device]): Device to load the model weights on.
|
||||
dit_weight_dtype (Optional[torch.dtype]): Data type of the DiT weights.
|
||||
If None, it will be loaded as is (same as the state_dict) or scaled for fp8. if not None, model weights will be casted to this dtype.
|
||||
fp8_scaled (bool): Whether to use fp8 scaling for the model weights.
|
||||
lora_weights_list (Optional[Dict[str, torch.Tensor]]): LoRA weights to apply, if any.
|
||||
lora_multipliers (Optional[List[float]]): LoRA multipliers for the weights, if any.
|
||||
"""
|
||||
# dit_weight_dtype is None for fp8_scaled
|
||||
assert (not fp8_scaled and dit_weight_dtype is not None) or (fp8_scaled and dit_weight_dtype is None)
|
||||
|
||||
device = torch.device(device)
|
||||
loading_device = torch.device(loading_device)
|
||||
|
||||
model = create_model(attn_mode, split_attn, dit_weight_dtype)
|
||||
|
||||
# load model weights with dynamic fp8 optimization and LoRA merging if needed
|
||||
logger.info(f"Loading DiT model from {dit_path}, device={loading_device}")
|
||||
|
||||
sd = load_safetensors_with_lora_and_fp8(
|
||||
model_files=dit_path,
|
||||
lora_weights_list=lora_weights_list,
|
||||
lora_multipliers=lora_multipliers,
|
||||
fp8_optimization=fp8_scaled,
|
||||
calc_device=device,
|
||||
move_to_device=(loading_device == device),
|
||||
dit_weight_dtype=dit_weight_dtype,
|
||||
target_keys=FP8_OPTIMIZATION_TARGET_KEYS,
|
||||
exclude_keys=FP8_OPTIMIZATION_EXCLUDE_KEYS,
|
||||
)
|
||||
|
||||
if fp8_scaled:
|
||||
apply_fp8_monkey_patch(model, sd, use_scaled_mm=False)
|
||||
|
||||
if loading_device.type != "cpu":
|
||||
# make sure all the model weights are on the loading_device
|
||||
logger.info(f"Moving weights to {loading_device}")
|
||||
for key in sd.keys():
|
||||
sd[key] = sd[key].to(loading_device)
|
||||
|
||||
info = model.load_state_dict(sd, strict=True, assign=True)
|
||||
logger.info(f"Loaded DiT model from {dit_path}, info={info}")
|
||||
|
||||
return model
|
||||
|
||||
|
||||
# endregion
|
||||
863
library/hunyuan_image_modules.py
Normal file
863
library/hunyuan_image_modules.py
Normal file
@@ -0,0 +1,863 @@
|
||||
# Original work: https://github.com/Tencent-Hunyuan/HunyuanImage-2.1
|
||||
# Re-implemented for license compliance for sd-scripts.
|
||||
|
||||
from typing import Tuple, Callable
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from einops import rearrange
|
||||
|
||||
from library import custom_offloading_utils
|
||||
from library.attention import AttentionParams, attention
|
||||
from library.hunyuan_image_utils import timestep_embedding, apply_rotary_emb, _to_tuple, apply_gate, modulate
|
||||
from library.attention import attention
|
||||
|
||||
# region Modules
|
||||
|
||||
|
||||
class ByT5Mapper(nn.Module):
|
||||
"""
|
||||
Maps ByT5 character-level encoder outputs to transformer hidden space.
|
||||
|
||||
Applies layer normalization, two MLP layers with GELU activation,
|
||||
and optional residual connection.
|
||||
|
||||
Args:
|
||||
in_dim: Input dimension from ByT5 encoder (1472 for ByT5-large).
|
||||
out_dim: Intermediate dimension after first projection.
|
||||
hidden_dim: Hidden dimension for MLP layer.
|
||||
out_dim1: Final output dimension matching transformer hidden size.
|
||||
use_residual: Whether to add residual connection (requires in_dim == out_dim).
|
||||
"""
|
||||
|
||||
def __init__(self, in_dim, out_dim, hidden_dim, out_dim1, use_residual=True):
|
||||
super().__init__()
|
||||
if use_residual:
|
||||
assert in_dim == out_dim
|
||||
self.layernorm = nn.LayerNorm(in_dim)
|
||||
self.fc1 = nn.Linear(in_dim, hidden_dim)
|
||||
self.fc2 = nn.Linear(hidden_dim, out_dim)
|
||||
self.fc3 = nn.Linear(out_dim, out_dim1)
|
||||
self.use_residual = use_residual
|
||||
self.act_fn = nn.GELU()
|
||||
|
||||
def forward(self, x):
|
||||
"""
|
||||
Transform ByT5 embeddings to transformer space.
|
||||
|
||||
Args:
|
||||
x: Input ByT5 embeddings [..., in_dim].
|
||||
|
||||
Returns:
|
||||
Transformed embeddings [..., out_dim1].
|
||||
"""
|
||||
residual = x if self.use_residual else None
|
||||
x = self.layernorm(x)
|
||||
x = self.fc1(x)
|
||||
x = self.act_fn(x)
|
||||
x = self.fc2(x)
|
||||
x = self.act_fn(x)
|
||||
x = self.fc3(x)
|
||||
if self.use_residual:
|
||||
x = x + residual
|
||||
return x
|
||||
|
||||
|
||||
class PatchEmbed2D(nn.Module):
|
||||
"""
|
||||
2D patch embedding layer for converting image latents to transformer tokens.
|
||||
|
||||
Uses 2D convolution to project image patches to embedding space.
|
||||
For HunyuanImage-2.1, patch_size=[1,1] means no spatial downsampling.
|
||||
|
||||
Args:
|
||||
patch_size: Spatial size of patches (int or tuple).
|
||||
in_chans: Number of input channels.
|
||||
embed_dim: Output embedding dimension.
|
||||
"""
|
||||
|
||||
def __init__(self, patch_size=16, in_chans=3, embed_dim=768):
|
||||
super().__init__()
|
||||
self.patch_size = tuple(patch_size)
|
||||
|
||||
self.proj = nn.Conv2d(in_chans, embed_dim, kernel_size=self.patch_size, stride=self.patch_size, bias=True)
|
||||
self.norm = nn.Identity() # No normalization layer used
|
||||
|
||||
def forward(self, x):
|
||||
x = self.proj(x)
|
||||
x = x.flatten(2).transpose(1, 2)
|
||||
x = self.norm(x)
|
||||
return x
|
||||
|
||||
|
||||
class TimestepEmbedder(nn.Module):
|
||||
"""
|
||||
Embeds scalar diffusion timesteps into vector representations.
|
||||
|
||||
Uses sinusoidal encoding followed by a two-layer MLP.
|
||||
|
||||
Args:
|
||||
hidden_size: Output embedding dimension.
|
||||
act_layer: Activation function class (e.g., nn.SiLU).
|
||||
frequency_embedding_size: Dimension of sinusoidal encoding.
|
||||
max_period: Maximum period for sinusoidal frequencies.
|
||||
out_size: Output dimension (defaults to hidden_size).
|
||||
"""
|
||||
|
||||
def __init__(self, hidden_size, act_layer, frequency_embedding_size=256, max_period=10000, out_size=None):
|
||||
super().__init__()
|
||||
self.frequency_embedding_size = frequency_embedding_size
|
||||
self.max_period = max_period
|
||||
if out_size is None:
|
||||
out_size = hidden_size
|
||||
|
||||
self.mlp = nn.Sequential(
|
||||
nn.Linear(frequency_embedding_size, hidden_size, bias=True), act_layer(), nn.Linear(hidden_size, out_size, bias=True)
|
||||
)
|
||||
|
||||
def forward(self, t):
|
||||
t_freq = timestep_embedding(t, self.frequency_embedding_size, self.max_period).type(self.mlp[0].weight.dtype)
|
||||
return self.mlp(t_freq)
|
||||
|
||||
|
||||
class TextProjection(nn.Module):
|
||||
"""
|
||||
Projects text embeddings through a two-layer MLP.
|
||||
|
||||
Used for context-aware representation computation in token refinement.
|
||||
|
||||
Args:
|
||||
in_channels: Input feature dimension.
|
||||
hidden_size: Hidden and output dimension.
|
||||
act_layer: Activation function class.
|
||||
"""
|
||||
|
||||
def __init__(self, in_channels, hidden_size, act_layer):
|
||||
super().__init__()
|
||||
self.linear_1 = nn.Linear(in_features=in_channels, out_features=hidden_size, bias=True)
|
||||
self.act_1 = act_layer()
|
||||
self.linear_2 = nn.Linear(in_features=hidden_size, out_features=hidden_size, bias=True)
|
||||
|
||||
def forward(self, caption):
|
||||
hidden_states = self.linear_1(caption)
|
||||
hidden_states = self.act_1(hidden_states)
|
||||
hidden_states = self.linear_2(hidden_states)
|
||||
return hidden_states
|
||||
|
||||
|
||||
class MLP(nn.Module):
|
||||
"""
|
||||
Multi-layer perceptron with configurable activation and normalization.
|
||||
|
||||
Standard two-layer MLP with optional dropout and intermediate normalization.
|
||||
|
||||
Args:
|
||||
in_channels: Input feature dimension.
|
||||
hidden_channels: Hidden layer dimension (defaults to in_channels).
|
||||
out_features: Output dimension (defaults to in_channels).
|
||||
act_layer: Activation function class.
|
||||
norm_layer: Optional normalization layer class.
|
||||
bias: Whether to use bias (can be bool or tuple for each layer).
|
||||
drop: Dropout rate (can be float or tuple for each layer).
|
||||
use_conv: Whether to use convolution instead of linear (not supported).
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
in_channels,
|
||||
hidden_channels=None,
|
||||
out_features=None,
|
||||
act_layer=nn.GELU,
|
||||
norm_layer=None,
|
||||
bias=True,
|
||||
drop=0.0,
|
||||
use_conv=False,
|
||||
):
|
||||
super().__init__()
|
||||
assert not use_conv, "Convolutional MLP not supported in this implementation."
|
||||
|
||||
out_features = out_features or in_channels
|
||||
hidden_channels = hidden_channels or in_channels
|
||||
bias = _to_tuple(bias, 2)
|
||||
drop_probs = _to_tuple(drop, 2)
|
||||
|
||||
self.fc1 = nn.Linear(in_channels, hidden_channels, bias=bias[0])
|
||||
self.act = act_layer()
|
||||
self.drop1 = nn.Dropout(drop_probs[0])
|
||||
self.norm = norm_layer(hidden_channels) if norm_layer is not None else nn.Identity()
|
||||
self.fc2 = nn.Linear(hidden_channels, out_features, bias=bias[1])
|
||||
self.drop2 = nn.Dropout(drop_probs[1])
|
||||
|
||||
def forward(self, x):
|
||||
x = self.fc1(x)
|
||||
x = self.act(x)
|
||||
x = self.drop1(x)
|
||||
x = self.norm(x)
|
||||
x = self.fc2(x)
|
||||
x = self.drop2(x)
|
||||
return x
|
||||
|
||||
|
||||
class IndividualTokenRefinerBlock(nn.Module):
|
||||
"""
|
||||
Single transformer block for individual token refinement.
|
||||
|
||||
Applies self-attention and MLP with adaptive layer normalization (AdaLN)
|
||||
conditioned on timestep and context information.
|
||||
|
||||
Args:
|
||||
hidden_size: Model dimension.
|
||||
heads_num: Number of attention heads.
|
||||
mlp_width_ratio: MLP expansion ratio.
|
||||
mlp_drop_rate: MLP dropout rate.
|
||||
act_type: Activation function (only "silu" supported).
|
||||
qk_norm: QK normalization flag (must be False).
|
||||
qk_norm_type: QK normalization type (only "layer" supported).
|
||||
qkv_bias: Use bias in QKV projections.
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
hidden_size: int,
|
||||
heads_num: int,
|
||||
mlp_width_ratio: float = 4.0,
|
||||
mlp_drop_rate: float = 0.0,
|
||||
act_type: str = "silu",
|
||||
qk_norm: bool = False,
|
||||
qk_norm_type: str = "layer",
|
||||
qkv_bias: bool = True,
|
||||
):
|
||||
super().__init__()
|
||||
assert qk_norm_type == "layer", "Only layer normalization supported for QK norm."
|
||||
assert act_type == "silu", "Only SiLU activation supported."
|
||||
assert not qk_norm, "QK normalization must be disabled."
|
||||
|
||||
self.heads_num = heads_num
|
||||
mlp_hidden_dim = int(hidden_size * mlp_width_ratio)
|
||||
|
||||
self.norm1 = nn.LayerNorm(hidden_size, elementwise_affine=True, eps=1e-6)
|
||||
self.self_attn_qkv = nn.Linear(hidden_size, hidden_size * 3, bias=qkv_bias)
|
||||
|
||||
self.self_attn_q_norm = nn.Identity()
|
||||
self.self_attn_k_norm = nn.Identity()
|
||||
self.self_attn_proj = nn.Linear(hidden_size, hidden_size, bias=qkv_bias)
|
||||
|
||||
self.norm2 = nn.LayerNorm(hidden_size, elementwise_affine=True, eps=1e-6)
|
||||
self.mlp = MLP(in_channels=hidden_size, hidden_channels=mlp_hidden_dim, act_layer=nn.SiLU, drop=mlp_drop_rate)
|
||||
|
||||
self.adaLN_modulation = nn.Sequential(
|
||||
nn.SiLU(),
|
||||
nn.Linear(hidden_size, 2 * hidden_size, bias=True),
|
||||
)
|
||||
|
||||
def forward(self, x: torch.Tensor, c: torch.Tensor, attn_params: AttentionParams) -> torch.Tensor:
|
||||
"""
|
||||
Apply self-attention and MLP with adaptive conditioning.
|
||||
|
||||
Args:
|
||||
x: Input token embeddings [B, L, C].
|
||||
c: Combined conditioning vector [B, C].
|
||||
attn_params: Attention parameters including sequence lengths.
|
||||
|
||||
Returns:
|
||||
Refined token embeddings [B, L, C].
|
||||
"""
|
||||
gate_msa, gate_mlp = self.adaLN_modulation(c).chunk(2, dim=1)
|
||||
norm_x = self.norm1(x)
|
||||
qkv = self.self_attn_qkv(norm_x)
|
||||
del norm_x
|
||||
q, k, v = rearrange(qkv, "B L (K H D) -> K B L H D", K=3, H=self.heads_num)
|
||||
del qkv
|
||||
q = self.self_attn_q_norm(q).to(v)
|
||||
k = self.self_attn_k_norm(k).to(v)
|
||||
qkv = [q, k, v]
|
||||
del q, k, v
|
||||
attn = attention(qkv, attn_params=attn_params)
|
||||
|
||||
x = x + apply_gate(self.self_attn_proj(attn), gate_msa)
|
||||
x = x + apply_gate(self.mlp(self.norm2(x)), gate_mlp)
|
||||
return x
|
||||
|
||||
|
||||
class IndividualTokenRefiner(nn.Module):
|
||||
"""
|
||||
Stack of token refinement blocks with self-attention.
|
||||
|
||||
Processes tokens individually with adaptive layer normalization.
|
||||
|
||||
Args:
|
||||
hidden_size: Model dimension.
|
||||
heads_num: Number of attention heads.
|
||||
depth: Number of refinement blocks.
|
||||
mlp_width_ratio: MLP expansion ratio.
|
||||
mlp_drop_rate: MLP dropout rate.
|
||||
act_type: Activation function type.
|
||||
qk_norm: QK normalization flag.
|
||||
qk_norm_type: QK normalization type.
|
||||
qkv_bias: Use bias in QKV projections.
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
hidden_size: int,
|
||||
heads_num: int,
|
||||
depth: int,
|
||||
mlp_width_ratio: float = 4.0,
|
||||
mlp_drop_rate: float = 0.0,
|
||||
act_type: str = "silu",
|
||||
qk_norm: bool = False,
|
||||
qk_norm_type: str = "layer",
|
||||
qkv_bias: bool = True,
|
||||
):
|
||||
super().__init__()
|
||||
self.blocks = nn.ModuleList(
|
||||
[
|
||||
IndividualTokenRefinerBlock(
|
||||
hidden_size=hidden_size,
|
||||
heads_num=heads_num,
|
||||
mlp_width_ratio=mlp_width_ratio,
|
||||
mlp_drop_rate=mlp_drop_rate,
|
||||
act_type=act_type,
|
||||
qk_norm=qk_norm,
|
||||
qk_norm_type=qk_norm_type,
|
||||
qkv_bias=qkv_bias,
|
||||
)
|
||||
for _ in range(depth)
|
||||
]
|
||||
)
|
||||
|
||||
def forward(self, x: torch.Tensor, c: torch.LongTensor, attn_params: AttentionParams) -> torch.Tensor:
|
||||
"""
|
||||
Apply sequential token refinement.
|
||||
|
||||
Args:
|
||||
x: Input token embeddings [B, L, C].
|
||||
c: Combined conditioning vector [B, C].
|
||||
attn_params: Attention parameters including sequence lengths.
|
||||
|
||||
Returns:
|
||||
Refined token embeddings [B, L, C].
|
||||
"""
|
||||
for block in self.blocks:
|
||||
x = block(x, c, attn_params)
|
||||
return x
|
||||
|
||||
|
||||
class SingleTokenRefiner(nn.Module):
|
||||
"""
|
||||
Text embedding refinement with timestep and context conditioning.
|
||||
|
||||
Projects input text embeddings and applies self-attention refinement
|
||||
conditioned on diffusion timestep and aggregate text context.
|
||||
|
||||
Args:
|
||||
in_channels: Input text embedding dimension.
|
||||
hidden_size: Transformer hidden dimension.
|
||||
heads_num: Number of attention heads.
|
||||
depth: Number of refinement blocks.
|
||||
"""
|
||||
|
||||
def __init__(self, in_channels: int, hidden_size: int, heads_num: int, depth: int):
|
||||
# Fixed architecture parameters for HunyuanImage-2.1
|
||||
mlp_drop_rate: float = 0.0 # No MLP dropout
|
||||
act_type: str = "silu" # SiLU activation
|
||||
mlp_width_ratio: float = 4.0 # 4x MLP expansion
|
||||
qk_norm: bool = False # No QK normalization
|
||||
qk_norm_type: str = "layer" # Layer norm type (unused)
|
||||
qkv_bias: bool = True # Use QKV bias
|
||||
|
||||
super().__init__()
|
||||
self.input_embedder = nn.Linear(in_channels, hidden_size, bias=True)
|
||||
act_layer = nn.SiLU
|
||||
self.t_embedder = TimestepEmbedder(hidden_size, act_layer)
|
||||
self.c_embedder = TextProjection(in_channels, hidden_size, act_layer)
|
||||
self.individual_token_refiner = IndividualTokenRefiner(
|
||||
hidden_size=hidden_size,
|
||||
heads_num=heads_num,
|
||||
depth=depth,
|
||||
mlp_width_ratio=mlp_width_ratio,
|
||||
mlp_drop_rate=mlp_drop_rate,
|
||||
act_type=act_type,
|
||||
qk_norm=qk_norm,
|
||||
qk_norm_type=qk_norm_type,
|
||||
qkv_bias=qkv_bias,
|
||||
)
|
||||
|
||||
def forward(self, x: torch.Tensor, t: torch.LongTensor, attn_params: AttentionParams) -> torch.Tensor:
|
||||
"""
|
||||
Refine text embeddings with timestep conditioning.
|
||||
|
||||
Args:
|
||||
x: Input text embeddings [B, L, in_channels].
|
||||
t: Diffusion timestep [B].
|
||||
attn_params: Attention parameters including sequence lengths.
|
||||
|
||||
Returns:
|
||||
Refined embeddings [B, L, hidden_size].
|
||||
"""
|
||||
timestep_aware_representations = self.t_embedder(t)
|
||||
|
||||
# Compute context-aware representations by averaging valid tokens
|
||||
txt_lens = attn_params.seqlens # img_len is not used for SingleTokenRefiner
|
||||
context_aware_representations = torch.stack([x[i, : txt_lens[i]].mean(dim=0) for i in range(x.shape[0])], dim=0) # [B, C]
|
||||
|
||||
context_aware_representations = self.c_embedder(context_aware_representations)
|
||||
c = timestep_aware_representations + context_aware_representations
|
||||
del timestep_aware_representations, context_aware_representations
|
||||
x = self.input_embedder(x)
|
||||
x = self.individual_token_refiner(x, c, attn_params)
|
||||
return x
|
||||
|
||||
|
||||
class FinalLayer(nn.Module):
|
||||
"""
|
||||
Final output projection layer with adaptive layer normalization.
|
||||
|
||||
Projects transformer hidden states to output patch space with
|
||||
timestep-conditioned modulation.
|
||||
|
||||
Args:
|
||||
hidden_size: Input hidden dimension.
|
||||
patch_size: Spatial patch size for output reshaping.
|
||||
out_channels: Number of output channels.
|
||||
act_layer: Activation function class.
|
||||
"""
|
||||
|
||||
def __init__(self, hidden_size, patch_size, out_channels, act_layer):
|
||||
super().__init__()
|
||||
|
||||
# Layer normalization without learnable parameters
|
||||
self.norm_final = nn.LayerNorm(hidden_size, elementwise_affine=False, eps=1e-6)
|
||||
out_size = (patch_size[0] * patch_size[1]) * out_channels
|
||||
self.linear = nn.Linear(hidden_size, out_size, bias=True)
|
||||
|
||||
# Adaptive layer normalization modulation
|
||||
self.adaLN_modulation = nn.Sequential(
|
||||
act_layer(),
|
||||
nn.Linear(hidden_size, 2 * hidden_size, bias=True),
|
||||
)
|
||||
|
||||
def forward(self, x, c):
|
||||
shift, scale = self.adaLN_modulation(c).chunk(2, dim=1)
|
||||
x = modulate(self.norm_final(x), shift=shift, scale=scale)
|
||||
del shift, scale, c
|
||||
x = self.linear(x)
|
||||
return x
|
||||
|
||||
|
||||
class RMSNorm(nn.Module):
|
||||
"""
|
||||
Root Mean Square Layer Normalization.
|
||||
|
||||
Normalizes input using RMS and applies learnable scaling.
|
||||
More efficient than LayerNorm as it doesn't compute mean.
|
||||
|
||||
Args:
|
||||
dim: Input feature dimension.
|
||||
eps: Small value for numerical stability.
|
||||
"""
|
||||
|
||||
def __init__(self, dim: int, eps: float = 1e-6):
|
||||
super().__init__()
|
||||
self.eps = eps
|
||||
self.weight = nn.Parameter(torch.ones(dim))
|
||||
|
||||
def _norm(self, x):
|
||||
"""
|
||||
Apply RMS normalization.
|
||||
|
||||
Args:
|
||||
x: Input tensor.
|
||||
|
||||
Returns:
|
||||
RMS normalized tensor.
|
||||
"""
|
||||
return x * torch.rsqrt(x.pow(2).mean(-1, keepdim=True) + self.eps)
|
||||
|
||||
def reset_parameters(self):
|
||||
self.weight.fill_(1)
|
||||
|
||||
def forward(self, x):
|
||||
"""
|
||||
Apply RMSNorm with learnable scaling.
|
||||
|
||||
Args:
|
||||
x: Input tensor.
|
||||
|
||||
Returns:
|
||||
Normalized and scaled tensor.
|
||||
"""
|
||||
output = self._norm(x.float()).type_as(x)
|
||||
del x
|
||||
# output = output * self.weight
|
||||
# fp8 support
|
||||
output = output * self.weight.to(output.dtype)
|
||||
return output
|
||||
|
||||
|
||||
# kept for reference, not used in current implementation
|
||||
# class LinearWarpforSingle(nn.Module):
|
||||
# """
|
||||
# Linear layer wrapper for concatenating and projecting two inputs.
|
||||
|
||||
# Used in single-stream blocks to combine attention output with MLP features.
|
||||
|
||||
# Args:
|
||||
# in_dim: Input dimension (sum of both input feature dimensions).
|
||||
# out_dim: Output dimension.
|
||||
# bias: Whether to use bias in linear projection.
|
||||
# """
|
||||
|
||||
# def __init__(self, in_dim: int, out_dim: int, bias=False):
|
||||
# super().__init__()
|
||||
# self.fc = nn.Linear(in_dim, out_dim, bias=bias)
|
||||
|
||||
# def forward(self, x, y):
|
||||
# """Concatenate inputs along feature dimension and project."""
|
||||
# x = torch.cat([x.contiguous(), y.contiguous()], dim=2).contiguous()
|
||||
# return self.fc(x)
|
||||
|
||||
|
||||
class ModulateDiT(nn.Module):
|
||||
"""
|
||||
Timestep conditioning modulation layer.
|
||||
|
||||
Projects timestep embeddings to multiple modulation parameters
|
||||
for adaptive layer normalization.
|
||||
|
||||
Args:
|
||||
hidden_size: Input conditioning dimension.
|
||||
factor: Number of modulation parameters to generate.
|
||||
act_layer: Activation function class.
|
||||
"""
|
||||
|
||||
def __init__(self, hidden_size: int, factor: int, act_layer: Callable):
|
||||
super().__init__()
|
||||
self.act = act_layer()
|
||||
self.linear = nn.Linear(hidden_size, factor * hidden_size, bias=True)
|
||||
|
||||
def forward(self, x: torch.Tensor) -> torch.Tensor:
|
||||
return self.linear(self.act(x))
|
||||
|
||||
|
||||
class MMDoubleStreamBlock(nn.Module):
|
||||
"""
|
||||
Multimodal double-stream transformer block.
|
||||
|
||||
Processes image and text tokens separately with cross-modal attention.
|
||||
Each stream has its own normalization and MLP layers but shares
|
||||
attention computation for cross-modal interaction.
|
||||
|
||||
Args:
|
||||
hidden_size: Model dimension.
|
||||
heads_num: Number of attention heads.
|
||||
mlp_width_ratio: MLP expansion ratio.
|
||||
mlp_act_type: MLP activation function (only "gelu_tanh" supported).
|
||||
qk_norm: QK normalization flag (must be True).
|
||||
qk_norm_type: QK normalization type (only "rms" supported).
|
||||
qkv_bias: Use bias in QKV projections.
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
hidden_size: int,
|
||||
heads_num: int,
|
||||
mlp_width_ratio: float,
|
||||
mlp_act_type: str = "gelu_tanh",
|
||||
qk_norm: bool = True,
|
||||
qk_norm_type: str = "rms",
|
||||
qkv_bias: bool = False,
|
||||
):
|
||||
super().__init__()
|
||||
|
||||
assert mlp_act_type == "gelu_tanh", "Only GELU-tanh activation supported."
|
||||
assert qk_norm_type == "rms", "Only RMS normalization supported."
|
||||
assert qk_norm, "QK normalization must be enabled."
|
||||
|
||||
self.heads_num = heads_num
|
||||
head_dim = hidden_size // heads_num
|
||||
mlp_hidden_dim = int(hidden_size * mlp_width_ratio)
|
||||
|
||||
# Image stream processing components
|
||||
self.img_mod = ModulateDiT(hidden_size, factor=6, act_layer=nn.SiLU)
|
||||
self.img_norm1 = nn.LayerNorm(hidden_size, elementwise_affine=False, eps=1e-6)
|
||||
|
||||
self.img_attn_qkv = nn.Linear(hidden_size, hidden_size * 3, bias=qkv_bias)
|
||||
|
||||
self.img_attn_q_norm = RMSNorm(head_dim, eps=1e-6)
|
||||
self.img_attn_k_norm = RMSNorm(head_dim, eps=1e-6)
|
||||
self.img_attn_proj = nn.Linear(hidden_size, hidden_size, bias=qkv_bias)
|
||||
|
||||
self.img_norm2 = nn.LayerNorm(hidden_size, elementwise_affine=False, eps=1e-6)
|
||||
self.img_mlp = MLP(hidden_size, mlp_hidden_dim, act_layer=lambda: nn.GELU(approximate="tanh"), bias=True)
|
||||
|
||||
# Text stream processing components
|
||||
self.txt_mod = ModulateDiT(hidden_size, factor=6, act_layer=nn.SiLU)
|
||||
self.txt_norm1 = nn.LayerNorm(hidden_size, elementwise_affine=False, eps=1e-6)
|
||||
|
||||
self.txt_attn_qkv = nn.Linear(hidden_size, hidden_size * 3, bias=qkv_bias)
|
||||
self.txt_attn_q_norm = RMSNorm(head_dim, eps=1e-6)
|
||||
self.txt_attn_k_norm = RMSNorm(head_dim, eps=1e-6)
|
||||
self.txt_attn_proj = nn.Linear(hidden_size, hidden_size, bias=qkv_bias)
|
||||
|
||||
self.txt_norm2 = nn.LayerNorm(hidden_size, elementwise_affine=False, eps=1e-6)
|
||||
self.txt_mlp = MLP(hidden_size, mlp_hidden_dim, act_layer=lambda: nn.GELU(approximate="tanh"), bias=True)
|
||||
|
||||
self.gradient_checkpointing = False
|
||||
self.cpu_offload_checkpointing = False
|
||||
|
||||
def enable_gradient_checkpointing(self, cpu_offload: bool = False):
|
||||
self.gradient_checkpointing = True
|
||||
self.cpu_offload_checkpointing = cpu_offload
|
||||
|
||||
def disable_gradient_checkpointing(self):
|
||||
self.gradient_checkpointing = False
|
||||
self.cpu_offload_checkpointing = False
|
||||
|
||||
def _forward(
|
||||
self, img: torch.Tensor, txt: torch.Tensor, vec: torch.Tensor, freqs_cis: tuple = None, attn_params: AttentionParams = None
|
||||
) -> Tuple[torch.Tensor, torch.Tensor]:
|
||||
# Extract modulation parameters for image and text streams
|
||||
(img_mod1_shift, img_mod1_scale, img_mod1_gate, img_mod2_shift, img_mod2_scale, img_mod2_gate) = self.img_mod(vec).chunk(
|
||||
6, dim=-1
|
||||
)
|
||||
(txt_mod1_shift, txt_mod1_scale, txt_mod1_gate, txt_mod2_shift, txt_mod2_scale, txt_mod2_gate) = self.txt_mod(vec).chunk(
|
||||
6, dim=-1
|
||||
)
|
||||
|
||||
# Process image stream for attention
|
||||
img_modulated = self.img_norm1(img)
|
||||
img_modulated = modulate(img_modulated, shift=img_mod1_shift, scale=img_mod1_scale)
|
||||
del img_mod1_shift, img_mod1_scale
|
||||
|
||||
img_qkv = self.img_attn_qkv(img_modulated)
|
||||
del img_modulated
|
||||
img_q, img_k, img_v = img_qkv.chunk(3, dim=-1)
|
||||
del img_qkv
|
||||
|
||||
img_q = rearrange(img_q, "B L (H D) -> B L H D", H=self.heads_num)
|
||||
img_k = rearrange(img_k, "B L (H D) -> B L H D", H=self.heads_num)
|
||||
img_v = rearrange(img_v, "B L (H D) -> B L H D", H=self.heads_num)
|
||||
|
||||
# Apply QK-Norm if enabled
|
||||
img_q = self.img_attn_q_norm(img_q).to(img_v)
|
||||
img_k = self.img_attn_k_norm(img_k).to(img_v)
|
||||
|
||||
# Apply rotary position embeddings to image tokens
|
||||
if freqs_cis is not None:
|
||||
img_q, img_k = apply_rotary_emb(img_q, img_k, freqs_cis, head_first=False)
|
||||
del freqs_cis
|
||||
|
||||
# Process text stream for attention
|
||||
txt_modulated = self.txt_norm1(txt)
|
||||
txt_modulated = modulate(txt_modulated, shift=txt_mod1_shift, scale=txt_mod1_scale)
|
||||
|
||||
txt_qkv = self.txt_attn_qkv(txt_modulated)
|
||||
del txt_modulated
|
||||
txt_q, txt_k, txt_v = txt_qkv.chunk(3, dim=-1)
|
||||
del txt_qkv
|
||||
|
||||
txt_q = rearrange(txt_q, "B L (H D) -> B L H D", H=self.heads_num)
|
||||
txt_k = rearrange(txt_k, "B L (H D) -> B L H D", H=self.heads_num)
|
||||
txt_v = rearrange(txt_v, "B L (H D) -> B L H D", H=self.heads_num)
|
||||
|
||||
# Apply QK-Norm if enabled
|
||||
txt_q = self.txt_attn_q_norm(txt_q).to(txt_v)
|
||||
txt_k = self.txt_attn_k_norm(txt_k).to(txt_v)
|
||||
|
||||
# Concatenate image and text tokens for joint attention
|
||||
img_seq_len = img.shape[1]
|
||||
q = torch.cat([img_q, txt_q], dim=1)
|
||||
del img_q, txt_q
|
||||
k = torch.cat([img_k, txt_k], dim=1)
|
||||
del img_k, txt_k
|
||||
v = torch.cat([img_v, txt_v], dim=1)
|
||||
del img_v, txt_v
|
||||
|
||||
qkv = [q, k, v]
|
||||
del q, k, v
|
||||
attn = attention(qkv, attn_params=attn_params)
|
||||
del qkv
|
||||
|
||||
# Split attention outputs back to separate streams
|
||||
img_attn, txt_attn = (attn[:, :img_seq_len].contiguous(), attn[:, img_seq_len:].contiguous())
|
||||
del attn
|
||||
|
||||
# Apply attention projection and residual connection for image stream
|
||||
img = img + apply_gate(self.img_attn_proj(img_attn), gate=img_mod1_gate)
|
||||
del img_attn, img_mod1_gate
|
||||
|
||||
# Apply MLP and residual connection for image stream
|
||||
img = img + apply_gate(
|
||||
self.img_mlp(modulate(self.img_norm2(img), shift=img_mod2_shift, scale=img_mod2_scale)),
|
||||
gate=img_mod2_gate,
|
||||
)
|
||||
del img_mod2_shift, img_mod2_scale, img_mod2_gate
|
||||
|
||||
# Apply attention projection and residual connection for text stream
|
||||
txt = txt + apply_gate(self.txt_attn_proj(txt_attn), gate=txt_mod1_gate)
|
||||
del txt_attn, txt_mod1_gate
|
||||
|
||||
# Apply MLP and residual connection for text stream
|
||||
txt = txt + apply_gate(
|
||||
self.txt_mlp(modulate(self.txt_norm2(txt), shift=txt_mod2_shift, scale=txt_mod2_scale)),
|
||||
gate=txt_mod2_gate,
|
||||
)
|
||||
del txt_mod2_shift, txt_mod2_scale, txt_mod2_gate
|
||||
|
||||
return img, txt
|
||||
|
||||
def forward(
|
||||
self, img: torch.Tensor, txt: torch.Tensor, vec: torch.Tensor, freqs_cis: tuple = None, attn_params: AttentionParams = None
|
||||
) -> Tuple[torch.Tensor, torch.Tensor]:
|
||||
if self.gradient_checkpointing and self.training:
|
||||
forward_fn = self._forward
|
||||
if self.cpu_offload_checkpointing:
|
||||
forward_fn = custom_offloading_utils.cpu_offload_wrapper(forward_fn, self.img_attn_qkv.weight.device)
|
||||
|
||||
return torch.utils.checkpoint.checkpoint(forward_fn, img, txt, vec, freqs_cis, attn_params, use_reentrant=False)
|
||||
else:
|
||||
return self._forward(img, txt, vec, freqs_cis, attn_params)
|
||||
|
||||
|
||||
class MMSingleStreamBlock(nn.Module):
|
||||
"""
|
||||
Multimodal single-stream transformer block.
|
||||
|
||||
Processes concatenated image and text tokens jointly with shared attention.
|
||||
Uses parallel linear layers for efficiency and applies RoPE only to image tokens.
|
||||
|
||||
Args:
|
||||
hidden_size: Model dimension.
|
||||
heads_num: Number of attention heads.
|
||||
mlp_width_ratio: MLP expansion ratio.
|
||||
mlp_act_type: MLP activation function (only "gelu_tanh" supported).
|
||||
qk_norm: QK normalization flag (must be True).
|
||||
qk_norm_type: QK normalization type (only "rms" supported).
|
||||
qk_scale: Attention scaling factor (computed automatically if None).
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
hidden_size: int,
|
||||
heads_num: int,
|
||||
mlp_width_ratio: float = 4.0,
|
||||
mlp_act_type: str = "gelu_tanh",
|
||||
qk_norm: bool = True,
|
||||
qk_norm_type: str = "rms",
|
||||
qk_scale: float = None,
|
||||
):
|
||||
super().__init__()
|
||||
|
||||
assert mlp_act_type == "gelu_tanh", "Only GELU-tanh activation supported."
|
||||
assert qk_norm_type == "rms", "Only RMS normalization supported."
|
||||
assert qk_norm, "QK normalization must be enabled."
|
||||
|
||||
self.hidden_size = hidden_size
|
||||
self.heads_num = heads_num
|
||||
head_dim = hidden_size // heads_num
|
||||
mlp_hidden_dim = int(hidden_size * mlp_width_ratio)
|
||||
self.mlp_hidden_dim = mlp_hidden_dim
|
||||
self.scale = qk_scale or head_dim**-0.5
|
||||
|
||||
# Parallel linear projections for efficiency
|
||||
self.linear1 = nn.Linear(hidden_size, hidden_size * 3 + mlp_hidden_dim)
|
||||
|
||||
# Combined output projection
|
||||
# self.linear2 = LinearWarpforSingle(hidden_size + mlp_hidden_dim, hidden_size, bias=True) # for reference
|
||||
self.linear2 = nn.Linear(hidden_size + mlp_hidden_dim, hidden_size, bias=True)
|
||||
|
||||
# QK normalization layers
|
||||
self.q_norm = RMSNorm(head_dim, eps=1e-6)
|
||||
self.k_norm = RMSNorm(head_dim, eps=1e-6)
|
||||
|
||||
self.pre_norm = nn.LayerNorm(hidden_size, elementwise_affine=False, eps=1e-6)
|
||||
|
||||
self.mlp_act = nn.GELU(approximate="tanh")
|
||||
self.modulation = ModulateDiT(hidden_size, factor=3, act_layer=nn.SiLU)
|
||||
|
||||
self.gradient_checkpointing = False
|
||||
self.cpu_offload_checkpointing = False
|
||||
|
||||
def enable_gradient_checkpointing(self, cpu_offload: bool = False):
|
||||
self.gradient_checkpointing = True
|
||||
self.cpu_offload_checkpointing = cpu_offload
|
||||
|
||||
def disable_gradient_checkpointing(self):
|
||||
self.gradient_checkpointing = False
|
||||
self.cpu_offload_checkpointing = False
|
||||
|
||||
def _forward(
|
||||
self,
|
||||
x: torch.Tensor,
|
||||
vec: torch.Tensor,
|
||||
freqs_cis: Tuple[torch.Tensor, torch.Tensor] = None,
|
||||
attn_params: AttentionParams = None,
|
||||
) -> torch.Tensor:
|
||||
# Extract modulation parameters
|
||||
mod_shift, mod_scale, mod_gate = self.modulation(vec).chunk(3, dim=-1)
|
||||
x_mod = modulate(self.pre_norm(x), shift=mod_shift, scale=mod_scale)
|
||||
|
||||
# Compute Q, K, V, and MLP input
|
||||
qkv_mlp = self.linear1(x_mod)
|
||||
del x_mod
|
||||
q, k, v, mlp = qkv_mlp.split([self.hidden_size, self.hidden_size, self.hidden_size, self.mlp_hidden_dim], dim=-1)
|
||||
del qkv_mlp
|
||||
|
||||
q = rearrange(q, "B L (H D) -> B L H D", H=self.heads_num)
|
||||
k = rearrange(k, "B L (H D) -> B L H D", H=self.heads_num)
|
||||
v = rearrange(v, "B L (H D) -> B L H D", H=self.heads_num)
|
||||
|
||||
# Apply QK-Norm if enabled
|
||||
q = self.q_norm(q).to(v)
|
||||
k = self.k_norm(k).to(v)
|
||||
|
||||
# Separate image and text tokens
|
||||
img_q, txt_q = q[:, : attn_params.img_len, :, :], q[:, attn_params.img_len :, :, :]
|
||||
del q
|
||||
img_k, txt_k = k[:, : attn_params.img_len, :, :], k[:, attn_params.img_len :, :, :]
|
||||
del k
|
||||
|
||||
# Apply rotary position embeddings only to image tokens
|
||||
img_q, img_k = apply_rotary_emb(img_q, img_k, freqs_cis, head_first=False)
|
||||
del freqs_cis
|
||||
|
||||
# Recombine and compute joint attention
|
||||
q = torch.cat([img_q, txt_q], dim=1)
|
||||
del img_q, txt_q
|
||||
k = torch.cat([img_k, txt_k], dim=1)
|
||||
del img_k, txt_k
|
||||
# v = torch.cat([img_v, txt_v], dim=1)
|
||||
# del img_v, txt_v
|
||||
qkv = [q, k, v]
|
||||
del q, k, v
|
||||
attn = attention(qkv, attn_params=attn_params)
|
||||
del qkv
|
||||
|
||||
# Combine attention and MLP outputs, apply gating
|
||||
# output = self.linear2(attn, self.mlp_act(mlp))
|
||||
|
||||
mlp = self.mlp_act(mlp)
|
||||
output = torch.cat([attn, mlp], dim=2).contiguous()
|
||||
del attn, mlp
|
||||
output = self.linear2(output)
|
||||
|
||||
return x + apply_gate(output, gate=mod_gate)
|
||||
|
||||
def forward(
|
||||
self,
|
||||
x: torch.Tensor,
|
||||
vec: torch.Tensor,
|
||||
freqs_cis: Tuple[torch.Tensor, torch.Tensor] = None,
|
||||
attn_params: AttentionParams = None,
|
||||
) -> torch.Tensor:
|
||||
if self.gradient_checkpointing and self.training:
|
||||
forward_fn = self._forward
|
||||
if self.cpu_offload_checkpointing:
|
||||
forward_fn = custom_offloading_utils.create_cpu_offloading_wrapper(forward_fn, self.linear1.weight.device)
|
||||
|
||||
return torch.utils.checkpoint.checkpoint(forward_fn, x, vec, freqs_cis, attn_params, use_reentrant=False)
|
||||
else:
|
||||
return self._forward(x, vec, freqs_cis, attn_params)
|
||||
|
||||
|
||||
# endregion
|
||||
661
library/hunyuan_image_text_encoder.py
Normal file
661
library/hunyuan_image_text_encoder.py
Normal file
@@ -0,0 +1,661 @@
|
||||
import json
|
||||
import re
|
||||
from typing import Tuple, Optional, Union
|
||||
import torch
|
||||
from transformers import (
|
||||
AutoTokenizer,
|
||||
Qwen2_5_VLConfig,
|
||||
Qwen2_5_VLForConditionalGeneration,
|
||||
Qwen2Tokenizer,
|
||||
T5ForConditionalGeneration,
|
||||
T5Config,
|
||||
T5Tokenizer,
|
||||
)
|
||||
from transformers.models.t5.modeling_t5 import T5Stack
|
||||
from accelerate import init_empty_weights
|
||||
|
||||
from library.safetensors_utils import load_safetensors
|
||||
from library.utils import setup_logging
|
||||
|
||||
setup_logging()
|
||||
import logging
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
BYT5_TOKENIZER_PATH = "google/byt5-small"
|
||||
QWEN_2_5_VL_IMAGE_ID = "Qwen/Qwen2.5-VL-7B-Instruct"
|
||||
|
||||
|
||||
# Copy from Glyph-SDXL-V2
|
||||
|
||||
COLOR_IDX_JSON = """{"white": 0, "black": 1, "darkslategray": 2, "dimgray": 3, "darkolivegreen": 4, "midnightblue": 5, "saddlebrown": 6, "sienna": 7, "whitesmoke": 8, "darkslateblue": 9,
|
||||
"indianred": 10, "linen": 11, "maroon": 12, "khaki": 13, "sandybrown": 14, "gray": 15, "gainsboro": 16, "teal": 17, "peru": 18, "gold": 19,
|
||||
"snow": 20, "firebrick": 21, "crimson": 22, "chocolate": 23, "tomato": 24, "brown": 25, "goldenrod": 26, "antiquewhite": 27, "rosybrown": 28, "steelblue": 29,
|
||||
"floralwhite": 30, "seashell": 31, "darkgreen": 32, "oldlace": 33, "darkkhaki": 34, "burlywood": 35, "red": 36, "darkgray": 37, "orange": 38, "royalblue": 39,
|
||||
"seagreen": 40, "lightgray": 41, "tan": 42, "coral": 43, "beige": 44, "palevioletred": 45, "wheat": 46, "lavender": 47, "darkcyan": 48, "slateblue": 49,
|
||||
"slategray": 50, "orangered": 51, "silver": 52, "olivedrab": 53, "forestgreen": 54, "darkgoldenrod": 55, "ivory": 56, "darkorange": 57, "yellow": 58, "hotpink": 59,
|
||||
"ghostwhite": 60, "lightcoral": 61, "indigo": 62, "bisque": 63, "darkred": 64, "darksalmon": 65, "lightslategray": 66, "dodgerblue": 67, "lightpink": 68, "mistyrose": 69,
|
||||
"mediumvioletred": 70, "cadetblue": 71, "deeppink": 72, "salmon": 73, "palegoldenrod": 74, "blanchedalmond": 75, "lightseagreen": 76, "cornflowerblue": 77, "yellowgreen": 78, "greenyellow": 79,
|
||||
"navajowhite": 80, "papayawhip": 81, "mediumslateblue": 82, "purple": 83, "blueviolet": 84, "pink": 85, "cornsilk": 86, "lightsalmon": 87, "mediumpurple": 88, "moccasin": 89,
|
||||
"turquoise": 90, "mediumseagreen": 91, "lavenderblush": 92, "mediumblue": 93, "darkseagreen": 94, "mediumturquoise": 95, "paleturquoise": 96, "skyblue": 97, "lemonchiffon": 98, "olive": 99,
|
||||
"peachpuff": 100, "lightyellow": 101, "lightsteelblue": 102, "mediumorchid": 103, "plum": 104, "darkturquoise": 105, "aliceblue": 106, "mediumaquamarine": 107, "orchid": 108, "powderblue": 109,
|
||||
"blue": 110, "darkorchid": 111, "violet": 112, "lightskyblue": 113, "lightcyan": 114, "lightgoldenrodyellow": 115, "navy": 116, "thistle": 117, "honeydew": 118, "mintcream": 119,
|
||||
"lightblue": 120, "darkblue": 121, "darkmagenta": 122, "deepskyblue": 123, "magenta": 124, "limegreen": 125, "darkviolet": 126, "cyan": 127, "palegreen": 128, "aquamarine": 129,
|
||||
"lawngreen": 130, "lightgreen": 131, "azure": 132, "chartreuse": 133, "green": 134, "mediumspringgreen": 135, "lime": 136, "springgreen": 137}"""
|
||||
|
||||
MULTILINGUAL_10_LANG_IDX_JSON = """{"en-Montserrat-Regular": 0, "en-Poppins-Italic": 1, "en-GlacialIndifference-Regular": 2, "en-OpenSans-ExtraBoldItalic": 3, "en-Montserrat-Bold": 4, "en-Now-Regular": 5, "en-Garet-Regular": 6, "en-LeagueSpartan-Bold": 7, "en-DMSans-Regular": 8, "en-OpenSauceOne-Regular": 9,
|
||||
"en-OpenSans-ExtraBold": 10, "en-KGPrimaryPenmanship": 11, "en-Anton-Regular": 12, "en-Aileron-BlackItalic": 13, "en-Quicksand-Light": 14, "en-Roboto-BoldItalic": 15, "en-TheSeasons-It": 16, "en-Kollektif": 17, "en-Inter-BoldItalic": 18, "en-Poppins-Medium": 19,
|
||||
"en-Poppins-Light": 20, "en-RoxboroughCF-RegularItalic": 21, "en-PlayfairDisplay-SemiBold": 22, "en-Agrandir-Italic": 23, "en-Lato-Regular": 24, "en-MoreSugarRegular": 25, "en-CanvaSans-RegularItalic": 26, "en-PublicSans-Italic": 27, "en-CodePro-NormalLC": 28, "en-Belleza-Regular": 29,
|
||||
"en-JosefinSans-Bold": 30, "en-HKGrotesk-Bold": 31, "en-Telegraf-Medium": 32, "en-BrittanySignatureRegular": 33, "en-Raleway-ExtraBoldItalic": 34, "en-Mont-RegularItalic": 35, "en-Arimo-BoldItalic": 36, "en-Lora-Italic": 37, "en-ArchivoBlack-Regular": 38, "en-Poppins": 39,
|
||||
"en-Barlow-Black": 40, "en-CormorantGaramond-Bold": 41, "en-LibreBaskerville-Regular": 42, "en-CanvaSchoolFontRegular": 43, "en-BebasNeueBold": 44, "en-LazydogRegular": 45, "en-FredokaOne-Regular": 46, "en-Horizon-Bold": 47, "en-Nourd-Regular": 48, "en-Hatton-Regular": 49,
|
||||
"en-Nunito-ExtraBoldItalic": 50, "en-CerebriSans-Regular": 51, "en-Montserrat-Light": 52, "en-TenorSans": 53, "en-Norwester-Regular": 54, "en-ClearSans-Bold": 55, "en-Cardo-Regular": 56, "en-Alice-Regular": 57, "en-Oswald-Regular": 58, "en-Gaegu-Bold": 59,
|
||||
"en-Muli-Black": 60, "en-TAN-PEARL-Regular": 61, "en-CooperHewitt-Book": 62, "en-Agrandir-Grand": 63, "en-BlackMango-Thin": 64, "en-DMSerifDisplay-Regular": 65, "en-Antonio-Bold": 66, "en-Sniglet-Regular": 67, "en-BeVietnam-Regular": 68, "en-NunitoSans10pt-BlackItalic": 69,
|
||||
"en-AbhayaLibre-ExtraBold": 70, "en-Rubik-Regular": 71, "en-PPNeueMachina-Regular": 72, "en-TAN - MON CHERI-Regular": 73, "en-Jua-Regular": 74, "en-Playlist-Script": 75, "en-SourceSansPro-BoldItalic": 76, "en-MoonTime-Regular": 77, "en-Eczar-ExtraBold": 78, "en-Gatwick-Regular": 79,
|
||||
"en-MonumentExtended-Regular": 80, "en-BarlowSemiCondensed-Regular": 81, "en-BarlowCondensed-Regular": 82, "en-Alegreya-Regular": 83, "en-DreamAvenue": 84, "en-RobotoCondensed-Italic": 85, "en-BobbyJones-Regular": 86, "en-Garet-ExtraBold": 87, "en-YesevaOne-Regular": 88, "en-Dosis-ExtraBold": 89,
|
||||
"en-LeagueGothic-Regular": 90, "en-OpenSans-Italic": 91, "en-TANAEGEAN-Regular": 92, "en-Maharlika-Regular": 93, "en-MarykateRegular": 94, "en-Cinzel-Regular": 95, "en-Agrandir-Wide": 96, "en-Chewy-Regular": 97, "en-BodoniFLF-BoldItalic": 98, "en-Nunito-BlackItalic": 99,
|
||||
"en-LilitaOne": 100, "en-HandyCasualCondensed-Regular": 101, "en-Ovo": 102, "en-Livvic-Regular": 103, "en-Agrandir-Narrow": 104, "en-CrimsonPro-Italic": 105, "en-AnonymousPro-Bold": 106, "en-NF-OneLittleFont-Bold": 107, "en-RedHatDisplay-BoldItalic": 108, "en-CodecPro-Regular": 109,
|
||||
"en-HalimunRegular": 110, "en-LibreFranklin-Black": 111, "en-TeXGyreTermes-BoldItalic": 112, "en-Shrikhand-Regular": 113, "en-TTNormsPro-Italic": 114, "en-Gagalin-Regular": 115, "en-OpenSans-Bold": 116, "en-GreatVibes-Regular": 117, "en-Breathing": 118, "en-HeroLight-Regular": 119,
|
||||
"en-KGPrimaryDots": 120, "en-Quicksand-Bold": 121, "en-Brice-ExtraLightSemiExpanded": 122, "en-Lato-BoldItalic": 123, "en-Fraunces9pt-Italic": 124, "en-AbrilFatface-Regular": 125, "en-BerkshireSwash-Regular": 126, "en-Atma-Bold": 127, "en-HolidayRegular": 128, "en-BebasNeueCyrillic": 129,
|
||||
"en-IntroRust-Base": 130, "en-Gistesy": 131, "en-BDScript-Regular": 132, "en-ApricotsRegular": 133, "en-Prompt-Black": 134, "en-TAN MERINGUE": 135, "en-Sukar Regular": 136, "en-GentySans-Regular": 137, "en-NeueEinstellung-Normal": 138, "en-Garet-Bold": 139,
|
||||
"en-FiraSans-Black": 140, "en-BantayogLight": 141, "en-NotoSerifDisplay-Black": 142, "en-TTChocolates-Regular": 143, "en-Ubuntu-Regular": 144, "en-Assistant-Bold": 145, "en-ABeeZee-Regular": 146, "en-LexendDeca-Regular": 147, "en-KingredSerif": 148, "en-Radley-Regular": 149,
|
||||
"en-BrownSugar": 150, "en-MigraItalic-ExtraboldItalic": 151, "en-ChildosArabic-Regular": 152, "en-PeaceSans": 153, "en-LondrinaSolid-Black": 154, "en-SpaceMono-BoldItalic": 155, "en-RobotoMono-Light": 156, "en-CourierPrime-Regular": 157, "en-Alata-Regular": 158, "en-Amsterdam-One": 159,
|
||||
"en-IreneFlorentina-Regular": 160, "en-CatchyMager": 161, "en-Alta_regular": 162, "en-ArticulatCF-Regular": 163, "en-Raleway-Regular": 164, "en-BrasikaDisplay": 165, "en-TANAngleton-Italic": 166, "en-NotoSerifDisplay-ExtraCondensedItalic": 167, "en-Bryndan Write": 168, "en-TTCommonsPro-It": 169,
|
||||
"en-AlexBrush-Regular": 170, "en-Antic-Regular": 171, "en-TTHoves-Bold": 172, "en-DroidSerif": 173, "en-AblationRegular": 174, "en-Marcellus-Regular": 175, "en-Sanchez-Italic": 176, "en-JosefinSans": 177, "en-Afrah-Regular": 178, "en-PinyonScript": 179,
|
||||
"en-TTInterphases-BoldItalic": 180, "en-Yellowtail-Regular": 181, "en-Gliker-Regular": 182, "en-BobbyJonesSoft-Regular": 183, "en-IBMPlexSans": 184, "en-Amsterdam-Three": 185, "en-Amsterdam-FourSlant": 186, "en-TTFors-Regular": 187, "en-Quattrocento": 188, "en-Sifonn-Basic": 189,
|
||||
"en-AlegreyaSans-Black": 190, "en-Daydream": 191, "en-AristotelicaProTx-Rg": 192, "en-NotoSerif": 193, "en-EBGaramond-Italic": 194, "en-HammersmithOne-Regular": 195, "en-RobotoSlab-Regular": 196, "en-DO-Sans-Regular": 197, "en-KGPrimaryDotsLined": 198, "en-Blinker-Regular": 199,
|
||||
"en-TAN NIMBUS": 200, "en-Blueberry-Regular": 201, "en-Rosario-Regular": 202, "en-Forum": 203, "en-MistrullyRegular": 204, "en-SourceSerifPro-Regular": 205, "en-Bugaki-Regular": 206, "en-CMUSerif-Roman": 207, "en-GulfsDisplay-NormalItalic": 208, "en-PTSans-Bold": 209,
|
||||
"en-Sensei-Medium": 210, "en-SquadaOne-Regular": 211, "en-Arapey-Italic": 212, "en-Parisienne-Regular": 213, "en-Aleo-Italic": 214, "en-QuicheDisplay-Italic": 215, "en-RocaOne-It": 216, "en-Funtastic-Regular": 217, "en-PTSerif-BoldItalic": 218, "en-Muller-RegularItalic": 219,
|
||||
"en-ArgentCF-Regular": 220, "en-Brightwall-Italic": 221, "en-Knewave-Regular": 222, "en-TYSerif-D": 223, "en-Agrandir-Tight": 224, "en-AlfaSlabOne-Regular": 225, "en-TANTangkiwood-Display": 226, "en-Kief-Montaser-Regular": 227, "en-Gotham-Book": 228, "en-JuliusSansOne-Regular": 229,
|
||||
"en-CocoGothic-Italic": 230, "en-SairaCondensed-Regular": 231, "en-DellaRespira-Regular": 232, "en-Questrial-Regular": 233, "en-BukhariScript-Regular": 234, "en-HelveticaWorld-Bold": 235, "en-TANKINDRED-Display": 236, "en-CinzelDecorative-Regular": 237, "en-Vidaloka-Regular": 238, "en-AlegreyaSansSC-Black": 239,
|
||||
"en-FeelingPassionate-Regular": 240, "en-QuincyCF-Regular": 241, "en-FiraCode-Regular": 242, "en-Genty-Regular": 243, "en-Nickainley-Normal": 244, "en-RubikOne-Regular": 245, "en-Gidole-Regular": 246, "en-Borsok": 247, "en-Gordita-RegularItalic": 248, "en-Scripter-Regular": 249,
|
||||
"en-Buffalo-Regular": 250, "en-KleinText-Regular": 251, "en-Creepster-Regular": 252, "en-Arvo-Bold": 253, "en-GabrielSans-NormalItalic": 254, "en-Heebo-Black": 255, "en-LexendExa-Regular": 256, "en-BrixtonSansTC-Regular": 257, "en-GildaDisplay-Regular": 258, "en-ChunkFive-Roman": 259,
|
||||
"en-Amaranth-BoldItalic": 260, "en-BubbleboddyNeue-Regular": 261, "en-MavenPro-Bold": 262, "en-TTDrugs-Italic": 263, "en-CyGrotesk-KeyRegular": 264, "en-VarelaRound-Regular": 265, "en-Ruda-Black": 266, "en-SafiraMarch": 267, "en-BloggerSans": 268, "en-TANHEADLINE-Regular": 269,
|
||||
"en-SloopScriptPro-Regular": 270, "en-NeueMontreal-Regular": 271, "en-Schoolbell-Regular": 272, "en-SigherRegular": 273, "en-InriaSerif-Regular": 274, "en-JetBrainsMono-Regular": 275, "en-MADEEvolveSans": 276, "en-Dekko": 277, "en-Handyman-Regular": 278, "en-Aileron-BoldItalic": 279,
|
||||
"en-Bright-Italic": 280, "en-Solway-Regular": 281, "en-Higuen-Regular": 282, "en-WedgesItalic": 283, "en-TANASHFORD-BOLD": 284, "en-IBMPlexMono": 285, "en-RacingSansOne-Regular": 286, "en-RegularBrush": 287, "en-OpenSans-LightItalic": 288, "en-SpecialElite-Regular": 289,
|
||||
"en-FuturaLTPro-Medium": 290, "en-MaragsaDisplay": 291, "en-BigShouldersDisplay-Regular": 292, "en-BDSans-Regular": 293, "en-RasputinRegular": 294, "en-Yvesyvesdrawing-BoldItalic": 295, "en-Bitter-Regular": 296, "en-LuckiestGuy-Regular": 297, "en-CanvaSchoolFontDotted": 298, "en-TTFirsNeue-Italic": 299,
|
||||
"en-Sunday-Regular": 300, "en-HKGothic-MediumItalic": 301, "en-CaveatBrush-Regular": 302, "en-HeliosExt": 303, "en-ArchitectsDaughter-Regular": 304, "en-Angelina": 305, "en-Calistoga-Regular": 306, "en-ArchivoNarrow-Regular": 307, "en-ObjectSans-MediumSlanted": 308, "en-AyrLucidityCondensed-Regular": 309,
|
||||
"en-Nexa-RegularItalic": 310, "en-Lustria-Regular": 311, "en-Amsterdam-TwoSlant": 312, "en-Virtual-Regular": 313, "en-Brusher-Regular": 314, "en-NF-Lepetitcochon-Regular": 315, "en-TANTWINKLE": 316, "en-LeJour-Serif": 317, "en-Prata-Regular": 318, "en-PPWoodland-Regular": 319,
|
||||
"en-PlayfairDisplay-BoldItalic": 320, "en-AmaticSC-Regular": 321, "en-Cabin-Regular": 322, "en-Manjari-Bold": 323, "en-MrDafoe-Regular": 324, "en-TTRamillas-Italic": 325, "en-Luckybones-Bold": 326, "en-DarkerGrotesque-Light": 327, "en-BellabooRegular": 328, "en-CormorantSC-Bold": 329,
|
||||
"en-GochiHand-Regular": 330, "en-Atteron": 331, "en-RocaTwo-Lt": 332, "en-ZCOOLXiaoWei-Regular": 333, "en-TANSONGBIRD": 334, "en-HeadingNow-74Regular": 335, "en-Luthier-BoldItalic": 336, "en-Oregano-Regular": 337, "en-AyrTropikaIsland-Int": 338, "en-Mali-Regular": 339,
|
||||
"en-DidactGothic-Regular": 340, "en-Lovelace-Regular": 341, "en-BakerieSmooth-Regular": 342, "en-CarterOne": 343, "en-HussarBd": 344, "en-OldStandard-Italic": 345, "en-TAN-ASTORIA-Display": 346, "en-rugratssans-Regular": 347, "en-BMHANNA": 348, "en-BetterSaturday": 349,
|
||||
"en-AdigianaToybox": 350, "en-Sailors": 351, "en-PlayfairDisplaySC-Italic": 352, "en-Etna-Regular": 353, "en-Revive80Signature": 354, "en-CAGenerated": 355, "en-Poppins-Regular": 356, "en-Jonathan-Regular": 357, "en-Pacifico-Regular": 358, "en-Saira-Black": 359,
|
||||
"en-Loubag-Regular": 360, "en-Decalotype-Black": 361, "en-Mansalva-Regular": 362, "en-Allura-Regular": 363, "en-ProximaNova-Bold": 364, "en-TANMIGNON-DISPLAY": 365, "en-ArsenicaAntiqua-Regular": 366, "en-BreulGroteskA-RegularItalic": 367, "en-HKModular-Bold": 368, "en-TANNightingale-Regular": 369,
|
||||
"en-AristotelicaProCndTxt-Rg": 370, "en-Aprila-Regular": 371, "en-Tomorrow-Regular": 372, "en-AngellaWhite": 373, "en-KaushanScript-Regular": 374, "en-NotoSans": 375, "en-LeJour-Script": 376, "en-BrixtonTC-Regular": 377, "en-OleoScript-Regular": 378, "en-Cakerolli-Regular": 379,
|
||||
"en-Lobster-Regular": 380, "en-FrunchySerif-Regular": 381, "en-PorcelainRegular": 382, "en-AlojaExtended": 383, "en-SergioTrendy-Italic": 384, "en-LovelaceText-Bold": 385, "en-Anaktoria": 386, "en-JimmyScript-Light": 387, "en-IBMPlexSerif": 388, "en-Marta": 389,
|
||||
"en-Mango-Regular": 390, "en-Overpass-Italic": 391, "en-Hagrid-Regular": 392, "en-ElikaGorica": 393, "en-Amiko-Regular": 394, "en-EFCOBrookshire-Regular": 395, "en-Caladea-Regular": 396, "en-MoonlightBold": 397, "en-Staatliches-Regular": 398, "en-Helios-Bold": 399,
|
||||
"en-Satisfy-Regular": 400, "en-NexaScript-Regular": 401, "en-Trocchi-Regular": 402, "en-March": 403, "en-IbarraRealNova-Regular": 404, "en-Nectarine-Regular": 405, "en-Overpass-Light": 406, "en-TruetypewriterPolyglOTT": 407, "en-Bangers-Regular": 408, "en-Lazord-BoldExpandedItalic": 409,
|
||||
"en-Chloe-Regular": 410, "en-BaskervilleDisplayPT-Regular": 411, "en-Bright-Regular": 412, "en-Vollkorn-Regular": 413, "en-Harmattan": 414, "en-SortsMillGoudy-Regular": 415, "en-Biryani-Bold": 416, "en-SugoProDisplay-Italic": 417, "en-Lazord-BoldItalic": 418, "en-Alike-Regular": 419,
|
||||
"en-PermanentMarker-Regular": 420, "en-Sacramento-Regular": 421, "en-HKGroteskPro-Italic": 422, "en-Aleo-BoldItalic": 423, "en-Noot": 424, "en-TANGARLAND-Regular": 425, "en-Twister": 426, "en-Arsenal-Italic": 427, "en-Bogart-Italic": 428, "en-BethEllen-Regular": 429,
|
||||
"en-Caveat-Regular": 430, "en-BalsamiqSans-Bold": 431, "en-BreeSerif-Regular": 432, "en-CodecPro-ExtraBold": 433, "en-Pierson-Light": 434, "en-CyGrotesk-WideRegular": 435, "en-Lumios-Marker": 436, "en-Comfortaa-Bold": 437, "en-TraceFontRegular": 438, "en-RTL-AdamScript-Regular": 439,
|
||||
"en-EastmanGrotesque-Italic": 440, "en-Kalam-Bold": 441, "en-ChauPhilomeneOne-Regular": 442, "en-Coiny-Regular": 443, "en-Lovera": 444, "en-Gellatio": 445, "en-TitilliumWeb-Bold": 446, "en-OilvareBase-Italic": 447, "en-Catamaran-Black": 448, "en-Anteb-Italic": 449,
|
||||
"en-SueEllenFrancisco": 450, "en-SweetApricot": 451, "en-BrightSunshine": 452, "en-IM_FELL_Double_Pica_Italic": 453, "en-Granaina-limpia": 454, "en-TANPARFAIT": 455, "en-AcherusGrotesque-Regular": 456, "en-AwesomeLathusca-Italic": 457, "en-Signika-Bold": 458, "en-Andasia": 459,
|
||||
"en-DO-AllCaps-Slanted": 460, "en-Zenaida-Regular": 461, "en-Fahkwang-Regular": 462, "en-Play-Regular": 463, "en-BERNIERRegular-Regular": 464, "en-PlumaThin-Regular": 465, "en-SportsWorld": 466, "en-Garet-Black": 467, "en-CarolloPlayscript-BlackItalic": 468, "en-Cheque-Regular": 469,
|
||||
"en-SEGO": 470, "en-BobbyJones-Condensed": 471, "en-NexaSlab-RegularItalic": 472, "en-DancingScript-Regular": 473, "en-PaalalabasDisplayWideBETA": 474, "en-Magnolia-Script": 475, "en-OpunMai-400It": 476, "en-MadelynFill-Regular": 477, "en-ZingRust-Base": 478, "en-FingerPaint-Regular": 479,
|
||||
"en-BostonAngel-Light": 480, "en-Gliker-RegularExpanded": 481, "en-Ahsing": 482, "en-Engagement-Regular": 483, "en-EyesomeScript": 484, "en-LibraSerifModern-Regular": 485, "en-London-Regular": 486, "en-AtkinsonHyperlegible-Regular": 487, "en-StadioNow-TextItalic": 488, "en-Aniyah": 489,
|
||||
"en-ITCAvantGardePro-Bold": 490, "en-Comica-Regular": 491, "en-Coustard-Regular": 492, "en-Brice-BoldCondensed": 493, "en-TANNEWYORK-Bold": 494, "en-TANBUSTER-Bold": 495, "en-Alatsi-Regular": 496, "en-TYSerif-Book": 497, "en-Jingleberry": 498, "en-Rajdhani-Bold": 499,
|
||||
"en-LobsterTwo-BoldItalic": 500, "en-BestLight-Medium": 501, "en-Hitchcut-Regular": 502, "en-GermaniaOne-Regular": 503, "en-Emitha-Script": 504, "en-LemonTuesday": 505, "en-Cubao_Free_Regular": 506, "en-MonterchiSerif-Regular": 507, "en-AllertaStencil-Regular": 508, "en-RTL-Sondos-Regular": 509,
|
||||
"en-HomemadeApple-Regular": 510, "en-CosmicOcto-Medium": 511, "cn-HelloFont-FangHuaTi": 0, "cn-HelloFont-ID-DianFangSong-Bold": 1, "cn-HelloFont-ID-DianFangSong": 2, "cn-HelloFont-ID-DianHei-CEJ": 3, "cn-HelloFont-ID-DianHei-DEJ": 4, "cn-HelloFont-ID-DianHei-EEJ": 5, "cn-HelloFont-ID-DianHei-FEJ": 6, "cn-HelloFont-ID-DianHei-GEJ": 7, "cn-HelloFont-ID-DianKai-Bold": 8, "cn-HelloFont-ID-DianKai": 9,
|
||||
"cn-HelloFont-WenYiHei": 10, "cn-Hellofont-ID-ChenYanXingKai": 11, "cn-Hellofont-ID-DaZiBao": 12, "cn-Hellofont-ID-DaoCaoRen": 13, "cn-Hellofont-ID-JianSong": 14, "cn-Hellofont-ID-JiangHuZhaoPaiHei": 15, "cn-Hellofont-ID-KeSong": 16, "cn-Hellofont-ID-LeYuanTi": 17, "cn-Hellofont-ID-Pinocchio": 18, "cn-Hellofont-ID-QiMiaoTi": 19,
|
||||
"cn-Hellofont-ID-QingHuaKai": 20, "cn-Hellofont-ID-QingHuaXingKai": 21, "cn-Hellofont-ID-ShanShuiXingKai": 22, "cn-Hellofont-ID-ShouXieQiShu": 23, "cn-Hellofont-ID-ShouXieTongZhenTi": 24, "cn-Hellofont-ID-TengLingTi": 25, "cn-Hellofont-ID-XiaoLiShu": 26, "cn-Hellofont-ID-XuanZhenSong": 27, "cn-Hellofont-ID-ZhongLingXingKai": 28, "cn-HellofontIDJiaoTangTi": 29,
|
||||
"cn-HellofontIDJiuZhuTi": 30, "cn-HuXiaoBao-SaoBao": 31, "cn-HuXiaoBo-NanShen": 32, "cn-HuXiaoBo-ZhenShuai": 33, "cn-SourceHanSansSC-Bold": 34, "cn-SourceHanSansSC-ExtraLight": 35, "cn-SourceHanSansSC-Heavy": 36, "cn-SourceHanSansSC-Light": 37, "cn-SourceHanSansSC-Medium": 38, "cn-SourceHanSansSC-Normal": 39,
|
||||
"cn-SourceHanSansSC-Regular": 40, "cn-SourceHanSerifSC-Bold": 41, "cn-SourceHanSerifSC-ExtraLight": 42, "cn-SourceHanSerifSC-Heavy": 43, "cn-SourceHanSerifSC-Light": 44, "cn-SourceHanSerifSC-Medium": 45, "cn-SourceHanSerifSC-Regular": 46, "cn-SourceHanSerifSC-SemiBold": 47, "cn-xiaowei": 48, "cn-AaJianHaoTi": 49,
|
||||
"cn-AlibabaPuHuiTi-Bold": 50, "cn-AlibabaPuHuiTi-Heavy": 51, "cn-AlibabaPuHuiTi-Light": 52, "cn-AlibabaPuHuiTi-Medium": 53, "cn-AlibabaPuHuiTi-Regular": 54, "cn-CanvaAcidBoldSC": 55, "cn-CanvaBreezeCN": 56, "cn-CanvaBumperCropSC": 57, "cn-CanvaCakeShopCN": 58, "cn-CanvaEndeavorBlackSC": 59,
|
||||
"cn-CanvaJoyHeiCN": 60, "cn-CanvaLiCN": 61, "cn-CanvaOrientalBrushCN": 62, "cn-CanvaPoster": 63, "cn-CanvaQinfuCalligraphyCN": 64, "cn-CanvaSweetHeartCN": 65, "cn-CanvaSwordLikeDreamCN": 66, "cn-CanvaTangyuanHandwritingCN": 67, "cn-CanvaWanderWorldCN": 68, "cn-CanvaWenCN": 69,
|
||||
"cn-DianZiChunYi": 70, "cn-GenSekiGothicTW-H": 71, "cn-GenWanMinTW-L": 72, "cn-GenYoMinTW-B": 73, "cn-GenYoMinTW-EL": 74, "cn-GenYoMinTW-H": 75, "cn-GenYoMinTW-M": 76, "cn-GenYoMinTW-R": 77, "cn-GenYoMinTW-SB": 78, "cn-HYQiHei-AZEJ": 79,
|
||||
"cn-HYQiHei-EES": 80, "cn-HanaMinA": 81, "cn-HappyZcool-2016": 82, "cn-HelloFont ZJ KeKouKeAiTi": 83, "cn-HelloFont-ID-BoBoTi": 84, "cn-HelloFont-ID-FuGuHei-25": 85, "cn-HelloFont-ID-FuGuHei-35": 86, "cn-HelloFont-ID-FuGuHei-45": 87, "cn-HelloFont-ID-FuGuHei-55": 88, "cn-HelloFont-ID-FuGuHei-65": 89,
|
||||
"cn-HelloFont-ID-FuGuHei-75": 90, "cn-HelloFont-ID-FuGuHei-85": 91, "cn-HelloFont-ID-HeiKa": 92, "cn-HelloFont-ID-HeiTang": 93, "cn-HelloFont-ID-JianSong-95": 94, "cn-HelloFont-ID-JueJiangHei-50": 95, "cn-HelloFont-ID-JueJiangHei-55": 96, "cn-HelloFont-ID-JueJiangHei-60": 97, "cn-HelloFont-ID-JueJiangHei-65": 98, "cn-HelloFont-ID-JueJiangHei-70": 99,
|
||||
"cn-HelloFont-ID-JueJiangHei-75": 100, "cn-HelloFont-ID-JueJiangHei-80": 101, "cn-HelloFont-ID-KuHeiTi": 102, "cn-HelloFont-ID-LingDongTi": 103, "cn-HelloFont-ID-LingLiTi": 104, "cn-HelloFont-ID-MuFengTi": 105, "cn-HelloFont-ID-NaiNaiJiangTi": 106, "cn-HelloFont-ID-PangDu": 107, "cn-HelloFont-ID-ReLieTi": 108, "cn-HelloFont-ID-RouRun": 109,
|
||||
"cn-HelloFont-ID-SaShuangShouXieTi": 110, "cn-HelloFont-ID-WangZheFengFan": 111, "cn-HelloFont-ID-YouQiTi": 112, "cn-Hellofont-ID-XiaLeTi": 113, "cn-Hellofont-ID-XianXiaTi": 114, "cn-HuXiaoBoKuHei": 115, "cn-IDDanMoXingKai": 116, "cn-IDJueJiangHei": 117, "cn-IDMeiLingTi": 118, "cn-IDQQSugar": 119,
|
||||
"cn-LiuJianMaoCao-Regular": 120, "cn-LongCang-Regular": 121, "cn-MaShanZheng-Regular": 122, "cn-PangMenZhengDao-3": 123, "cn-PangMenZhengDao-Cu": 124, "cn-PangMenZhengDao": 125, "cn-SentyCaramel": 126, "cn-SourceHanSerifSC": 127, "cn-WenCang-Regular": 128, "cn-WenQuanYiMicroHei": 129,
|
||||
"cn-XianErTi": 130, "cn-YRDZSTJF": 131, "cn-YS-HelloFont-BangBangTi": 132, "cn-ZCOOLKuaiLe-Regular": 133, "cn-ZCOOLQingKeHuangYou-Regular": 134, "cn-ZCOOLXiaoWei-Regular": 135, "cn-ZCOOL_KuHei": 136, "cn-ZhiMangXing-Regular": 137, "cn-baotuxiaobaiti": 138, "cn-jiangxizhuokai-Regular": 139,
|
||||
"cn-zcool-gdh": 140, "cn-zcoolqingkehuangyouti-Regular": 141, "cn-zcoolwenyiti": 142, "jp-04KanjyukuGothic": 0, "jp-07LightNovelPOP": 1, "jp-07NikumaruFont": 2, "jp-07YasashisaAntique": 3, "jp-07YasashisaGothic": 4, "jp-BokutachinoGothic2Bold": 5, "jp-BokutachinoGothic2Regular": 6, "jp-CHI_SpeedyRight_full_211128-Regular": 7, "jp-CHI_SpeedyRight_italic_full_211127-Regular": 8, "jp-CP-Font": 9,
|
||||
"jp-Canva_CezanneProN-B": 10, "jp-Canva_CezanneProN-M": 11, "jp-Canva_ChiaroStd-B": 12, "jp-Canva_CometStd-B": 13, "jp-Canva_DotMincho16Std-M": 14, "jp-Canva_GrecoStd-B": 15, "jp-Canva_GrecoStd-M": 16, "jp-Canva_LyraStd-DB": 17, "jp-Canva_MatisseHatsuhiPro-B": 18, "jp-Canva_MatisseHatsuhiPro-M": 19,
|
||||
"jp-Canva_ModeMinAStd-B": 20, "jp-Canva_NewCezanneProN-B": 21, "jp-Canva_NewCezanneProN-M": 22, "jp-Canva_PearlStd-L": 23, "jp-Canva_RaglanStd-UB": 24, "jp-Canva_RailwayStd-B": 25, "jp-Canva_ReggaeStd-B": 26, "jp-Canva_RocknRollStd-DB": 27, "jp-Canva_RodinCattleyaPro-B": 28, "jp-Canva_RodinCattleyaPro-M": 29,
|
||||
"jp-Canva_RodinCattleyaPro-UB": 30, "jp-Canva_RodinHimawariPro-B": 31, "jp-Canva_RodinHimawariPro-M": 32, "jp-Canva_RodinMariaPro-B": 33, "jp-Canva_RodinMariaPro-DB": 34, "jp-Canva_RodinProN-M": 35, "jp-Canva_ShadowTLStd-B": 36, "jp-Canva_StickStd-B": 37, "jp-Canva_TsukuAOldMinPr6N-B": 38, "jp-Canva_TsukuAOldMinPr6N-R": 39,
|
||||
"jp-Canva_UtrilloPro-DB": 40, "jp-Canva_UtrilloPro-M": 41, "jp-Canva_YurukaStd-UB": 42, "jp-FGUIGEN": 43, "jp-GlowSansJ-Condensed-Heavy": 44, "jp-GlowSansJ-Condensed-Light": 45, "jp-GlowSansJ-Normal-Bold": 46, "jp-GlowSansJ-Normal-Light": 47, "jp-HannariMincho": 48, "jp-HarenosoraMincho": 49,
|
||||
"jp-Jiyucho": 50, "jp-Kaiso-Makina-B": 51, "jp-Kaisotai-Next-UP-B": 52, "jp-KokoroMinchoutai": 53, "jp-Mamelon-3-Hi-Regular": 54, "jp-MotoyaAnemoneStd-W1": 55, "jp-MotoyaAnemoneStd-W5": 56, "jp-MotoyaAnticPro-W3": 57, "jp-MotoyaCedarStd-W3": 58, "jp-MotoyaCedarStd-W5": 59,
|
||||
"jp-MotoyaGochikaStd-W4": 60, "jp-MotoyaGochikaStd-W8": 61, "jp-MotoyaGothicMiyabiStd-W6": 62, "jp-MotoyaGothicStd-W3": 63, "jp-MotoyaGothicStd-W5": 64, "jp-MotoyaKoinStd-W3": 65, "jp-MotoyaKyotaiStd-W2": 66, "jp-MotoyaKyotaiStd-W4": 67, "jp-MotoyaMaruStd-W3": 68, "jp-MotoyaMaruStd-W5": 69,
|
||||
"jp-MotoyaMinchoMiyabiStd-W4": 70, "jp-MotoyaMinchoMiyabiStd-W6": 71, "jp-MotoyaMinchoModernStd-W4": 72, "jp-MotoyaMinchoModernStd-W6": 73, "jp-MotoyaMinchoStd-W3": 74, "jp-MotoyaMinchoStd-W5": 75, "jp-MotoyaReisyoStd-W2": 76, "jp-MotoyaReisyoStd-W6": 77, "jp-MotoyaTohitsuStd-W4": 78, "jp-MotoyaTohitsuStd-W6": 79,
|
||||
"jp-MtySousyokuEmBcJis-W6": 80, "jp-MtySousyokuLiBcJis-W6": 81, "jp-Mushin": 82, "jp-NotoSansJP-Bold": 83, "jp-NotoSansJP-Regular": 84, "jp-NudMotoyaAporoStd-W3": 85, "jp-NudMotoyaAporoStd-W5": 86, "jp-NudMotoyaCedarStd-W3": 87, "jp-NudMotoyaCedarStd-W5": 88, "jp-NudMotoyaMaruStd-W3": 89,
|
||||
"jp-NudMotoyaMaruStd-W5": 90, "jp-NudMotoyaMinchoStd-W5": 91, "jp-Ounen-mouhitsu": 92, "jp-Ronde-B-Square": 93, "jp-SMotoyaGyosyoStd-W5": 94, "jp-SMotoyaSinkaiStd-W3": 95, "jp-SMotoyaSinkaiStd-W5": 96, "jp-SourceHanSansJP-Bold": 97, "jp-SourceHanSansJP-Regular": 98, "jp-SourceHanSerifJP-Bold": 99,
|
||||
"jp-SourceHanSerifJP-Regular": 100, "jp-TazuganeGothicStdN-Bold": 101, "jp-TazuganeGothicStdN-Regular": 102, "jp-TelopMinProN-B": 103, "jp-Togalite-Bold": 104, "jp-Togalite-Regular": 105, "jp-TsukuMinPr6N-E": 106, "jp-TsukuMinPr6N-M": 107, "jp-mikachan_o": 108, "jp-nagayama_kai": 109,
|
||||
"jp-07LogoTypeGothic7": 110, "jp-07TetsubinGothic": 111, "jp-851CHIKARA-DZUYOKU-KANA-A": 112, "jp-ARMinchoJIS-Light": 113, "jp-ARMinchoJIS-Ultra": 114, "jp-ARPCrystalMinchoJIS-Medium": 115, "jp-ARPCrystalRGothicJIS-Medium": 116, "jp-ARShounanShinpitsuGyosyoJIS-Medium": 117, "jp-AozoraMincho-bold": 118, "jp-AozoraMinchoRegular": 119,
|
||||
"jp-ArialUnicodeMS-Bold": 120, "jp-ArialUnicodeMS": 121, "jp-CanvaBreezeJP": 122, "jp-CanvaLiCN": 123, "jp-CanvaLiJP": 124, "jp-CanvaOrientalBrushCN": 125, "jp-CanvaQinfuCalligraphyJP": 126, "jp-CanvaSweetHeartJP": 127, "jp-CanvaWenJP": 128, "jp-Corporate-Logo-Bold": 129,
|
||||
"jp-DelaGothicOne-Regular": 130, "jp-GN-Kin-iro_SansSerif": 131, "jp-GN-Koharuiro_Sunray": 132, "jp-GenEiGothicM-B": 133, "jp-GenEiGothicM-R": 134, "jp-GenJyuuGothic-Bold": 135, "jp-GenRyuMinTW-B": 136, "jp-GenRyuMinTW-R": 137, "jp-GenSekiGothicTW-B": 138, "jp-GenSekiGothicTW-R": 139,
|
||||
"jp-GenSenRoundedTW-B": 140, "jp-GenSenRoundedTW-R": 141, "jp-GenShinGothic-Bold": 142, "jp-GenShinGothic-Normal": 143, "jp-GenWanMinTW-L": 144, "jp-GenYoGothicTW-B": 145, "jp-GenYoGothicTW-R": 146, "jp-GenYoMinTW-B": 147, "jp-GenYoMinTW-R": 148, "jp-HGBouquet": 149,
|
||||
"jp-HanaMinA": 150, "jp-HanazomeFont": 151, "jp-HinaMincho-Regular": 152, "jp-Honoka-Antique-Maru": 153, "jp-Honoka-Mincho": 154, "jp-HuiFontP": 155, "jp-IPAexMincho": 156, "jp-JK-Gothic-L": 157, "jp-JK-Gothic-M": 158, "jp-JackeyFont": 159,
|
||||
"jp-KaiseiTokumin-Bold": 160, "jp-KaiseiTokumin-Regular": 161, "jp-Keifont": 162, "jp-KiwiMaru-Regular": 163, "jp-Koku-Mincho-Regular": 164, "jp-MotoyaLMaru-W3-90ms-RKSJ-H": 165, "jp-NewTegomin-Regular": 166, "jp-NicoKaku": 167, "jp-NicoMoji+": 168, "jp-Otsutome_font-Bold": 169,
|
||||
"jp-PottaOne-Regular": 170, "jp-RampartOne-Regular": 171, "jp-Senobi-Gothic-Bold": 172, "jp-Senobi-Gothic-Regular": 173, "jp-SmartFontUI-Proportional": 174, "jp-SoukouMincho": 175, "jp-TEST_Klee-DB": 176, "jp-TEST_Klee-M": 177, "jp-TEST_UDMincho-B": 178, "jp-TEST_UDMincho-L": 179,
|
||||
"jp-TT_Akakane-EB": 180, "jp-Tanuki-Permanent-Marker": 181, "jp-TrainOne-Regular": 182, "jp-TsunagiGothic-Black": 183, "jp-Ume-Hy-Gothic": 184, "jp-Ume-P-Mincho": 185, "jp-WenQuanYiMicroHei": 186, "jp-XANO-mincho-U32": 187, "jp-YOzFontM90-Regular": 188, "jp-Yomogi-Regular": 189,
|
||||
"jp-YujiBoku-Regular": 190, "jp-YujiSyuku-Regular": 191, "jp-ZenKakuGothicNew-Bold": 192, "jp-ZenKakuGothicNew-Regular": 193, "jp-ZenKurenaido-Regular": 194, "jp-ZenMaruGothic-Bold": 195, "jp-ZenMaruGothic-Regular": 196, "jp-darts-font": 197, "jp-irohakakuC-Bold": 198, "jp-irohakakuC-Medium": 199,
|
||||
"jp-irohakakuC-Regular": 200, "jp-katyou": 201, "jp-mplus-1m-bold": 202, "jp-mplus-1m-regular": 203, "jp-mplus-1p-bold": 204, "jp-mplus-1p-regular": 205, "jp-rounded-mplus-1p-bold": 206, "jp-rounded-mplus-1p-regular": 207, "jp-timemachine-wa": 208, "jp-ttf-GenEiLateMin-Medium": 209,
|
||||
"jp-uzura_font": 210, "kr-Arita-buri-Bold_OTF": 0, "kr-Arita-buri-HairLine_OTF": 1, "kr-Arita-buri-Light_OTF": 2, "kr-Arita-buri-Medium_OTF": 3, "kr-Arita-buri-SemiBold_OTF": 4, "kr-Canva_YDSunshineL": 5, "kr-Canva_YDSunshineM": 6, "kr-Canva_YoonGulimPro710": 7, "kr-Canva_YoonGulimPro730": 8, "kr-Canva_YoonGulimPro740": 9,
|
||||
"kr-Canva_YoonGulimPro760": 10, "kr-Canva_YoonGulimPro770": 11, "kr-Canva_YoonGulimPro790": 12, "kr-CreHappB": 13, "kr-CreHappL": 14, "kr-CreHappM": 15, "kr-CreHappS": 16, "kr-OTAuroraB": 17, "kr-OTAuroraL": 18, "kr-OTAuroraR": 19,
|
||||
"kr-OTDoldamgilB": 20, "kr-OTDoldamgilL": 21, "kr-OTDoldamgilR": 22, "kr-OTHamsterB": 23, "kr-OTHamsterL": 24, "kr-OTHamsterR": 25, "kr-OTHapchangdanB": 26, "kr-OTHapchangdanL": 27, "kr-OTHapchangdanR": 28, "kr-OTSupersizeBkBOX": 29,
|
||||
"kr-SourceHanSansKR-Bold": 30, "kr-SourceHanSansKR-ExtraLight": 31, "kr-SourceHanSansKR-Heavy": 32, "kr-SourceHanSansKR-Light": 33, "kr-SourceHanSansKR-Medium": 34, "kr-SourceHanSansKR-Normal": 35, "kr-SourceHanSansKR-Regular": 36, "kr-SourceHanSansSC-Bold": 37, "kr-SourceHanSansSC-ExtraLight": 38, "kr-SourceHanSansSC-Heavy": 39,
|
||||
"kr-SourceHanSansSC-Light": 40, "kr-SourceHanSansSC-Medium": 41, "kr-SourceHanSansSC-Normal": 42, "kr-SourceHanSansSC-Regular": 43, "kr-SourceHanSerifSC-Bold": 44, "kr-SourceHanSerifSC-SemiBold": 45, "kr-TDTDBubbleBubbleOTF": 46, "kr-TDTDConfusionOTF": 47, "kr-TDTDCuteAndCuteOTF": 48, "kr-TDTDEggTakOTF": 49,
|
||||
"kr-TDTDEmotionalLetterOTF": 50, "kr-TDTDGalapagosOTF": 51, "kr-TDTDHappyHourOTF": 52, "kr-TDTDLatteOTF": 53, "kr-TDTDMoonLightOTF": 54, "kr-TDTDParkForestOTF": 55, "kr-TDTDPencilOTF": 56, "kr-TDTDSmileOTF": 57, "kr-TDTDSproutOTF": 58, "kr-TDTDSunshineOTF": 59,
|
||||
"kr-TDTDWaferOTF": 60, "kr-777Chyaochyureu": 61, "kr-ArialUnicodeMS-Bold": 62, "kr-ArialUnicodeMS": 63, "kr-BMHANNA": 64, "kr-Baekmuk-Dotum": 65, "kr-BagelFatOne-Regular": 66, "kr-CoreBandi": 67, "kr-CoreBandiFace": 68, "kr-CoreBori": 69,
|
||||
"kr-DoHyeon-Regular": 70, "kr-Dokdo-Regular": 71, "kr-Gaegu-Bold": 72, "kr-Gaegu-Light": 73, "kr-Gaegu-Regular": 74, "kr-GamjaFlower-Regular": 75, "kr-GasoekOne-Regular": 76, "kr-GothicA1-Black": 77, "kr-GothicA1-Bold": 78, "kr-GothicA1-ExtraBold": 79,
|
||||
"kr-GothicA1-ExtraLight": 80, "kr-GothicA1-Light": 81, "kr-GothicA1-Medium": 82, "kr-GothicA1-Regular": 83, "kr-GothicA1-SemiBold": 84, "kr-GothicA1-Thin": 85, "kr-Gugi-Regular": 86, "kr-HiMelody-Regular": 87, "kr-Jua-Regular": 88, "kr-KirangHaerang-Regular": 89,
|
||||
"kr-NanumBrush": 90, "kr-NanumPen": 91, "kr-NanumSquareRoundB": 92, "kr-NanumSquareRoundEB": 93, "kr-NanumSquareRoundL": 94, "kr-NanumSquareRoundR": 95, "kr-SeH-CB": 96, "kr-SeH-CBL": 97, "kr-SeH-CEB": 98, "kr-SeH-CL": 99,
|
||||
"kr-SeH-CM": 100, "kr-SeN-CB": 101, "kr-SeN-CBL": 102, "kr-SeN-CEB": 103, "kr-SeN-CL": 104, "kr-SeN-CM": 105, "kr-Sunflower-Bold": 106, "kr-Sunflower-Light": 107, "kr-Sunflower-Medium": 108, "kr-TTClaytoyR": 109,
|
||||
"kr-TTDalpangiR": 110, "kr-TTMamablockR": 111, "kr-TTNauidongmuR": 112, "kr-TTOktapbangR": 113, "kr-UhBeeMiMi": 114, "kr-UhBeeMiMiBold": 115, "kr-UhBeeSe_hyun": 116, "kr-UhBeeSe_hyunBold": 117, "kr-UhBeenamsoyoung": 118, "kr-UhBeenamsoyoungBold": 119,
|
||||
"kr-WenQuanYiMicroHei": 120, "kr-YeonSung-Regular": 121}"""
|
||||
|
||||
|
||||
def add_special_token(tokenizer: T5Tokenizer, text_encoder: T5Stack):
|
||||
"""
|
||||
Add special tokens for color and font to tokenizer and text encoder.
|
||||
|
||||
Args:
|
||||
tokenizer: Huggingface tokenizer.
|
||||
text_encoder: Huggingface T5 encoder.
|
||||
"""
|
||||
idx_font_dict = json.loads(MULTILINGUAL_10_LANG_IDX_JSON)
|
||||
idx_color_dict = json.loads(COLOR_IDX_JSON)
|
||||
|
||||
font_token = [f"<{font_code[:2]}-font-{idx_font_dict[font_code]}>" for font_code in idx_font_dict]
|
||||
color_token = [f"<color-{i}>" for i in range(len(idx_color_dict))]
|
||||
additional_special_tokens = []
|
||||
additional_special_tokens += color_token
|
||||
additional_special_tokens += font_token
|
||||
|
||||
tokenizer.add_tokens(additional_special_tokens, special_tokens=True)
|
||||
# Set mean_resizing=False to avoid PyTorch LAPACK dependency
|
||||
text_encoder.resize_token_embeddings(len(tokenizer), mean_resizing=False)
|
||||
|
||||
|
||||
def load_byt5(
|
||||
ckpt_path: str,
|
||||
dtype: Optional[torch.dtype],
|
||||
device: Union[str, torch.device],
|
||||
disable_mmap: bool = False,
|
||||
state_dict: Optional[dict] = None,
|
||||
) -> Tuple[T5Stack, T5Tokenizer]:
|
||||
BYT5_CONFIG_JSON = """
|
||||
{
|
||||
"_name_or_path": "/home/patrick/t5/byt5-small",
|
||||
"architectures": [
|
||||
"T5ForConditionalGeneration"
|
||||
],
|
||||
"d_ff": 3584,
|
||||
"d_kv": 64,
|
||||
"d_model": 1472,
|
||||
"decoder_start_token_id": 0,
|
||||
"dropout_rate": 0.1,
|
||||
"eos_token_id": 1,
|
||||
"feed_forward_proj": "gated-gelu",
|
||||
"gradient_checkpointing": false,
|
||||
"initializer_factor": 1.0,
|
||||
"is_encoder_decoder": true,
|
||||
"layer_norm_epsilon": 1e-06,
|
||||
"model_type": "t5",
|
||||
"num_decoder_layers": 4,
|
||||
"num_heads": 6,
|
||||
"num_layers": 12,
|
||||
"pad_token_id": 0,
|
||||
"relative_attention_num_buckets": 32,
|
||||
"tie_word_embeddings": false,
|
||||
"tokenizer_class": "ByT5Tokenizer",
|
||||
"transformers_version": "4.7.0.dev0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 384
|
||||
}
|
||||
"""
|
||||
|
||||
logger.info(f"Loading BYT5 tokenizer from {BYT5_TOKENIZER_PATH}")
|
||||
byt5_tokenizer = AutoTokenizer.from_pretrained(BYT5_TOKENIZER_PATH)
|
||||
|
||||
logger.info("Initializing BYT5 text encoder")
|
||||
config = json.loads(BYT5_CONFIG_JSON)
|
||||
config = T5Config(**config)
|
||||
with init_empty_weights():
|
||||
byt5_text_encoder = T5ForConditionalGeneration._from_config(config).get_encoder()
|
||||
|
||||
add_special_token(byt5_tokenizer, byt5_text_encoder)
|
||||
|
||||
if state_dict is not None:
|
||||
sd = state_dict
|
||||
else:
|
||||
logger.info(f"Loading state dict from {ckpt_path}")
|
||||
sd = load_safetensors(ckpt_path, device, disable_mmap=disable_mmap, dtype=dtype)
|
||||
|
||||
# remove "encoder." prefix
|
||||
sd = {k[len("encoder.") :] if k.startswith("encoder.") else k: v for k, v in sd.items()}
|
||||
sd["embed_tokens.weight"] = sd.pop("shared.weight")
|
||||
|
||||
info = byt5_text_encoder.load_state_dict(sd, strict=True, assign=True)
|
||||
byt5_text_encoder.to(device)
|
||||
byt5_text_encoder.eval()
|
||||
logger.info(f"BYT5 text encoder loaded with info: {info}")
|
||||
|
||||
return byt5_tokenizer, byt5_text_encoder
|
||||
|
||||
|
||||
def load_qwen2_5_vl(
|
||||
ckpt_path: str,
|
||||
dtype: Optional[torch.dtype],
|
||||
device: Union[str, torch.device],
|
||||
disable_mmap: bool = False,
|
||||
state_dict: Optional[dict] = None,
|
||||
) -> tuple[Qwen2Tokenizer, Qwen2_5_VLForConditionalGeneration]:
|
||||
QWEN2_5_VL_CONFIG_JSON = """
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2_5_VLForConditionalGeneration"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3584,
|
||||
"image_token_id": 151655,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 18944,
|
||||
"max_position_embeddings": 128000,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen2_5_vl",
|
||||
"num_attention_heads": 28,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 4,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": {
|
||||
"mrope_section": [
|
||||
16,
|
||||
24,
|
||||
24
|
||||
],
|
||||
"rope_type": "default",
|
||||
"type": "default"
|
||||
},
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": 32768,
|
||||
"text_config": {
|
||||
"architectures": [
|
||||
"Qwen2_5_VLForConditionalGeneration"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3584,
|
||||
"image_token_id": null,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 18944,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 128000,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen2_5_vl_text",
|
||||
"num_attention_heads": 28,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 4,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": {
|
||||
"mrope_section": [
|
||||
16,
|
||||
24,
|
||||
24
|
||||
],
|
||||
"rope_type": "default",
|
||||
"type": "default"
|
||||
},
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"torch_dtype": "float32",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"video_token_id": null,
|
||||
"vision_end_token_id": 151653,
|
||||
"vision_start_token_id": 151652,
|
||||
"vision_token_id": 151654,
|
||||
"vocab_size": 152064
|
||||
},
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.53.1",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"video_token_id": 151656,
|
||||
"vision_config": {
|
||||
"depth": 32,
|
||||
"fullatt_block_indexes": [
|
||||
7,
|
||||
15,
|
||||
23,
|
||||
31
|
||||
],
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1280,
|
||||
"in_channels": 3,
|
||||
"in_chans": 3,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 3420,
|
||||
"model_type": "qwen2_5_vl",
|
||||
"num_heads": 16,
|
||||
"out_hidden_size": 3584,
|
||||
"patch_size": 14,
|
||||
"spatial_merge_size": 2,
|
||||
"spatial_patch_size": 14,
|
||||
"temporal_patch_size": 2,
|
||||
"tokens_per_second": 2,
|
||||
"torch_dtype": "float32",
|
||||
"window_size": 112
|
||||
},
|
||||
"vision_end_token_id": 151653,
|
||||
"vision_start_token_id": 151652,
|
||||
"vision_token_id": 151654,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
"""
|
||||
config = json.loads(QWEN2_5_VL_CONFIG_JSON)
|
||||
config = Qwen2_5_VLConfig(**config)
|
||||
with init_empty_weights():
|
||||
qwen2_5_vl = Qwen2_5_VLForConditionalGeneration._from_config(config)
|
||||
|
||||
if state_dict is not None:
|
||||
sd = state_dict
|
||||
else:
|
||||
logger.info(f"Loading state dict from {ckpt_path}")
|
||||
sd = load_safetensors(ckpt_path, device, disable_mmap=disable_mmap, dtype=dtype)
|
||||
|
||||
# convert prefixes
|
||||
for key in list(sd.keys()):
|
||||
if key.startswith("model."):
|
||||
new_key = key.replace("model.", "model.language_model.", 1)
|
||||
elif key.startswith("visual."):
|
||||
new_key = key.replace("visual.", "model.visual.", 1)
|
||||
else:
|
||||
continue
|
||||
if key not in sd:
|
||||
logger.warning(f"Key {key} not found in state dict, skipping.")
|
||||
continue
|
||||
sd[new_key] = sd.pop(key)
|
||||
|
||||
info = qwen2_5_vl.load_state_dict(sd, strict=True, assign=True)
|
||||
logger.info(f"Loaded Qwen2.5-VL: {info}")
|
||||
qwen2_5_vl.to(device)
|
||||
qwen2_5_vl.eval()
|
||||
|
||||
if dtype is not None:
|
||||
if dtype.itemsize == 1: # fp8
|
||||
org_dtype = torch.bfloat16 # model weight is fp8 in loading, but original dtype is bfloat16
|
||||
logger.info(f"prepare Qwen2.5-VL for fp8: set to {dtype} from {org_dtype}")
|
||||
qwen2_5_vl.to(dtype)
|
||||
|
||||
# prepare LLM for fp8
|
||||
def prepare_fp8(vl_model: Qwen2_5_VLForConditionalGeneration, target_dtype):
|
||||
def forward_hook(module):
|
||||
def forward(hidden_states):
|
||||
input_dtype = hidden_states.dtype
|
||||
hidden_states = hidden_states.to(torch.float32)
|
||||
variance = hidden_states.pow(2).mean(-1, keepdim=True)
|
||||
hidden_states = hidden_states * torch.rsqrt(variance + module.variance_epsilon)
|
||||
# return module.weight.to(input_dtype) * hidden_states.to(input_dtype)
|
||||
return (module.weight.to(torch.float32) * hidden_states.to(torch.float32)).to(input_dtype)
|
||||
|
||||
return forward
|
||||
|
||||
def decoder_forward_hook(module):
|
||||
def forward(
|
||||
hidden_states: torch.Tensor,
|
||||
attention_mask: Optional[torch.Tensor] = None,
|
||||
position_ids: Optional[torch.LongTensor] = None,
|
||||
past_key_value: Optional[tuple[torch.Tensor]] = None,
|
||||
output_attentions: Optional[bool] = False,
|
||||
use_cache: Optional[bool] = False,
|
||||
cache_position: Optional[torch.LongTensor] = None,
|
||||
position_embeddings: Optional[tuple[torch.Tensor, torch.Tensor]] = None, # necessary, but kept here for BC
|
||||
**kwargs,
|
||||
) -> tuple[torch.FloatTensor, Optional[tuple[torch.FloatTensor, torch.FloatTensor]]]:
|
||||
|
||||
residual = hidden_states
|
||||
|
||||
hidden_states = module.input_layernorm(hidden_states)
|
||||
|
||||
# Self Attention
|
||||
hidden_states, self_attn_weights = module.self_attn(
|
||||
hidden_states=hidden_states,
|
||||
attention_mask=attention_mask,
|
||||
position_ids=position_ids,
|
||||
past_key_value=past_key_value,
|
||||
output_attentions=output_attentions,
|
||||
use_cache=use_cache,
|
||||
cache_position=cache_position,
|
||||
position_embeddings=position_embeddings,
|
||||
**kwargs,
|
||||
)
|
||||
input_dtype = hidden_states.dtype
|
||||
hidden_states = residual.to(torch.float32) + hidden_states.to(torch.float32)
|
||||
hidden_states = hidden_states.to(input_dtype)
|
||||
|
||||
# Fully Connected
|
||||
residual = hidden_states
|
||||
hidden_states = module.post_attention_layernorm(hidden_states)
|
||||
hidden_states = module.mlp(hidden_states)
|
||||
hidden_states = residual + hidden_states
|
||||
|
||||
outputs = (hidden_states,)
|
||||
|
||||
if output_attentions:
|
||||
outputs += (self_attn_weights,)
|
||||
|
||||
return outputs
|
||||
|
||||
return forward
|
||||
|
||||
for module in vl_model.modules():
|
||||
if module.__class__.__name__ in ["Embedding"]:
|
||||
# print("set", module.__class__.__name__, "to", target_dtype)
|
||||
module.to(target_dtype)
|
||||
if module.__class__.__name__ in ["Qwen2RMSNorm"]:
|
||||
# print("set", module.__class__.__name__, "hooks")
|
||||
module.forward = forward_hook(module)
|
||||
if module.__class__.__name__ in ["Qwen2_5_VLDecoderLayer"]:
|
||||
# print("set", module.__class__.__name__, "hooks")
|
||||
module.forward = decoder_forward_hook(module)
|
||||
if module.__class__.__name__ in ["Qwen2_5_VisionRotaryEmbedding"]:
|
||||
# print("set", module.__class__.__name__, "hooks")
|
||||
module.to(target_dtype)
|
||||
|
||||
prepare_fp8(qwen2_5_vl, org_dtype)
|
||||
|
||||
else:
|
||||
logger.info(f"Setting Qwen2.5-VL to dtype: {dtype}")
|
||||
qwen2_5_vl.to(dtype)
|
||||
|
||||
# Load tokenizer
|
||||
logger.info(f"Loading tokenizer from {QWEN_2_5_VL_IMAGE_ID}")
|
||||
tokenizer = Qwen2Tokenizer.from_pretrained(QWEN_2_5_VL_IMAGE_ID)
|
||||
return tokenizer, qwen2_5_vl
|
||||
|
||||
|
||||
TOKENIZER_MAX_LENGTH = 1024
|
||||
PROMPT_TEMPLATE_ENCODE_START_IDX = 34
|
||||
|
||||
|
||||
def get_qwen_prompt_embeds(
|
||||
tokenizer: Qwen2Tokenizer, vlm: Qwen2_5_VLForConditionalGeneration, prompt: Union[str, list[str]] = None
|
||||
) -> Tuple[torch.Tensor, torch.Tensor]:
|
||||
input_ids, mask = get_qwen_tokens(tokenizer, prompt)
|
||||
return get_qwen_prompt_embeds_from_tokens(vlm, input_ids, mask)
|
||||
|
||||
|
||||
def get_qwen_tokens(tokenizer: Qwen2Tokenizer, prompt: Union[str, list[str]] = None) -> Tuple[torch.Tensor, torch.Tensor]:
|
||||
tokenizer_max_length = TOKENIZER_MAX_LENGTH
|
||||
|
||||
# HunyuanImage-2.1 does not use "<|im_start|>assistant\n" in the prompt template
|
||||
prompt_template_encode = "<|im_start|>system\nDescribe the image by detailing the color, shape, size, texture, quantity, text, spatial relationships of the objects and background:<|im_end|>\n<|im_start|>user\n{}<|im_end|>"
|
||||
# \n<|im_start|>assistant\n"
|
||||
prompt_template_encode_start_idx = PROMPT_TEMPLATE_ENCODE_START_IDX
|
||||
# default_sample_size = 128
|
||||
|
||||
prompt = [prompt] if isinstance(prompt, str) else prompt
|
||||
|
||||
template = prompt_template_encode
|
||||
drop_idx = prompt_template_encode_start_idx
|
||||
txt = [template.format(e) for e in prompt]
|
||||
txt_tokens = tokenizer(txt, max_length=tokenizer_max_length + drop_idx, padding=True, truncation=True, return_tensors="pt")
|
||||
return txt_tokens.input_ids, txt_tokens.attention_mask
|
||||
|
||||
|
||||
def get_qwen_prompt_embeds_from_tokens(
|
||||
vlm: Qwen2_5_VLForConditionalGeneration, input_ids: torch.Tensor, attention_mask: torch.Tensor
|
||||
) -> Tuple[torch.Tensor, torch.Tensor]:
|
||||
tokenizer_max_length = TOKENIZER_MAX_LENGTH
|
||||
drop_idx = PROMPT_TEMPLATE_ENCODE_START_IDX
|
||||
|
||||
device = vlm.device
|
||||
dtype = vlm.dtype
|
||||
|
||||
input_ids = input_ids.to(device=device)
|
||||
attention_mask = attention_mask.to(device=device)
|
||||
|
||||
if dtype.itemsize == 1: # fp8
|
||||
with torch.no_grad(), torch.autocast(device_type=device.type, dtype=torch.bfloat16, enabled=True):
|
||||
encoder_hidden_states = vlm(input_ids=input_ids, attention_mask=attention_mask, output_hidden_states=True)
|
||||
else:
|
||||
with torch.no_grad(), torch.autocast(device_type=device.type, dtype=dtype, enabled=True):
|
||||
encoder_hidden_states = vlm(input_ids=input_ids, attention_mask=attention_mask, output_hidden_states=True)
|
||||
|
||||
hidden_states = encoder_hidden_states.hidden_states[-3] # use the 3rd last layer's hidden states for HunyuanImage-2.1
|
||||
if hidden_states.shape[1] > tokenizer_max_length + drop_idx:
|
||||
logger.warning(f"Hidden states shape {hidden_states.shape} exceeds max length {tokenizer_max_length + drop_idx}")
|
||||
|
||||
# --- Unnecessary complicated processing, keep for reference ---
|
||||
# split_hidden_states = extract_masked_hidden(hidden_states, txt_tokens.attention_mask)
|
||||
# split_hidden_states = [e[drop_idx:] for e in split_hidden_states]
|
||||
# attn_mask_list = [torch.ones(e.size(0), dtype=torch.long, device=e.device) for e in split_hidden_states]
|
||||
# max_seq_len = max([e.size(0) for e in split_hidden_states])
|
||||
# prompt_embeds = torch.stack([torch.cat([u, u.new_zeros(max_seq_len - u.size(0), u.size(1))]) for u in split_hidden_states])
|
||||
# encoder_attention_mask = torch.stack([torch.cat([u, u.new_zeros(max_seq_len - u.size(0))]) for u in attn_mask_list])
|
||||
# ----------------------------------------------------------
|
||||
|
||||
prompt_embeds = hidden_states[:, drop_idx:, :]
|
||||
encoder_attention_mask = attention_mask[:, drop_idx:]
|
||||
prompt_embeds = prompt_embeds.to(device=device)
|
||||
|
||||
return prompt_embeds, encoder_attention_mask
|
||||
|
||||
|
||||
def format_prompt(texts, styles):
|
||||
"""
|
||||
Text "{text}" in {color}, {type}.
|
||||
"""
|
||||
|
||||
prompt = ""
|
||||
for text, style in zip(texts, styles):
|
||||
# color and style are always None in official implementation, so we only use text
|
||||
text_prompt = f'Text "{text}"'
|
||||
text_prompt += ". "
|
||||
prompt = prompt + text_prompt
|
||||
return prompt
|
||||
|
||||
|
||||
BYT5_MAX_LENGTH = 128
|
||||
|
||||
|
||||
def get_glyph_prompt_embeds(
|
||||
tokenizer: T5Tokenizer, text_encoder: T5Stack, prompt: Optional[str] = None
|
||||
) -> Tuple[list[bool], torch.Tensor, torch.Tensor]:
|
||||
byt5_tokens, byt5_text_mask = get_byt5_text_tokens(tokenizer, prompt)
|
||||
return get_byt5_prompt_embeds_from_tokens(text_encoder, byt5_tokens, byt5_text_mask)
|
||||
|
||||
|
||||
def get_byt5_prompt_embeds_from_tokens(
|
||||
text_encoder: T5Stack, byt5_text_ids: Optional[torch.Tensor], byt5_text_mask: Optional[torch.Tensor]
|
||||
) -> Tuple[list[bool], torch.Tensor, torch.Tensor]:
|
||||
byt5_max_length = BYT5_MAX_LENGTH
|
||||
|
||||
if byt5_text_ids is None or byt5_text_mask is None or byt5_text_mask.sum() == 0:
|
||||
return (
|
||||
[False],
|
||||
torch.zeros((1, byt5_max_length, 1472), device=text_encoder.device),
|
||||
torch.zeros((1, byt5_max_length), device=text_encoder.device, dtype=torch.int64),
|
||||
)
|
||||
|
||||
byt5_text_ids = byt5_text_ids.to(device=text_encoder.device)
|
||||
byt5_text_mask = byt5_text_mask.to(device=text_encoder.device)
|
||||
|
||||
with torch.no_grad(), torch.autocast(device_type=text_encoder.device.type, dtype=text_encoder.dtype, enabled=True):
|
||||
byt5_prompt_embeds = text_encoder(byt5_text_ids, attention_mask=byt5_text_mask.float())
|
||||
byt5_emb = byt5_prompt_embeds[0]
|
||||
|
||||
return [True], byt5_emb, byt5_text_mask
|
||||
|
||||
|
||||
def get_byt5_text_tokens(tokenizer, prompt):
|
||||
if not prompt:
|
||||
return None, None
|
||||
|
||||
try:
|
||||
text_prompt_texts = []
|
||||
# pattern_quote_single = r"\'(.*?)\'"
|
||||
pattern_quote_double = r"\"(.*?)\""
|
||||
pattern_quote_chinese_single = r"‘(.*?)’"
|
||||
pattern_quote_chinese_double = r"“(.*?)”"
|
||||
|
||||
# matches_quote_single = re.findall(pattern_quote_single, prompt)
|
||||
matches_quote_double = re.findall(pattern_quote_double, prompt)
|
||||
matches_quote_chinese_single = re.findall(pattern_quote_chinese_single, prompt)
|
||||
matches_quote_chinese_double = re.findall(pattern_quote_chinese_double, prompt)
|
||||
|
||||
# text_prompt_texts.extend(matches_quote_single)
|
||||
text_prompt_texts.extend(matches_quote_double)
|
||||
text_prompt_texts.extend(matches_quote_chinese_single)
|
||||
text_prompt_texts.extend(matches_quote_chinese_double)
|
||||
|
||||
if not text_prompt_texts:
|
||||
return None, None
|
||||
|
||||
text_prompt_style_list = [{"color": None, "font-family": None} for _ in range(len(text_prompt_texts))]
|
||||
glyph_text_formatted = format_prompt(text_prompt_texts, text_prompt_style_list)
|
||||
logger.info(f"Glyph text formatted: {glyph_text_formatted}")
|
||||
|
||||
byt5_text_inputs = tokenizer(
|
||||
glyph_text_formatted,
|
||||
padding="max_length",
|
||||
max_length=BYT5_MAX_LENGTH,
|
||||
truncation=True,
|
||||
add_special_tokens=True,
|
||||
return_tensors="pt",
|
||||
)
|
||||
|
||||
byt5_text_ids = byt5_text_inputs.input_ids
|
||||
byt5_text_mask = byt5_text_inputs.attention_mask
|
||||
|
||||
return byt5_text_ids, byt5_text_mask
|
||||
|
||||
except Exception as e:
|
||||
logger.warning(f"Warning: Error in glyph encoding, using fallback: {e}")
|
||||
return None, None
|
||||
483
library/hunyuan_image_utils.py
Normal file
483
library/hunyuan_image_utils.py
Normal file
@@ -0,0 +1,483 @@
|
||||
# Original work: https://github.com/Tencent-Hunyuan/HunyuanImage-2.1
|
||||
# Re-implemented for license compliance for sd-scripts.
|
||||
|
||||
import math
|
||||
from typing import Tuple, Union, Optional
|
||||
import torch
|
||||
|
||||
from library.utils import setup_logging
|
||||
|
||||
setup_logging()
|
||||
import logging
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
MODEL_VERSION_2_1 = "hunyuan-image-2.1"
|
||||
|
||||
# region model
|
||||
|
||||
|
||||
def _to_tuple(x, dim=2):
|
||||
"""
|
||||
Convert int or sequence to tuple of specified dimension.
|
||||
|
||||
Args:
|
||||
x: Int or sequence to convert.
|
||||
dim: Target dimension for tuple.
|
||||
|
||||
Returns:
|
||||
Tuple of length dim.
|
||||
"""
|
||||
if isinstance(x, int) or isinstance(x, float):
|
||||
return (x,) * dim
|
||||
elif len(x) == dim:
|
||||
return x
|
||||
else:
|
||||
raise ValueError(f"Expected length {dim} or int, but got {x}")
|
||||
|
||||
|
||||
def get_meshgrid_nd(start, dim=2):
|
||||
"""
|
||||
Generate n-dimensional coordinate meshgrid from 0 to grid_size.
|
||||
|
||||
Creates coordinate grids for each spatial dimension, useful for
|
||||
generating position embeddings.
|
||||
|
||||
Args:
|
||||
start: Grid size for each dimension (int or tuple).
|
||||
dim: Number of spatial dimensions.
|
||||
|
||||
Returns:
|
||||
Coordinate grid tensor [dim, *grid_size].
|
||||
"""
|
||||
# Convert start to grid sizes
|
||||
num = _to_tuple(start, dim=dim)
|
||||
start = (0,) * dim
|
||||
stop = num
|
||||
|
||||
# Generate coordinate arrays for each dimension
|
||||
axis_grid = []
|
||||
for i in range(dim):
|
||||
a, b, n = start[i], stop[i], num[i]
|
||||
g = torch.linspace(a, b, n + 1, dtype=torch.float32)[:n]
|
||||
axis_grid.append(g)
|
||||
grid = torch.meshgrid(*axis_grid, indexing="ij") # dim x [W, H, D]
|
||||
grid = torch.stack(grid, dim=0) # [dim, W, H, D]
|
||||
|
||||
return grid
|
||||
|
||||
|
||||
def get_nd_rotary_pos_embed(rope_dim_list, start, theta=10000.0):
|
||||
"""
|
||||
Generate n-dimensional rotary position embeddings for spatial tokens.
|
||||
|
||||
Creates RoPE embeddings for multi-dimensional positional encoding,
|
||||
distributing head dimensions across spatial dimensions.
|
||||
|
||||
Args:
|
||||
rope_dim_list: Dimensions allocated to each spatial axis (should sum to head_dim).
|
||||
start: Spatial grid size for each dimension.
|
||||
theta: Base frequency for RoPE computation.
|
||||
|
||||
Returns:
|
||||
Tuple of (cos_freqs, sin_freqs) for rotary embedding [H*W, D/2].
|
||||
"""
|
||||
|
||||
grid = get_meshgrid_nd(start, dim=len(rope_dim_list)) # [3, W, H, D] / [2, W, H]
|
||||
|
||||
# Generate RoPE embeddings for each spatial dimension
|
||||
embs = []
|
||||
for i in range(len(rope_dim_list)):
|
||||
emb = get_1d_rotary_pos_embed(rope_dim_list[i], grid[i].reshape(-1), theta) # 2 x [WHD, rope_dim_list[i]]
|
||||
embs.append(emb)
|
||||
|
||||
cos = torch.cat([emb[0] for emb in embs], dim=1) # (WHD, D/2)
|
||||
sin = torch.cat([emb[1] for emb in embs], dim=1) # (WHD, D/2)
|
||||
return cos, sin
|
||||
|
||||
|
||||
def get_1d_rotary_pos_embed(
|
||||
dim: int, pos: Union[torch.FloatTensor, int], theta: float = 10000.0
|
||||
) -> Tuple[torch.Tensor, torch.Tensor]:
|
||||
"""
|
||||
Generate 1D rotary position embeddings.
|
||||
|
||||
Args:
|
||||
dim: Embedding dimension (must be even).
|
||||
pos: Position indices [S] or scalar for sequence length.
|
||||
theta: Base frequency for sinusoidal encoding.
|
||||
|
||||
Returns:
|
||||
Tuple of (cos_freqs, sin_freqs) tensors [S, D].
|
||||
"""
|
||||
if isinstance(pos, int):
|
||||
pos = torch.arange(pos).float()
|
||||
|
||||
freqs = 1.0 / (theta ** (torch.arange(0, dim, 2)[: (dim // 2)].float() / dim)) # [D/2]
|
||||
freqs = torch.outer(pos, freqs) # [S, D/2]
|
||||
freqs_cos = freqs.cos().repeat_interleave(2, dim=1) # [S, D]
|
||||
freqs_sin = freqs.sin().repeat_interleave(2, dim=1) # [S, D]
|
||||
return freqs_cos, freqs_sin
|
||||
|
||||
|
||||
def timestep_embedding(t, dim, max_period=10000):
|
||||
"""
|
||||
Create sinusoidal timestep embeddings for diffusion models.
|
||||
|
||||
Converts scalar timesteps to high-dimensional embeddings using
|
||||
sinusoidal encoding at different frequencies.
|
||||
|
||||
Args:
|
||||
t: Timestep tensor [N].
|
||||
dim: Output embedding dimension.
|
||||
max_period: Maximum period for frequency computation.
|
||||
|
||||
Returns:
|
||||
Timestep embeddings [N, dim].
|
||||
"""
|
||||
half = dim // 2
|
||||
freqs = torch.exp(-math.log(max_period) * torch.arange(start=0, end=half, dtype=torch.float32) / half).to(device=t.device)
|
||||
args = t[:, None].float() * freqs[None]
|
||||
embedding = torch.cat([torch.cos(args), torch.sin(args)], dim=-1)
|
||||
if dim % 2:
|
||||
embedding = torch.cat([embedding, torch.zeros_like(embedding[:, :1])], dim=-1)
|
||||
return embedding
|
||||
|
||||
|
||||
def modulate(x, shift=None, scale=None):
|
||||
"""
|
||||
Apply adaptive layer normalization modulation.
|
||||
|
||||
Applies scale and shift transformations for conditioning
|
||||
in adaptive layer normalization.
|
||||
|
||||
Args:
|
||||
x: Input tensor to modulate.
|
||||
shift: Additive shift parameter (optional).
|
||||
scale: Multiplicative scale parameter (optional).
|
||||
|
||||
Returns:
|
||||
Modulated tensor x * (1 + scale) + shift.
|
||||
"""
|
||||
if scale is None and shift is None:
|
||||
return x
|
||||
elif shift is None:
|
||||
return x * (1 + scale.unsqueeze(1))
|
||||
elif scale is None:
|
||||
return x + shift.unsqueeze(1)
|
||||
else:
|
||||
return x * (1 + scale.unsqueeze(1)) + shift.unsqueeze(1)
|
||||
|
||||
|
||||
def apply_gate(x, gate=None, tanh=False):
|
||||
"""
|
||||
Apply gating mechanism to tensor.
|
||||
|
||||
Multiplies input by gate values, optionally applying tanh activation.
|
||||
Used in residual connections for adaptive control.
|
||||
|
||||
Args:
|
||||
x: Input tensor to gate.
|
||||
gate: Gating values (optional).
|
||||
tanh: Whether to apply tanh to gate values.
|
||||
|
||||
Returns:
|
||||
Gated tensor x * gate (with optional tanh).
|
||||
"""
|
||||
if gate is None:
|
||||
return x
|
||||
if tanh:
|
||||
return x * gate.unsqueeze(1).tanh()
|
||||
else:
|
||||
return x * gate.unsqueeze(1)
|
||||
|
||||
|
||||
def reshape_for_broadcast(
|
||||
freqs_cis: Tuple[torch.Tensor, torch.Tensor],
|
||||
x: torch.Tensor,
|
||||
head_first=False,
|
||||
):
|
||||
"""
|
||||
Reshape RoPE frequency tensors for broadcasting with attention tensors.
|
||||
|
||||
Args:
|
||||
freqs_cis: Tuple of (cos_freqs, sin_freqs) tensors.
|
||||
x: Target tensor for broadcasting compatibility.
|
||||
head_first: Must be False (only supported layout).
|
||||
|
||||
Returns:
|
||||
Reshaped (cos_freqs, sin_freqs) tensors ready for broadcasting.
|
||||
"""
|
||||
assert not head_first, "Only head_first=False layout supported."
|
||||
assert isinstance(freqs_cis, tuple), "Expected tuple of (cos, sin) frequency tensors."
|
||||
assert x.ndim > 1, f"x should have at least 2 dimensions, but got {x.ndim}"
|
||||
|
||||
# Validate frequency tensor dimensions match target tensor
|
||||
assert freqs_cis[0].shape == (
|
||||
x.shape[1],
|
||||
x.shape[-1],
|
||||
), f"Frequency tensor shape {freqs_cis[0].shape} incompatible with target shape {x.shape}"
|
||||
|
||||
shape = [d if i == 1 or i == x.ndim - 1 else 1 for i, d in enumerate(x.shape)]
|
||||
return freqs_cis[0].view(*shape), freqs_cis[1].view(*shape)
|
||||
|
||||
|
||||
def rotate_half(x):
|
||||
"""
|
||||
Rotate half the dimensions for RoPE computation.
|
||||
|
||||
Splits the last dimension in half and applies a 90-degree rotation
|
||||
by swapping and negating components.
|
||||
|
||||
Args:
|
||||
x: Input tensor [..., D] where D is even.
|
||||
|
||||
Returns:
|
||||
Rotated tensor with same shape as input.
|
||||
"""
|
||||
x_real, x_imag = x.float().reshape(*x.shape[:-1], -1, 2).unbind(-1) # [B, S, H, D//2]
|
||||
return torch.stack([-x_imag, x_real], dim=-1).flatten(3)
|
||||
|
||||
|
||||
def apply_rotary_emb(
|
||||
xq: torch.Tensor, xk: torch.Tensor, freqs_cis: Tuple[torch.Tensor, torch.Tensor], head_first: bool = False
|
||||
) -> Tuple[torch.Tensor, torch.Tensor]:
|
||||
"""
|
||||
Apply rotary position embeddings to query and key tensors.
|
||||
|
||||
Args:
|
||||
xq: Query tensor [B, S, H, D].
|
||||
xk: Key tensor [B, S, H, D].
|
||||
freqs_cis: Tuple of (cos_freqs, sin_freqs) for rotation.
|
||||
head_first: Whether head dimension precedes sequence dimension.
|
||||
|
||||
Returns:
|
||||
Tuple of rotated (query, key) tensors.
|
||||
"""
|
||||
device = xq.device
|
||||
dtype = xq.dtype
|
||||
|
||||
cos, sin = reshape_for_broadcast(freqs_cis, xq, head_first)
|
||||
cos, sin = cos.to(device), sin.to(device)
|
||||
|
||||
# Apply rotation: x' = x * cos + rotate_half(x) * sin
|
||||
xq_out = (xq.float() * cos + rotate_half(xq.float()) * sin).to(dtype)
|
||||
xk_out = (xk.float() * cos + rotate_half(xk.float()) * sin).to(dtype)
|
||||
|
||||
return xq_out, xk_out
|
||||
|
||||
|
||||
# endregion
|
||||
|
||||
# region inference
|
||||
|
||||
|
||||
def get_timesteps_sigmas(sampling_steps: int, shift: float, device: torch.device) -> Tuple[torch.Tensor, torch.Tensor]:
|
||||
"""
|
||||
Generate timesteps and sigmas for diffusion sampling.
|
||||
|
||||
Args:
|
||||
sampling_steps: Number of sampling steps.
|
||||
shift: Sigma shift parameter for schedule modification.
|
||||
device: Target device for tensors.
|
||||
|
||||
Returns:
|
||||
Tuple of (timesteps, sigmas) tensors.
|
||||
"""
|
||||
sigmas = torch.linspace(1, 0, sampling_steps + 1)
|
||||
sigmas = (shift * sigmas) / (1 + (shift - 1) * sigmas)
|
||||
sigmas = sigmas.to(torch.float32)
|
||||
timesteps = (sigmas[:-1] * 1000).to(dtype=torch.float32, device=device)
|
||||
return timesteps, sigmas
|
||||
|
||||
|
||||
def step(latents, noise_pred, sigmas, step_i):
|
||||
"""
|
||||
Perform a single diffusion sampling step.
|
||||
|
||||
Args:
|
||||
latents: Current latent state.
|
||||
noise_pred: Predicted noise.
|
||||
sigmas: Noise schedule sigmas.
|
||||
step_i: Current step index.
|
||||
|
||||
Returns:
|
||||
Updated latents after the step.
|
||||
"""
|
||||
return latents.float() - (sigmas[step_i] - sigmas[step_i + 1]) * noise_pred.float()
|
||||
|
||||
|
||||
# endregion
|
||||
|
||||
|
||||
# region AdaptiveProjectedGuidance
|
||||
|
||||
|
||||
class MomentumBuffer:
|
||||
"""
|
||||
Exponential moving average buffer for APG momentum.
|
||||
"""
|
||||
|
||||
def __init__(self, momentum: float):
|
||||
self.momentum = momentum
|
||||
self.running_average = 0
|
||||
|
||||
def update(self, update_value: torch.Tensor):
|
||||
new_average = self.momentum * self.running_average
|
||||
self.running_average = update_value + new_average
|
||||
|
||||
|
||||
def normalized_guidance_apg(
|
||||
pred_cond: torch.Tensor,
|
||||
pred_uncond: torch.Tensor,
|
||||
guidance_scale: float,
|
||||
momentum_buffer: Optional[MomentumBuffer] = None,
|
||||
eta: float = 1.0,
|
||||
norm_threshold: float = 0.0,
|
||||
use_original_formulation: bool = False,
|
||||
):
|
||||
"""
|
||||
Apply normalized adaptive projected guidance.
|
||||
|
||||
Projects the guidance vector to reduce over-saturation while maintaining
|
||||
directional control by decomposing into parallel and orthogonal components.
|
||||
|
||||
Args:
|
||||
pred_cond: Conditional prediction.
|
||||
pred_uncond: Unconditional prediction.
|
||||
guidance_scale: Guidance scale factor.
|
||||
momentum_buffer: Optional momentum buffer for temporal smoothing.
|
||||
eta: Scaling factor for parallel component.
|
||||
norm_threshold: Maximum norm for guidance vector clipping.
|
||||
use_original_formulation: Whether to use original APG formulation.
|
||||
|
||||
Returns:
|
||||
Guided prediction tensor.
|
||||
"""
|
||||
diff = pred_cond - pred_uncond
|
||||
dim = [-i for i in range(1, len(diff.shape))] # All dimensions except batch
|
||||
|
||||
# Apply momentum smoothing if available
|
||||
if momentum_buffer is not None:
|
||||
momentum_buffer.update(diff)
|
||||
diff = momentum_buffer.running_average
|
||||
|
||||
# Apply norm clipping if threshold is set
|
||||
if norm_threshold > 0:
|
||||
diff_norm = diff.norm(p=2, dim=dim, keepdim=True)
|
||||
scale_factor = torch.minimum(torch.ones_like(diff_norm), norm_threshold / diff_norm)
|
||||
diff = diff * scale_factor
|
||||
|
||||
# Project guidance vector into parallel and orthogonal components
|
||||
v0, v1 = diff.double(), pred_cond.double()
|
||||
v1 = torch.nn.functional.normalize(v1, dim=dim)
|
||||
v0_parallel = (v0 * v1).sum(dim=dim, keepdim=True) * v1
|
||||
v0_orthogonal = v0 - v0_parallel
|
||||
diff_parallel, diff_orthogonal = v0_parallel.type_as(diff), v0_orthogonal.type_as(diff)
|
||||
|
||||
# Combine components with different scaling
|
||||
normalized_update = diff_orthogonal + eta * diff_parallel
|
||||
pred = pred_cond if use_original_formulation else pred_uncond
|
||||
pred = pred + guidance_scale * normalized_update
|
||||
|
||||
return pred
|
||||
|
||||
|
||||
class AdaptiveProjectedGuidance:
|
||||
"""
|
||||
Adaptive Projected Guidance for classifier-free guidance.
|
||||
|
||||
Implements APG which projects the guidance vector to reduce over-saturation
|
||||
while maintaining directional control.
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
guidance_scale: float = 7.5,
|
||||
adaptive_projected_guidance_momentum: Optional[float] = None,
|
||||
adaptive_projected_guidance_rescale: float = 15.0,
|
||||
eta: float = 0.0,
|
||||
guidance_rescale: float = 0.0,
|
||||
use_original_formulation: bool = False,
|
||||
):
|
||||
assert guidance_rescale == 0.0, "guidance_rescale > 0.0 not supported."
|
||||
|
||||
self.guidance_scale = guidance_scale
|
||||
self.adaptive_projected_guidance_momentum = adaptive_projected_guidance_momentum
|
||||
self.adaptive_projected_guidance_rescale = adaptive_projected_guidance_rescale
|
||||
self.eta = eta
|
||||
self.guidance_rescale = guidance_rescale
|
||||
self.use_original_formulation = use_original_formulation
|
||||
self.momentum_buffer = None
|
||||
|
||||
def __call__(self, pred_cond: torch.Tensor, pred_uncond: Optional[torch.Tensor] = None, step=None) -> torch.Tensor:
|
||||
if step == 0 and self.adaptive_projected_guidance_momentum is not None:
|
||||
self.momentum_buffer = MomentumBuffer(self.adaptive_projected_guidance_momentum)
|
||||
|
||||
pred = normalized_guidance_apg(
|
||||
pred_cond,
|
||||
pred_uncond,
|
||||
self.guidance_scale,
|
||||
self.momentum_buffer,
|
||||
self.eta,
|
||||
self.adaptive_projected_guidance_rescale,
|
||||
self.use_original_formulation,
|
||||
)
|
||||
|
||||
return pred
|
||||
|
||||
|
||||
def apply_classifier_free_guidance(
|
||||
noise_pred_text: torch.Tensor,
|
||||
noise_pred_uncond: torch.Tensor,
|
||||
is_ocr: bool,
|
||||
guidance_scale: float,
|
||||
step: int,
|
||||
apg_start_step_ocr: int = 75,
|
||||
apg_start_step_general: int = 10,
|
||||
cfg_guider_ocr: AdaptiveProjectedGuidance = None,
|
||||
cfg_guider_general: AdaptiveProjectedGuidance = None,
|
||||
):
|
||||
"""
|
||||
Apply classifier-free guidance with OCR-aware APG for batch_size=1.
|
||||
|
||||
Args:
|
||||
noise_pred_text: Conditional noise prediction tensor [1, ...].
|
||||
noise_pred_uncond: Unconditional noise prediction tensor [1, ...].
|
||||
is_ocr: Whether this sample requires OCR-specific guidance.
|
||||
guidance_scale: Guidance scale for CFG.
|
||||
step: Current diffusion step index.
|
||||
apg_start_step_ocr: Step to start APG for OCR regions.
|
||||
apg_start_step_general: Step to start APG for general regions.
|
||||
cfg_guider_ocr: APG guider for OCR regions.
|
||||
cfg_guider_general: APG guider for general regions.
|
||||
|
||||
Returns:
|
||||
Guided noise prediction tensor [1, ...].
|
||||
"""
|
||||
if guidance_scale == 1.0:
|
||||
return noise_pred_text
|
||||
|
||||
# Select appropriate guider and start step based on OCR requirement
|
||||
if is_ocr:
|
||||
cfg_guider = cfg_guider_ocr
|
||||
apg_start_step = apg_start_step_ocr
|
||||
else:
|
||||
cfg_guider = cfg_guider_general
|
||||
apg_start_step = apg_start_step_general
|
||||
|
||||
# Apply standard CFG or APG based on current step
|
||||
if step <= apg_start_step:
|
||||
# Standard classifier-free guidance
|
||||
noise_pred = noise_pred_uncond + guidance_scale * (noise_pred_text - noise_pred_uncond)
|
||||
# Initialize APG guider state
|
||||
_ = cfg_guider(noise_pred_text, noise_pred_uncond, step=step)
|
||||
else:
|
||||
# Use APG for guidance
|
||||
noise_pred = cfg_guider(noise_pred_text, noise_pred_uncond, step=step)
|
||||
|
||||
return noise_pred
|
||||
|
||||
|
||||
# endregion
|
||||
755
library/hunyuan_image_vae.py
Normal file
755
library/hunyuan_image_vae.py
Normal file
@@ -0,0 +1,755 @@
|
||||
from typing import Optional, Tuple
|
||||
|
||||
from einops import rearrange
|
||||
import numpy as np
|
||||
import torch
|
||||
from torch import Tensor, nn
|
||||
from torch.nn import Conv2d
|
||||
from diffusers.models.autoencoders.vae import DiagonalGaussianDistribution
|
||||
|
||||
from library.safetensors_utils import load_safetensors
|
||||
from library.utils import setup_logging
|
||||
|
||||
setup_logging()
|
||||
import logging
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
VAE_SCALE_FACTOR = 32 # 32x spatial compression
|
||||
|
||||
LATENT_SCALING_FACTOR = 0.75289 # Latent scaling factor for Hunyuan Image-2.1
|
||||
|
||||
|
||||
def swish(x: Tensor) -> Tensor:
|
||||
"""Swish activation function: x * sigmoid(x)."""
|
||||
return x * torch.sigmoid(x)
|
||||
|
||||
|
||||
class AttnBlock(nn.Module):
|
||||
"""Self-attention block using scaled dot-product attention."""
|
||||
|
||||
def __init__(self, in_channels: int, chunk_size: Optional[int] = None):
|
||||
super().__init__()
|
||||
self.in_channels = in_channels
|
||||
self.norm = nn.GroupNorm(num_groups=32, num_channels=in_channels, eps=1e-6, affine=True)
|
||||
if chunk_size is None or chunk_size <= 0:
|
||||
self.q = Conv2d(in_channels, in_channels, kernel_size=1)
|
||||
self.k = Conv2d(in_channels, in_channels, kernel_size=1)
|
||||
self.v = Conv2d(in_channels, in_channels, kernel_size=1)
|
||||
self.proj_out = Conv2d(in_channels, in_channels, kernel_size=1)
|
||||
else:
|
||||
self.q = ChunkedConv2d(in_channels, in_channels, kernel_size=1, chunk_size=chunk_size)
|
||||
self.k = ChunkedConv2d(in_channels, in_channels, kernel_size=1, chunk_size=chunk_size)
|
||||
self.v = ChunkedConv2d(in_channels, in_channels, kernel_size=1, chunk_size=chunk_size)
|
||||
self.proj_out = ChunkedConv2d(in_channels, in_channels, kernel_size=1, chunk_size=chunk_size)
|
||||
|
||||
def attention(self, x: Tensor) -> Tensor:
|
||||
x = self.norm(x)
|
||||
q = self.q(x)
|
||||
k = self.k(x)
|
||||
v = self.v(x)
|
||||
|
||||
b, c, h, w = q.shape
|
||||
q = rearrange(q, "b c h w -> b (h w) c").contiguous()
|
||||
k = rearrange(k, "b c h w -> b (h w) c").contiguous()
|
||||
v = rearrange(v, "b c h w -> b (h w) c").contiguous()
|
||||
|
||||
x = nn.functional.scaled_dot_product_attention(q, k, v)
|
||||
return rearrange(x, "b (h w) c -> b c h w", h=h, w=w, c=c, b=b)
|
||||
|
||||
def forward(self, x: Tensor) -> Tensor:
|
||||
return x + self.proj_out(self.attention(x))
|
||||
|
||||
|
||||
class ChunkedConv2d(nn.Conv2d):
|
||||
"""
|
||||
Convolutional layer that processes input in chunks to reduce memory usage.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
chunk_size : int, optional
|
||||
Size of chunks to process at a time. Default is 64.
|
||||
"""
|
||||
|
||||
def __init__(self, *args, **kwargs):
|
||||
if "chunk_size" in kwargs:
|
||||
self.chunk_size = kwargs.pop("chunk_size", 64)
|
||||
super().__init__(*args, **kwargs)
|
||||
assert self.padding_mode == "zeros", "Only 'zeros' padding mode is supported."
|
||||
assert self.dilation == (1, 1) and self.stride == (1, 1), "Only dilation=1 and stride=1 are supported."
|
||||
assert self.groups == 1, "Only groups=1 is supported."
|
||||
assert self.kernel_size[0] == self.kernel_size[1], "Only square kernels are supported."
|
||||
assert (
|
||||
self.padding[0] == self.padding[1] and self.padding[0] == self.kernel_size[0] // 2
|
||||
), "Only kernel_size//2 padding is supported."
|
||||
self.original_padding = self.padding
|
||||
self.padding = (0, 0) # We handle padding manually in forward
|
||||
|
||||
def forward(self, x: Tensor) -> Tensor:
|
||||
# If chunking is not needed, process normally. We chunk only along height dimension.
|
||||
if self.chunk_size is None or x.shape[1] <= self.chunk_size:
|
||||
self.padding = self.original_padding
|
||||
x = super().forward(x)
|
||||
self.padding = (0, 0)
|
||||
if torch.cuda.is_available():
|
||||
torch.cuda.empty_cache()
|
||||
return x
|
||||
|
||||
# Process input in chunks to reduce memory usage
|
||||
org_shape = x.shape
|
||||
|
||||
# If kernel size is not 1, we need to use overlapping chunks
|
||||
overlap = self.kernel_size[0] // 2 # 1 for kernel size 3
|
||||
step = self.chunk_size - overlap
|
||||
y = torch.zeros((org_shape[0], self.out_channels, org_shape[2], org_shape[3]), dtype=x.dtype, device=x.device)
|
||||
yi = 0
|
||||
i = 0
|
||||
while i < org_shape[2]:
|
||||
si = i if i == 0 else i - overlap
|
||||
ei = i + self.chunk_size
|
||||
|
||||
# Check last chunk. If remaining part is small, include it in last chunk
|
||||
if ei > org_shape[2] or ei + step // 4 > org_shape[2]:
|
||||
ei = org_shape[2]
|
||||
|
||||
chunk = x[:, :, : ei - si, :]
|
||||
x = x[:, :, ei - si - overlap * 2 :, :]
|
||||
|
||||
# Pad chunk if needed: This is as the original Conv2d with padding
|
||||
if i == 0: # First chunk
|
||||
# Pad except bottom
|
||||
chunk = torch.nn.functional.pad(chunk, (overlap, overlap, overlap, 0), mode="constant", value=0)
|
||||
elif ei == org_shape[2]: # Last chunk
|
||||
# Pad except top
|
||||
chunk = torch.nn.functional.pad(chunk, (overlap, overlap, 0, overlap), mode="constant", value=0)
|
||||
else:
|
||||
# Pad left and right only
|
||||
chunk = torch.nn.functional.pad(chunk, (overlap, overlap), mode="constant", value=0)
|
||||
|
||||
chunk = super().forward(chunk)
|
||||
y[:, :, yi : yi + chunk.shape[2], :] = chunk
|
||||
yi += chunk.shape[2]
|
||||
del chunk
|
||||
|
||||
if ei == org_shape[2]:
|
||||
break
|
||||
i += step
|
||||
|
||||
assert yi == org_shape[2], f"yi={yi}, org_shape[2]={org_shape[2]}"
|
||||
|
||||
if torch.cuda.is_available():
|
||||
torch.cuda.empty_cache() # This helps reduce peak memory usage, but slows down a bit
|
||||
return y
|
||||
|
||||
|
||||
class ResnetBlock(nn.Module):
|
||||
"""
|
||||
Residual block with two convolutions, group normalization, and swish activation.
|
||||
Includes skip connection with optional channel dimension matching.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
in_channels : int
|
||||
Number of input channels.
|
||||
out_channels : int
|
||||
Number of output channels.
|
||||
"""
|
||||
|
||||
def __init__(self, in_channels: int, out_channels: int, chunk_size: Optional[int] = None):
|
||||
super().__init__()
|
||||
self.in_channels = in_channels
|
||||
self.out_channels = out_channels
|
||||
|
||||
self.norm1 = nn.GroupNorm(num_groups=32, num_channels=in_channels, eps=1e-6, affine=True)
|
||||
self.norm2 = nn.GroupNorm(num_groups=32, num_channels=out_channels, eps=1e-6, affine=True)
|
||||
if chunk_size is None or chunk_size <= 0:
|
||||
self.conv1 = Conv2d(in_channels, out_channels, kernel_size=3, stride=1, padding=1)
|
||||
self.conv2 = Conv2d(out_channels, out_channels, kernel_size=3, stride=1, padding=1)
|
||||
|
||||
# Skip connection projection for channel dimension mismatch
|
||||
if self.in_channels != self.out_channels:
|
||||
self.nin_shortcut = Conv2d(in_channels, out_channels, kernel_size=1, stride=1, padding=0)
|
||||
else:
|
||||
self.conv1 = ChunkedConv2d(in_channels, out_channels, kernel_size=3, stride=1, padding=1, chunk_size=chunk_size)
|
||||
self.conv2 = ChunkedConv2d(out_channels, out_channels, kernel_size=3, stride=1, padding=1, chunk_size=chunk_size)
|
||||
|
||||
# Skip connection projection for channel dimension mismatch
|
||||
if self.in_channels != self.out_channels:
|
||||
self.nin_shortcut = ChunkedConv2d(
|
||||
in_channels, out_channels, kernel_size=1, stride=1, padding=0, chunk_size=chunk_size
|
||||
)
|
||||
|
||||
def forward(self, x: Tensor) -> Tensor:
|
||||
h = x
|
||||
# First convolution block
|
||||
h = self.norm1(h)
|
||||
h = swish(h)
|
||||
h = self.conv1(h)
|
||||
# Second convolution block
|
||||
h = self.norm2(h)
|
||||
h = swish(h)
|
||||
h = self.conv2(h)
|
||||
|
||||
# Apply skip connection with optional projection
|
||||
if self.in_channels != self.out_channels:
|
||||
x = self.nin_shortcut(x)
|
||||
return x + h
|
||||
|
||||
|
||||
class Downsample(nn.Module):
|
||||
"""
|
||||
Spatial downsampling block that reduces resolution by 2x using convolution followed by
|
||||
pixel rearrangement. Includes skip connection with grouped averaging.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
in_channels : int
|
||||
Number of input channels.
|
||||
out_channels : int
|
||||
Number of output channels (must be divisible by 4).
|
||||
"""
|
||||
|
||||
def __init__(self, in_channels: int, out_channels: int, chunk_size: Optional[int] = None):
|
||||
super().__init__()
|
||||
factor = 4 # 2x2 spatial reduction factor
|
||||
assert out_channels % factor == 0
|
||||
|
||||
if chunk_size is None or chunk_size <= 0:
|
||||
self.conv = Conv2d(in_channels, out_channels // factor, kernel_size=3, stride=1, padding=1)
|
||||
else:
|
||||
self.conv = ChunkedConv2d(
|
||||
in_channels, out_channels // factor, kernel_size=3, stride=1, padding=1, chunk_size=chunk_size
|
||||
)
|
||||
self.group_size = factor * in_channels // out_channels
|
||||
|
||||
def forward(self, x: Tensor) -> Tensor:
|
||||
# Apply convolution and rearrange pixels for 2x downsampling
|
||||
h = self.conv(x)
|
||||
h = rearrange(h, "b c (h r1) (w r2) -> b (r1 r2 c) h w", r1=2, r2=2)
|
||||
|
||||
# Create skip connection with pixel rearrangement
|
||||
shortcut = rearrange(x, "b c (h r1) (w r2) -> b (r1 r2 c) h w", r1=2, r2=2)
|
||||
B, C, H, W = shortcut.shape
|
||||
shortcut = shortcut.view(B, h.shape[1], self.group_size, H, W).mean(dim=2)
|
||||
|
||||
return h + shortcut
|
||||
|
||||
|
||||
class Upsample(nn.Module):
|
||||
"""
|
||||
Spatial upsampling block that increases resolution by 2x using convolution followed by
|
||||
pixel rearrangement. Includes skip connection with channel repetition.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
in_channels : int
|
||||
Number of input channels.
|
||||
out_channels : int
|
||||
Number of output channels.
|
||||
"""
|
||||
|
||||
def __init__(self, in_channels: int, out_channels: int, chunk_size: Optional[int] = None):
|
||||
super().__init__()
|
||||
factor = 4 # 2x2 spatial expansion factor
|
||||
|
||||
if chunk_size is None or chunk_size <= 0:
|
||||
self.conv = Conv2d(in_channels, out_channels * factor, kernel_size=3, stride=1, padding=1)
|
||||
else:
|
||||
self.conv = ChunkedConv2d(in_channels, out_channels * factor, kernel_size=3, stride=1, padding=1, chunk_size=chunk_size)
|
||||
|
||||
self.repeats = factor * out_channels // in_channels
|
||||
|
||||
def forward(self, x: Tensor) -> Tensor:
|
||||
# Apply convolution and rearrange pixels for 2x upsampling
|
||||
h = self.conv(x)
|
||||
h = rearrange(h, "b (r1 r2 c) h w -> b c (h r1) (w r2)", r1=2, r2=2)
|
||||
|
||||
# Create skip connection with channel repetition
|
||||
shortcut = x.repeat_interleave(repeats=self.repeats, dim=1)
|
||||
shortcut = rearrange(shortcut, "b (r1 r2 c) h w -> b c (h r1) (w r2)", r1=2, r2=2)
|
||||
|
||||
return h + shortcut
|
||||
|
||||
|
||||
class Encoder(nn.Module):
|
||||
"""
|
||||
VAE encoder that progressively downsamples input images to a latent representation.
|
||||
Uses residual blocks, attention, and spatial downsampling.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
in_channels : int
|
||||
Number of input image channels (e.g., 3 for RGB).
|
||||
z_channels : int
|
||||
Number of latent channels in the output.
|
||||
block_out_channels : Tuple[int, ...]
|
||||
Output channels for each downsampling block.
|
||||
num_res_blocks : int
|
||||
Number of residual blocks per downsampling stage.
|
||||
ffactor_spatial : int
|
||||
Total spatial downsampling factor (e.g., 32 for 32x compression).
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
in_channels: int,
|
||||
z_channels: int,
|
||||
block_out_channels: Tuple[int, ...],
|
||||
num_res_blocks: int,
|
||||
ffactor_spatial: int,
|
||||
chunk_size: Optional[int] = None,
|
||||
):
|
||||
super().__init__()
|
||||
assert block_out_channels[-1] % (2 * z_channels) == 0
|
||||
|
||||
self.z_channels = z_channels
|
||||
self.block_out_channels = block_out_channels
|
||||
self.num_res_blocks = num_res_blocks
|
||||
|
||||
if chunk_size is None or chunk_size <= 0:
|
||||
self.conv_in = Conv2d(in_channels, block_out_channels[0], kernel_size=3, stride=1, padding=1)
|
||||
else:
|
||||
self.conv_in = ChunkedConv2d(
|
||||
in_channels, block_out_channels[0], kernel_size=3, stride=1, padding=1, chunk_size=chunk_size
|
||||
)
|
||||
|
||||
self.down = nn.ModuleList()
|
||||
block_in = block_out_channels[0]
|
||||
|
||||
# Build downsampling blocks
|
||||
for i_level, ch in enumerate(block_out_channels):
|
||||
block = nn.ModuleList()
|
||||
block_out = ch
|
||||
|
||||
# Add residual blocks for this level
|
||||
for _ in range(self.num_res_blocks):
|
||||
block.append(ResnetBlock(in_channels=block_in, out_channels=block_out, chunk_size=chunk_size))
|
||||
block_in = block_out
|
||||
|
||||
down = nn.Module()
|
||||
down.block = block
|
||||
|
||||
# Add spatial downsampling if needed
|
||||
add_spatial_downsample = bool(i_level < np.log2(ffactor_spatial))
|
||||
if add_spatial_downsample:
|
||||
assert i_level < len(block_out_channels) - 1
|
||||
block_out = block_out_channels[i_level + 1]
|
||||
down.downsample = Downsample(block_in, block_out, chunk_size=chunk_size)
|
||||
block_in = block_out
|
||||
|
||||
self.down.append(down)
|
||||
|
||||
# Middle blocks with attention
|
||||
self.mid = nn.Module()
|
||||
self.mid.block_1 = ResnetBlock(in_channels=block_in, out_channels=block_in, chunk_size=chunk_size)
|
||||
self.mid.attn_1 = AttnBlock(block_in, chunk_size=chunk_size)
|
||||
self.mid.block_2 = ResnetBlock(in_channels=block_in, out_channels=block_in, chunk_size=chunk_size)
|
||||
|
||||
# Output layers
|
||||
self.norm_out = nn.GroupNorm(num_groups=32, num_channels=block_in, eps=1e-6, affine=True)
|
||||
if chunk_size is None or chunk_size <= 0:
|
||||
self.conv_out = Conv2d(block_in, 2 * z_channels, kernel_size=3, stride=1, padding=1)
|
||||
else:
|
||||
self.conv_out = ChunkedConv2d(block_in, 2 * z_channels, kernel_size=3, stride=1, padding=1, chunk_size=chunk_size)
|
||||
|
||||
def forward(self, x: Tensor) -> Tensor:
|
||||
# Initial convolution
|
||||
h = self.conv_in(x)
|
||||
|
||||
# Progressive downsampling through blocks
|
||||
for i_level in range(len(self.block_out_channels)):
|
||||
# Apply residual blocks at this level
|
||||
for i_block in range(self.num_res_blocks):
|
||||
h = self.down[i_level].block[i_block](h)
|
||||
# Apply spatial downsampling if available
|
||||
if hasattr(self.down[i_level], "downsample"):
|
||||
h = self.down[i_level].downsample(h)
|
||||
|
||||
# Middle processing with attention
|
||||
h = self.mid.block_1(h)
|
||||
h = self.mid.attn_1(h)
|
||||
h = self.mid.block_2(h)
|
||||
|
||||
# Final output layers with skip connection
|
||||
group_size = self.block_out_channels[-1] // (2 * self.z_channels)
|
||||
shortcut = rearrange(h, "b (c r) h w -> b c r h w", r=group_size).mean(dim=2)
|
||||
h = self.norm_out(h)
|
||||
h = swish(h)
|
||||
h = self.conv_out(h)
|
||||
h += shortcut
|
||||
return h
|
||||
|
||||
|
||||
class Decoder(nn.Module):
|
||||
"""
|
||||
VAE decoder that progressively upsamples latent representations back to images.
|
||||
Uses residual blocks, attention, and spatial upsampling.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
z_channels : int
|
||||
Number of latent channels in the input.
|
||||
out_channels : int
|
||||
Number of output image channels (e.g., 3 for RGB).
|
||||
block_out_channels : Tuple[int, ...]
|
||||
Output channels for each upsampling block.
|
||||
num_res_blocks : int
|
||||
Number of residual blocks per upsampling stage.
|
||||
ffactor_spatial : int
|
||||
Total spatial upsampling factor (e.g., 32 for 32x expansion).
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
z_channels: int,
|
||||
out_channels: int,
|
||||
block_out_channels: Tuple[int, ...],
|
||||
num_res_blocks: int,
|
||||
ffactor_spatial: int,
|
||||
chunk_size: Optional[int] = None,
|
||||
):
|
||||
super().__init__()
|
||||
assert block_out_channels[0] % z_channels == 0
|
||||
|
||||
self.z_channels = z_channels
|
||||
self.block_out_channels = block_out_channels
|
||||
self.num_res_blocks = num_res_blocks
|
||||
|
||||
block_in = block_out_channels[0]
|
||||
if chunk_size is None or chunk_size <= 0:
|
||||
self.conv_in = Conv2d(z_channels, block_in, kernel_size=3, stride=1, padding=1)
|
||||
else:
|
||||
self.conv_in = ChunkedConv2d(z_channels, block_in, kernel_size=3, stride=1, padding=1, chunk_size=chunk_size)
|
||||
|
||||
# Middle blocks with attention
|
||||
self.mid = nn.Module()
|
||||
self.mid.block_1 = ResnetBlock(in_channels=block_in, out_channels=block_in, chunk_size=chunk_size)
|
||||
self.mid.attn_1 = AttnBlock(block_in, chunk_size=chunk_size)
|
||||
self.mid.block_2 = ResnetBlock(in_channels=block_in, out_channels=block_in, chunk_size=chunk_size)
|
||||
|
||||
# Build upsampling blocks
|
||||
self.up = nn.ModuleList()
|
||||
for i_level, ch in enumerate(block_out_channels):
|
||||
block = nn.ModuleList()
|
||||
block_out = ch
|
||||
|
||||
# Add residual blocks for this level (extra block for decoder)
|
||||
for _ in range(self.num_res_blocks + 1):
|
||||
block.append(ResnetBlock(in_channels=block_in, out_channels=block_out, chunk_size=chunk_size))
|
||||
block_in = block_out
|
||||
|
||||
up = nn.Module()
|
||||
up.block = block
|
||||
|
||||
# Add spatial upsampling if needed
|
||||
add_spatial_upsample = bool(i_level < np.log2(ffactor_spatial))
|
||||
if add_spatial_upsample:
|
||||
assert i_level < len(block_out_channels) - 1
|
||||
block_out = block_out_channels[i_level + 1]
|
||||
up.upsample = Upsample(block_in, block_out, chunk_size=chunk_size)
|
||||
block_in = block_out
|
||||
|
||||
self.up.append(up)
|
||||
|
||||
# Output layers
|
||||
self.norm_out = nn.GroupNorm(num_groups=32, num_channels=block_in, eps=1e-6, affine=True)
|
||||
if chunk_size is None or chunk_size <= 0:
|
||||
self.conv_out = Conv2d(block_in, out_channels, kernel_size=3, stride=1, padding=1)
|
||||
else:
|
||||
self.conv_out = ChunkedConv2d(block_in, out_channels, kernel_size=3, stride=1, padding=1, chunk_size=chunk_size)
|
||||
|
||||
def forward(self, z: Tensor) -> Tensor:
|
||||
# Initial processing with skip connection
|
||||
repeats = self.block_out_channels[0] // self.z_channels
|
||||
h = self.conv_in(z) + z.repeat_interleave(repeats=repeats, dim=1)
|
||||
|
||||
# Middle processing with attention
|
||||
h = self.mid.block_1(h)
|
||||
h = self.mid.attn_1(h)
|
||||
h = self.mid.block_2(h)
|
||||
|
||||
# Progressive upsampling through blocks
|
||||
for i_level in range(len(self.block_out_channels)):
|
||||
# Apply residual blocks at this level
|
||||
for i_block in range(self.num_res_blocks + 1):
|
||||
h = self.up[i_level].block[i_block](h)
|
||||
# Apply spatial upsampling if available
|
||||
if hasattr(self.up[i_level], "upsample"):
|
||||
h = self.up[i_level].upsample(h)
|
||||
|
||||
# Final output layers
|
||||
h = self.norm_out(h)
|
||||
h = swish(h)
|
||||
h = self.conv_out(h)
|
||||
return h
|
||||
|
||||
|
||||
class HunyuanVAE2D(nn.Module):
|
||||
"""
|
||||
VAE model for Hunyuan Image-2.1 with spatial tiling support.
|
||||
|
||||
This VAE uses a fixed architecture optimized for the Hunyuan Image-2.1 model,
|
||||
with 32x spatial compression and optional memory-efficient tiling for large images.
|
||||
"""
|
||||
|
||||
def __init__(self, chunk_size: Optional[int] = None):
|
||||
super().__init__()
|
||||
|
||||
# Fixed configuration for Hunyuan Image-2.1
|
||||
block_out_channels = (128, 256, 512, 512, 1024, 1024)
|
||||
in_channels = 3 # RGB input
|
||||
out_channels = 3 # RGB output
|
||||
latent_channels = 64
|
||||
layers_per_block = 2
|
||||
ffactor_spatial = 32 # 32x spatial compression
|
||||
sample_size = 384 # Minimum sample size for tiling
|
||||
scaling_factor = LATENT_SCALING_FACTOR # 0.75289 # Latent scaling factor
|
||||
|
||||
self.ffactor_spatial = ffactor_spatial
|
||||
self.scaling_factor = scaling_factor
|
||||
|
||||
self.encoder = Encoder(
|
||||
in_channels=in_channels,
|
||||
z_channels=latent_channels,
|
||||
block_out_channels=block_out_channels,
|
||||
num_res_blocks=layers_per_block,
|
||||
ffactor_spatial=ffactor_spatial,
|
||||
chunk_size=chunk_size,
|
||||
)
|
||||
|
||||
self.decoder = Decoder(
|
||||
z_channels=latent_channels,
|
||||
out_channels=out_channels,
|
||||
block_out_channels=list(reversed(block_out_channels)),
|
||||
num_res_blocks=layers_per_block,
|
||||
ffactor_spatial=ffactor_spatial,
|
||||
chunk_size=chunk_size,
|
||||
)
|
||||
|
||||
# Spatial tiling configuration for memory efficiency
|
||||
self.use_spatial_tiling = False
|
||||
self.tile_sample_min_size = sample_size
|
||||
self.tile_latent_min_size = sample_size // ffactor_spatial
|
||||
self.tile_overlap_factor = 0.25 # 25% overlap between tiles
|
||||
|
||||
@property
|
||||
def dtype(self):
|
||||
"""Get the data type of the model parameters."""
|
||||
return next(self.encoder.parameters()).dtype
|
||||
|
||||
@property
|
||||
def device(self):
|
||||
"""Get the device of the model parameters."""
|
||||
return next(self.encoder.parameters()).device
|
||||
|
||||
def enable_spatial_tiling(self, use_tiling: bool = True):
|
||||
"""Enable or disable spatial tiling."""
|
||||
self.use_spatial_tiling = use_tiling
|
||||
|
||||
def disable_spatial_tiling(self):
|
||||
"""Disable spatial tiling."""
|
||||
self.use_spatial_tiling = False
|
||||
|
||||
def enable_tiling(self, use_tiling: bool = True):
|
||||
"""Enable or disable spatial tiling (alias for enable_spatial_tiling)."""
|
||||
self.enable_spatial_tiling(use_tiling)
|
||||
|
||||
def disable_tiling(self):
|
||||
"""Disable spatial tiling (alias for disable_spatial_tiling)."""
|
||||
self.disable_spatial_tiling()
|
||||
|
||||
def blend_h(self, a: torch.Tensor, b: torch.Tensor, blend_extent: int) -> torch.Tensor:
|
||||
"""
|
||||
Blend two tensors horizontally with smooth transition.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
a : torch.Tensor
|
||||
Left tensor.
|
||||
b : torch.Tensor
|
||||
Right tensor.
|
||||
blend_extent : int
|
||||
Number of columns to blend.
|
||||
"""
|
||||
blend_extent = min(a.shape[-1], b.shape[-1], blend_extent)
|
||||
for x in range(blend_extent):
|
||||
b[:, :, :, x] = a[:, :, :, -blend_extent + x] * (1 - x / blend_extent) + b[:, :, :, x] * (x / blend_extent)
|
||||
return b
|
||||
|
||||
def blend_v(self, a: torch.Tensor, b: torch.Tensor, blend_extent: int) -> torch.Tensor:
|
||||
"""
|
||||
Blend two tensors vertically with smooth transition.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
a : torch.Tensor
|
||||
Top tensor.
|
||||
b : torch.Tensor
|
||||
Bottom tensor.
|
||||
blend_extent : int
|
||||
Number of rows to blend.
|
||||
"""
|
||||
blend_extent = min(a.shape[-2], b.shape[-2], blend_extent)
|
||||
for y in range(blend_extent):
|
||||
b[:, :, y, :] = a[:, :, -blend_extent + y, :] * (1 - y / blend_extent) + b[:, :, y, :] * (y / blend_extent)
|
||||
return b
|
||||
|
||||
def spatial_tiled_encode(self, x: torch.Tensor) -> torch.Tensor:
|
||||
"""
|
||||
Encode large images using spatial tiling to reduce memory usage.
|
||||
Tiles are processed independently and blended at boundaries.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
x : torch.Tensor
|
||||
Input tensor of shape (B, C, T, H, W) or (B, C, H, W).
|
||||
"""
|
||||
# Handle 5D input (B, C, T, H, W) by removing time dimension
|
||||
original_ndim = x.ndim
|
||||
if original_ndim == 5:
|
||||
x = x.squeeze(2)
|
||||
|
||||
B, C, H, W = x.shape
|
||||
overlap_size = int(self.tile_sample_min_size * (1 - self.tile_overlap_factor))
|
||||
blend_extent = int(self.tile_latent_min_size * self.tile_overlap_factor)
|
||||
row_limit = self.tile_latent_min_size - blend_extent
|
||||
|
||||
rows = []
|
||||
for i in range(0, H, overlap_size):
|
||||
row = []
|
||||
for j in range(0, W, overlap_size):
|
||||
tile = x[:, :, i : i + self.tile_sample_min_size, j : j + self.tile_sample_min_size]
|
||||
tile = self.encoder(tile)
|
||||
row.append(tile)
|
||||
rows.append(row)
|
||||
|
||||
result_rows = []
|
||||
for i, row in enumerate(rows):
|
||||
result_row = []
|
||||
for j, tile in enumerate(row):
|
||||
if i > 0:
|
||||
tile = self.blend_v(rows[i - 1][j], tile, blend_extent)
|
||||
if j > 0:
|
||||
tile = self.blend_h(row[j - 1], tile, blend_extent)
|
||||
result_row.append(tile[:, :, :row_limit, :row_limit])
|
||||
result_rows.append(torch.cat(result_row, dim=-1))
|
||||
|
||||
moments = torch.cat(result_rows, dim=-2)
|
||||
return moments
|
||||
|
||||
def spatial_tiled_decode(self, z: torch.Tensor) -> torch.Tensor:
|
||||
"""
|
||||
Decode large latents using spatial tiling to reduce memory usage.
|
||||
Tiles are processed independently and blended at boundaries.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
z : torch.Tensor
|
||||
Latent tensor of shape (B, C, H, W).
|
||||
"""
|
||||
B, C, H, W = z.shape
|
||||
overlap_size = int(self.tile_latent_min_size * (1 - self.tile_overlap_factor))
|
||||
blend_extent = int(self.tile_sample_min_size * self.tile_overlap_factor)
|
||||
row_limit = self.tile_sample_min_size - blend_extent
|
||||
|
||||
rows = []
|
||||
for i in range(0, H, overlap_size):
|
||||
row = []
|
||||
for j in range(0, W, overlap_size):
|
||||
tile = z[:, :, :, i : i + self.tile_latent_min_size, j : j + self.tile_latent_min_size]
|
||||
decoded = self.decoder(tile)
|
||||
row.append(decoded)
|
||||
rows.append(row)
|
||||
|
||||
result_rows = []
|
||||
for i, row in enumerate(rows):
|
||||
result_row = []
|
||||
for j, tile in enumerate(row):
|
||||
if i > 0:
|
||||
tile = self.blend_v(rows[i - 1][j], tile, blend_extent)
|
||||
if j > 0:
|
||||
tile = self.blend_h(row[j - 1], tile, blend_extent)
|
||||
result_row.append(tile[:, :, :, :row_limit, :row_limit])
|
||||
result_rows.append(torch.cat(result_row, dim=-1))
|
||||
|
||||
dec = torch.cat(result_rows, dim=-2)
|
||||
return dec
|
||||
|
||||
def encode(self, x: Tensor) -> DiagonalGaussianDistribution:
|
||||
"""
|
||||
Encode input images to latent representation.
|
||||
Uses spatial tiling for large images if enabled.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
x : Tensor
|
||||
Input image tensor of shape (B, C, H, W) or (B, C, T, H, W).
|
||||
|
||||
Returns
|
||||
-------
|
||||
DiagonalGaussianDistribution
|
||||
Latent distribution with mean and logvar.
|
||||
"""
|
||||
# Handle 5D input (B, C, T, H, W) by removing time dimension
|
||||
original_ndim = x.ndim
|
||||
if original_ndim == 5:
|
||||
x = x.squeeze(2)
|
||||
|
||||
# Use tiling for large images to reduce memory usage
|
||||
if self.use_spatial_tiling and (x.shape[-1] > self.tile_sample_min_size or x.shape[-2] > self.tile_sample_min_size):
|
||||
h = self.spatial_tiled_encode(x)
|
||||
else:
|
||||
h = self.encoder(x)
|
||||
|
||||
# Restore time dimension if input was 5D
|
||||
if original_ndim == 5:
|
||||
h = h.unsqueeze(2)
|
||||
|
||||
posterior = DiagonalGaussianDistribution(h)
|
||||
return posterior
|
||||
|
||||
def decode(self, z: Tensor):
|
||||
"""
|
||||
Decode latent representation back to images.
|
||||
Uses spatial tiling for large latents if enabled.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
z : Tensor
|
||||
Latent tensor of shape (B, C, H, W) or (B, C, T, H, W).
|
||||
|
||||
Returns
|
||||
-------
|
||||
Tensor
|
||||
Decoded image tensor.
|
||||
"""
|
||||
# Handle 5D input (B, C, T, H, W) by removing time dimension
|
||||
original_ndim = z.ndim
|
||||
if original_ndim == 5:
|
||||
z = z.squeeze(2)
|
||||
|
||||
# Use tiling for large latents to reduce memory usage
|
||||
if self.use_spatial_tiling and (z.shape[-1] > self.tile_latent_min_size or z.shape[-2] > self.tile_latent_min_size):
|
||||
decoded = self.spatial_tiled_decode(z)
|
||||
else:
|
||||
decoded = self.decoder(z)
|
||||
|
||||
# Restore time dimension if input was 5D
|
||||
if original_ndim == 5:
|
||||
decoded = decoded.unsqueeze(2)
|
||||
|
||||
return decoded
|
||||
|
||||
|
||||
def load_vae(vae_path: str, device: torch.device, disable_mmap: bool = False, chunk_size: Optional[int] = None) -> HunyuanVAE2D:
|
||||
logger.info(f"Initializing VAE with chunk_size={chunk_size}")
|
||||
vae = HunyuanVAE2D(chunk_size=chunk_size)
|
||||
|
||||
logger.info(f"Loading VAE from {vae_path}")
|
||||
state_dict = load_safetensors(vae_path, device=device, disable_mmap=disable_mmap)
|
||||
info = vae.load_state_dict(state_dict, strict=True, assign=True)
|
||||
logger.info(f"Loaded VAE: {info}")
|
||||
|
||||
vae.to(device)
|
||||
return vae
|
||||
246
library/lora_utils.py
Normal file
246
library/lora_utils.py
Normal file
@@ -0,0 +1,246 @@
|
||||
import os
|
||||
import re
|
||||
from typing import Dict, List, Optional, Union
|
||||
import torch
|
||||
from tqdm import tqdm
|
||||
from library.device_utils import synchronize_device
|
||||
from library.fp8_optimization_utils import load_safetensors_with_fp8_optimization
|
||||
from library.safetensors_utils import MemoryEfficientSafeOpen
|
||||
from library.utils import setup_logging
|
||||
|
||||
setup_logging()
|
||||
import logging
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def filter_lora_state_dict(
|
||||
weights_sd: Dict[str, torch.Tensor],
|
||||
include_pattern: Optional[str] = None,
|
||||
exclude_pattern: Optional[str] = None,
|
||||
) -> Dict[str, torch.Tensor]:
|
||||
# apply include/exclude patterns
|
||||
original_key_count = len(weights_sd.keys())
|
||||
if include_pattern is not None:
|
||||
regex_include = re.compile(include_pattern)
|
||||
weights_sd = {k: v for k, v in weights_sd.items() if regex_include.search(k)}
|
||||
logger.info(f"Filtered keys with include pattern {include_pattern}: {original_key_count} -> {len(weights_sd.keys())}")
|
||||
|
||||
if exclude_pattern is not None:
|
||||
original_key_count_ex = len(weights_sd.keys())
|
||||
regex_exclude = re.compile(exclude_pattern)
|
||||
weights_sd = {k: v for k, v in weights_sd.items() if not regex_exclude.search(k)}
|
||||
logger.info(f"Filtered keys with exclude pattern {exclude_pattern}: {original_key_count_ex} -> {len(weights_sd.keys())}")
|
||||
|
||||
if len(weights_sd) != original_key_count:
|
||||
remaining_keys = list(set([k.split(".", 1)[0] for k in weights_sd.keys()]))
|
||||
remaining_keys.sort()
|
||||
logger.info(f"Remaining LoRA modules after filtering: {remaining_keys}")
|
||||
if len(weights_sd) == 0:
|
||||
logger.warning("No keys left after filtering.")
|
||||
|
||||
return weights_sd
|
||||
|
||||
|
||||
def load_safetensors_with_lora_and_fp8(
|
||||
model_files: Union[str, List[str]],
|
||||
lora_weights_list: Optional[Dict[str, torch.Tensor]],
|
||||
lora_multipliers: Optional[List[float]],
|
||||
fp8_optimization: bool,
|
||||
calc_device: torch.device,
|
||||
move_to_device: bool = False,
|
||||
dit_weight_dtype: Optional[torch.dtype] = None,
|
||||
target_keys: Optional[List[str]] = None,
|
||||
exclude_keys: Optional[List[str]] = None,
|
||||
) -> dict[str, torch.Tensor]:
|
||||
"""
|
||||
Merge LoRA weights into the state dict of a model with fp8 optimization if needed.
|
||||
|
||||
Args:
|
||||
model_files (Union[str, List[str]]): Path to the model file or list of paths. If the path matches a pattern like `00001-of-00004`, it will load all files with the same prefix.
|
||||
lora_weights_list (Optional[Dict[str, torch.Tensor]]): Dictionary of LoRA weight tensors to load.
|
||||
lora_multipliers (Optional[List[float]]): List of multipliers for LoRA weights.
|
||||
fp8_optimization (bool): Whether to apply FP8 optimization.
|
||||
calc_device (torch.device): Device to calculate on.
|
||||
move_to_device (bool): Whether to move tensors to the calculation device after loading.
|
||||
target_keys (Optional[List[str]]): Keys to target for optimization.
|
||||
exclude_keys (Optional[List[str]]): Keys to exclude from optimization.
|
||||
"""
|
||||
|
||||
# if the file name ends with 00001-of-00004 etc, we need to load the files with the same prefix
|
||||
if isinstance(model_files, str):
|
||||
model_files = [model_files]
|
||||
|
||||
extended_model_files = []
|
||||
for model_file in model_files:
|
||||
basename = os.path.basename(model_file)
|
||||
match = re.match(r"^(.*?)(\d+)-of-(\d+)\.safetensors$", basename)
|
||||
if match:
|
||||
prefix = basename[: match.start(2)]
|
||||
count = int(match.group(3))
|
||||
state_dict = {}
|
||||
for i in range(count):
|
||||
filename = f"{prefix}{i + 1:05d}-of-{count:05d}.safetensors"
|
||||
filepath = os.path.join(os.path.dirname(model_file), filename)
|
||||
if os.path.exists(filepath):
|
||||
extended_model_files.append(filepath)
|
||||
else:
|
||||
raise FileNotFoundError(f"File {filepath} not found")
|
||||
else:
|
||||
extended_model_files.append(model_file)
|
||||
model_files = extended_model_files
|
||||
logger.info(f"Loading model files: {model_files}")
|
||||
|
||||
# load LoRA weights
|
||||
weight_hook = None
|
||||
if lora_weights_list is None or len(lora_weights_list) == 0:
|
||||
lora_weights_list = []
|
||||
lora_multipliers = []
|
||||
list_of_lora_weight_keys = []
|
||||
else:
|
||||
list_of_lora_weight_keys = []
|
||||
for lora_sd in lora_weights_list:
|
||||
lora_weight_keys = set(lora_sd.keys())
|
||||
list_of_lora_weight_keys.append(lora_weight_keys)
|
||||
|
||||
if lora_multipliers is None:
|
||||
lora_multipliers = [1.0] * len(lora_weights_list)
|
||||
while len(lora_multipliers) < len(lora_weights_list):
|
||||
lora_multipliers.append(1.0)
|
||||
if len(lora_multipliers) > len(lora_weights_list):
|
||||
lora_multipliers = lora_multipliers[: len(lora_weights_list)]
|
||||
|
||||
# Merge LoRA weights into the state dict
|
||||
logger.info(f"Merging LoRA weights into state dict. multipliers: {lora_multipliers}")
|
||||
|
||||
# make hook for LoRA merging
|
||||
def weight_hook_func(model_weight_key, model_weight, keep_on_calc_device=False):
|
||||
nonlocal list_of_lora_weight_keys, lora_weights_list, lora_multipliers, calc_device
|
||||
|
||||
if not model_weight_key.endswith(".weight"):
|
||||
return model_weight
|
||||
|
||||
original_device = model_weight.device
|
||||
if original_device != calc_device:
|
||||
model_weight = model_weight.to(calc_device) # to make calculation faster
|
||||
|
||||
for lora_weight_keys, lora_sd, multiplier in zip(list_of_lora_weight_keys, lora_weights_list, lora_multipliers):
|
||||
# check if this weight has LoRA weights
|
||||
lora_name = model_weight_key.rsplit(".", 1)[0] # remove trailing ".weight"
|
||||
lora_name = "lora_unet_" + lora_name.replace(".", "_")
|
||||
down_key = lora_name + ".lora_down.weight"
|
||||
up_key = lora_name + ".lora_up.weight"
|
||||
alpha_key = lora_name + ".alpha"
|
||||
if down_key not in lora_weight_keys or up_key not in lora_weight_keys:
|
||||
continue
|
||||
|
||||
# get LoRA weights
|
||||
down_weight = lora_sd[down_key]
|
||||
up_weight = lora_sd[up_key]
|
||||
|
||||
dim = down_weight.size()[0]
|
||||
alpha = lora_sd.get(alpha_key, dim)
|
||||
scale = alpha / dim
|
||||
|
||||
down_weight = down_weight.to(calc_device)
|
||||
up_weight = up_weight.to(calc_device)
|
||||
|
||||
# W <- W + U * D
|
||||
if len(model_weight.size()) == 2:
|
||||
# linear
|
||||
if len(up_weight.size()) == 4: # use linear projection mismatch
|
||||
up_weight = up_weight.squeeze(3).squeeze(2)
|
||||
down_weight = down_weight.squeeze(3).squeeze(2)
|
||||
model_weight = model_weight + multiplier * (up_weight @ down_weight) * scale
|
||||
elif down_weight.size()[2:4] == (1, 1):
|
||||
# conv2d 1x1
|
||||
model_weight = (
|
||||
model_weight
|
||||
+ multiplier
|
||||
* (up_weight.squeeze(3).squeeze(2) @ down_weight.squeeze(3).squeeze(2)).unsqueeze(2).unsqueeze(3)
|
||||
* scale
|
||||
)
|
||||
else:
|
||||
# conv2d 3x3
|
||||
conved = torch.nn.functional.conv2d(down_weight.permute(1, 0, 2, 3), up_weight).permute(1, 0, 2, 3)
|
||||
# logger.info(conved.size(), weight.size(), module.stride, module.padding)
|
||||
model_weight = model_weight + multiplier * conved * scale
|
||||
|
||||
# remove LoRA keys from set
|
||||
lora_weight_keys.remove(down_key)
|
||||
lora_weight_keys.remove(up_key)
|
||||
if alpha_key in lora_weight_keys:
|
||||
lora_weight_keys.remove(alpha_key)
|
||||
|
||||
if not keep_on_calc_device and original_device != calc_device:
|
||||
model_weight = model_weight.to(original_device) # move back to original device
|
||||
return model_weight
|
||||
|
||||
weight_hook = weight_hook_func
|
||||
|
||||
state_dict = load_safetensors_with_fp8_optimization_and_hook(
|
||||
model_files,
|
||||
fp8_optimization,
|
||||
calc_device,
|
||||
move_to_device,
|
||||
dit_weight_dtype,
|
||||
target_keys,
|
||||
exclude_keys,
|
||||
weight_hook=weight_hook,
|
||||
)
|
||||
|
||||
for lora_weight_keys in list_of_lora_weight_keys:
|
||||
# check if all LoRA keys are used
|
||||
if len(lora_weight_keys) > 0:
|
||||
# if there are still LoRA keys left, it means they are not used in the model
|
||||
# this is a warning, not an error
|
||||
logger.warning(f"Warning: not all LoRA keys are used: {', '.join(lora_weight_keys)}")
|
||||
|
||||
return state_dict
|
||||
|
||||
|
||||
def load_safetensors_with_fp8_optimization_and_hook(
|
||||
model_files: list[str],
|
||||
fp8_optimization: bool,
|
||||
calc_device: torch.device,
|
||||
move_to_device: bool = False,
|
||||
dit_weight_dtype: Optional[torch.dtype] = None,
|
||||
target_keys: Optional[List[str]] = None,
|
||||
exclude_keys: Optional[List[str]] = None,
|
||||
weight_hook: callable = None,
|
||||
) -> dict[str, torch.Tensor]:
|
||||
"""
|
||||
Load state dict from safetensors files and merge LoRA weights into the state dict with fp8 optimization if needed.
|
||||
"""
|
||||
if fp8_optimization:
|
||||
logger.info(
|
||||
f"Loading state dict with FP8 optimization. Dtype of weight: {dit_weight_dtype}, hook enabled: {weight_hook is not None}"
|
||||
)
|
||||
# dit_weight_dtype is not used because we use fp8 optimization
|
||||
state_dict = load_safetensors_with_fp8_optimization(
|
||||
model_files, calc_device, target_keys, exclude_keys, move_to_device=move_to_device, weight_hook=weight_hook
|
||||
)
|
||||
else:
|
||||
logger.info(
|
||||
f"Loading state dict without FP8 optimization. Dtype of weight: {dit_weight_dtype}, hook enabled: {weight_hook is not None}"
|
||||
)
|
||||
state_dict = {}
|
||||
for model_file in model_files:
|
||||
with MemoryEfficientSafeOpen(model_file) as f:
|
||||
for key in tqdm(f.keys(), desc=f"Loading {os.path.basename(model_file)}", leave=False):
|
||||
if weight_hook is None and move_to_device:
|
||||
value = f.get_tensor(key, device=calc_device, dtype=dit_weight_dtype)
|
||||
else:
|
||||
value = f.get_tensor(key) # we cannot directly load to device because get_tensor does non-blocking transfer
|
||||
if weight_hook is not None:
|
||||
value = weight_hook(key, value, keep_on_calc_device=move_to_device)
|
||||
if move_to_device:
|
||||
value = value.to(calc_device, dtype=dit_weight_dtype, non_blocking=True)
|
||||
elif dit_weight_dtype is not None:
|
||||
value = value.to(dit_weight_dtype)
|
||||
|
||||
state_dict[key] = value
|
||||
if move_to_device:
|
||||
synchronize_device(calc_device)
|
||||
|
||||
return state_dict
|
||||
@@ -37,18 +37,16 @@ metadata = {
|
||||
|
||||
BASE_METADATA = {
|
||||
# === MUST ===
|
||||
"modelspec.sai_model_spec": "1.0.1",
|
||||
"modelspec.sai_model_spec": "1.0.1",
|
||||
"modelspec.architecture": None,
|
||||
"modelspec.implementation": None,
|
||||
"modelspec.title": None,
|
||||
"modelspec.resolution": None,
|
||||
|
||||
# === SHOULD ===
|
||||
"modelspec.description": None,
|
||||
"modelspec.author": None,
|
||||
"modelspec.date": None,
|
||||
"modelspec.hash_sha256": None,
|
||||
|
||||
# === CAN===
|
||||
"modelspec.implementation_version": None,
|
||||
"modelspec.license": None,
|
||||
@@ -81,6 +79,8 @@ ARCH_FLUX_1_CHROMA = "chroma" # for Flux Chroma
|
||||
ARCH_FLUX_1_UNKNOWN = "flux-1"
|
||||
ARCH_LUMINA_2 = "lumina-2"
|
||||
ARCH_LUMINA_UNKNOWN = "lumina"
|
||||
ARCH_HUNYUAN_IMAGE_2_1 = "hunyuan-image-2.1"
|
||||
ARCH_HUNYUAN_IMAGE_UNKNOWN = "hunyuan-image"
|
||||
|
||||
ADAPTER_LORA = "lora"
|
||||
ADAPTER_TEXTUAL_INVERSION = "textual-inversion"
|
||||
@@ -91,6 +91,7 @@ IMPL_DIFFUSERS = "diffusers"
|
||||
IMPL_FLUX = "https://github.com/black-forest-labs/flux"
|
||||
IMPL_CHROMA = "https://huggingface.co/lodestones/Chroma"
|
||||
IMPL_LUMINA = "https://github.com/Alpha-VLLM/Lumina-Image-2.0"
|
||||
IMPL_HUNYUAN_IMAGE = "https://github.com/Tencent-Hunyuan/HunyuanImage-2.1"
|
||||
|
||||
PRED_TYPE_EPSILON = "epsilon"
|
||||
PRED_TYPE_V = "v"
|
||||
@@ -102,20 +103,20 @@ class ModelSpecMetadata:
|
||||
ModelSpec 1.0.1 compliant metadata for safetensors models.
|
||||
All fields correspond to modelspec.* keys in the final metadata.
|
||||
"""
|
||||
|
||||
|
||||
# === MUST ===
|
||||
architecture: str
|
||||
implementation: str
|
||||
title: str
|
||||
resolution: str
|
||||
sai_model_spec: str = "1.0.1"
|
||||
|
||||
|
||||
# === SHOULD ===
|
||||
description: str | None = None
|
||||
author: str | None = None
|
||||
date: str | None = None
|
||||
hash_sha256: str | None = None
|
||||
|
||||
|
||||
# === CAN ===
|
||||
implementation_version: str | None = None
|
||||
license: str | None = None
|
||||
@@ -131,14 +132,14 @@ class ModelSpecMetadata:
|
||||
is_negative_embedding: str | None = None
|
||||
unet_dtype: str | None = None
|
||||
vae_dtype: str | None = None
|
||||
|
||||
|
||||
# === Additional metadata ===
|
||||
additional_fields: dict[str, str] = field(default_factory=dict)
|
||||
|
||||
|
||||
def to_metadata_dict(self) -> dict[str, str]:
|
||||
"""Convert dataclass to metadata dictionary with modelspec. prefixes."""
|
||||
metadata = {}
|
||||
|
||||
|
||||
# Add all non-None fields with modelspec prefix
|
||||
for field_name, value in self.__dict__.items():
|
||||
if field_name == "additional_fields":
|
||||
@@ -150,14 +151,14 @@ class ModelSpecMetadata:
|
||||
metadata[f"modelspec.{key}"] = val
|
||||
elif value is not None:
|
||||
metadata[f"modelspec.{field_name}"] = value
|
||||
|
||||
|
||||
return metadata
|
||||
|
||||
|
||||
@classmethod
|
||||
def from_args(cls, args, **kwargs) -> "ModelSpecMetadata":
|
||||
"""Create ModelSpecMetadata from argparse Namespace, extracting metadata_* fields."""
|
||||
metadata_fields = {}
|
||||
|
||||
|
||||
# Extract all metadata_* attributes from args
|
||||
for attr_name in dir(args):
|
||||
if attr_name.startswith("metadata_") and not attr_name.startswith("metadata___"):
|
||||
@@ -166,7 +167,7 @@ class ModelSpecMetadata:
|
||||
# Remove metadata_ prefix
|
||||
field_name = attr_name[9:] # len("metadata_") = 9
|
||||
metadata_fields[field_name] = value
|
||||
|
||||
|
||||
# Handle known standard fields
|
||||
standard_fields = {
|
||||
"author": metadata_fields.pop("author", None),
|
||||
@@ -174,30 +175,25 @@ class ModelSpecMetadata:
|
||||
"license": metadata_fields.pop("license", None),
|
||||
"tags": metadata_fields.pop("tags", None),
|
||||
}
|
||||
|
||||
|
||||
# Remove None values
|
||||
standard_fields = {k: v for k, v in standard_fields.items() if v is not None}
|
||||
|
||||
|
||||
# Merge with kwargs and remaining metadata fields
|
||||
all_fields = {**standard_fields, **kwargs}
|
||||
if metadata_fields:
|
||||
all_fields["additional_fields"] = metadata_fields
|
||||
|
||||
|
||||
return cls(**all_fields)
|
||||
|
||||
|
||||
def determine_architecture(
|
||||
v2: bool,
|
||||
v_parameterization: bool,
|
||||
sdxl: bool,
|
||||
lora: bool,
|
||||
textual_inversion: bool,
|
||||
model_config: dict[str, str] | None = None
|
||||
v2: bool, v_parameterization: bool, sdxl: bool, lora: bool, textual_inversion: bool, model_config: dict[str, str] | None = None
|
||||
) -> str:
|
||||
"""Determine model architecture string from parameters."""
|
||||
|
||||
|
||||
model_config = model_config or {}
|
||||
|
||||
|
||||
if sdxl:
|
||||
arch = ARCH_SD_XL_V1_BASE
|
||||
elif "sd3" in model_config:
|
||||
@@ -218,17 +214,23 @@ def determine_architecture(
|
||||
arch = ARCH_LUMINA_2
|
||||
else:
|
||||
arch = ARCH_LUMINA_UNKNOWN
|
||||
elif "hunyuan_image" in model_config:
|
||||
hunyuan_image_type = model_config["hunyuan_image"]
|
||||
if hunyuan_image_type == "2.1":
|
||||
arch = ARCH_HUNYUAN_IMAGE_2_1
|
||||
else:
|
||||
arch = ARCH_HUNYUAN_IMAGE_UNKNOWN
|
||||
elif v2:
|
||||
arch = ARCH_SD_V2_768_V if v_parameterization else ARCH_SD_V2_512
|
||||
else:
|
||||
arch = ARCH_SD_V1
|
||||
|
||||
|
||||
# Add adapter suffix
|
||||
if lora:
|
||||
arch += f"/{ADAPTER_LORA}"
|
||||
elif textual_inversion:
|
||||
arch += f"/{ADAPTER_TEXTUAL_INVERSION}"
|
||||
|
||||
|
||||
return arch
|
||||
|
||||
|
||||
@@ -237,12 +239,12 @@ def determine_implementation(
|
||||
textual_inversion: bool,
|
||||
sdxl: bool,
|
||||
model_config: dict[str, str] | None = None,
|
||||
is_stable_diffusion_ckpt: bool | None = None
|
||||
is_stable_diffusion_ckpt: bool | None = None,
|
||||
) -> str:
|
||||
"""Determine implementation string from parameters."""
|
||||
|
||||
|
||||
model_config = model_config or {}
|
||||
|
||||
|
||||
if "flux" in model_config:
|
||||
if model_config["flux"] == "chroma":
|
||||
return IMPL_CHROMA
|
||||
@@ -265,16 +267,16 @@ def get_implementation_version() -> str:
|
||||
capture_output=True,
|
||||
text=True,
|
||||
cwd=os.path.dirname(os.path.dirname(__file__)), # Go up to sd-scripts root
|
||||
timeout=5
|
||||
timeout=5,
|
||||
)
|
||||
|
||||
|
||||
if result.returncode == 0:
|
||||
commit_hash = result.stdout.strip()
|
||||
return f"sd-scripts/{commit_hash}"
|
||||
else:
|
||||
logger.warning("Failed to get git commit hash, using fallback")
|
||||
return "sd-scripts/unknown"
|
||||
|
||||
|
||||
except (subprocess.TimeoutExpired, subprocess.SubprocessError, FileNotFoundError) as e:
|
||||
logger.warning(f"Could not determine git commit: {e}")
|
||||
return "sd-scripts/unknown"
|
||||
@@ -284,19 +286,19 @@ def file_to_data_url(file_path: str) -> str:
|
||||
"""Convert a file path to a data URL for embedding in metadata."""
|
||||
if not os.path.exists(file_path):
|
||||
raise FileNotFoundError(f"File not found: {file_path}")
|
||||
|
||||
|
||||
# Get MIME type
|
||||
mime_type, _ = mimetypes.guess_type(file_path)
|
||||
if mime_type is None:
|
||||
# Default to binary if we can't detect
|
||||
mime_type = "application/octet-stream"
|
||||
|
||||
|
||||
# Read file and encode as base64
|
||||
with open(file_path, "rb") as f:
|
||||
file_data = f.read()
|
||||
|
||||
|
||||
encoded_data = base64.b64encode(file_data).decode("ascii")
|
||||
|
||||
|
||||
return f"data:{mime_type};base64,{encoded_data}"
|
||||
|
||||
|
||||
@@ -305,12 +307,12 @@ def determine_resolution(
|
||||
sdxl: bool = False,
|
||||
model_config: dict[str, str] | None = None,
|
||||
v2: bool = False,
|
||||
v_parameterization: bool = False
|
||||
v_parameterization: bool = False,
|
||||
) -> str:
|
||||
"""Determine resolution string from parameters."""
|
||||
|
||||
|
||||
model_config = model_config or {}
|
||||
|
||||
|
||||
if reso is not None:
|
||||
# Handle comma separated string
|
||||
if isinstance(reso, str):
|
||||
@@ -318,21 +320,18 @@ def determine_resolution(
|
||||
# Handle single int
|
||||
if isinstance(reso, int):
|
||||
reso = (reso, reso)
|
||||
# Handle single-element tuple
|
||||
# Handle single-element tuple
|
||||
if len(reso) == 1:
|
||||
reso = (reso[0], reso[0])
|
||||
else:
|
||||
# Determine default resolution based on model type
|
||||
if (sdxl or
|
||||
"sd3" in model_config or
|
||||
"flux" in model_config or
|
||||
"lumina" in model_config):
|
||||
if sdxl or "sd3" in model_config or "flux" in model_config or "lumina" in model_config:
|
||||
reso = (1024, 1024)
|
||||
elif v2 and v_parameterization:
|
||||
reso = (768, 768)
|
||||
else:
|
||||
reso = (512, 512)
|
||||
|
||||
|
||||
return f"{reso[0]}x{reso[1]}"
|
||||
|
||||
|
||||
@@ -388,23 +387,19 @@ def build_metadata_dataclass(
|
||||
) -> ModelSpecMetadata:
|
||||
"""
|
||||
Build ModelSpec 1.0.1 compliant metadata dataclass.
|
||||
|
||||
|
||||
Args:
|
||||
model_config: Dict containing model type info, e.g. {"flux": "dev"}, {"sd3": "large"}
|
||||
optional_metadata: Dict of additional metadata fields to include
|
||||
"""
|
||||
|
||||
|
||||
# Use helper functions for complex logic
|
||||
architecture = determine_architecture(
|
||||
v2, v_parameterization, sdxl, lora, textual_inversion, model_config
|
||||
)
|
||||
architecture = determine_architecture(v2, v_parameterization, sdxl, lora, textual_inversion, model_config)
|
||||
|
||||
if not lora and not textual_inversion and is_stable_diffusion_ckpt is None:
|
||||
is_stable_diffusion_ckpt = True # default is stable diffusion ckpt if not lora and not textual_inversion
|
||||
|
||||
implementation = determine_implementation(
|
||||
lora, textual_inversion, sdxl, model_config, is_stable_diffusion_ckpt
|
||||
)
|
||||
implementation = determine_implementation(lora, textual_inversion, sdxl, model_config, is_stable_diffusion_ckpt)
|
||||
|
||||
if title is None:
|
||||
if lora:
|
||||
@@ -421,9 +416,7 @@ def build_metadata_dataclass(
|
||||
date = datetime.datetime.fromtimestamp(int_ts).isoformat()
|
||||
|
||||
# Use helper function for resolution
|
||||
resolution = determine_resolution(
|
||||
reso, sdxl, model_config, v2, v_parameterization
|
||||
)
|
||||
resolution = determine_resolution(reso, sdxl, model_config, v2, v_parameterization)
|
||||
|
||||
# Handle prediction type - Flux models don't use prediction_type
|
||||
model_config = model_config or {}
|
||||
@@ -488,7 +481,7 @@ def build_metadata_dataclass(
|
||||
prediction_type=prediction_type,
|
||||
timestep_range=timestep_range,
|
||||
encoder_layer=encoder_layer,
|
||||
additional_fields=processed_optional_metadata
|
||||
additional_fields=processed_optional_metadata,
|
||||
)
|
||||
|
||||
return metadata
|
||||
@@ -518,7 +511,7 @@ def build_metadata(
|
||||
"""
|
||||
Build ModelSpec 1.0.1 compliant metadata for safetensors models.
|
||||
Legacy function that returns dict - prefer build_metadata_dataclass for new code.
|
||||
|
||||
|
||||
Args:
|
||||
model_config: Dict containing model type info, e.g. {"flux": "dev"}, {"sd3": "large"}
|
||||
optional_metadata: Dict of additional metadata fields to include
|
||||
@@ -545,7 +538,7 @@ def build_metadata(
|
||||
model_config=model_config,
|
||||
optional_metadata=optional_metadata,
|
||||
)
|
||||
|
||||
|
||||
return metadata_obj.to_metadata_dict()
|
||||
|
||||
|
||||
@@ -581,7 +574,7 @@ def build_merged_from(models: list[str]) -> str:
|
||||
|
||||
def add_model_spec_arguments(parser: argparse.ArgumentParser):
|
||||
"""Add all ModelSpec metadata arguments to the parser."""
|
||||
|
||||
|
||||
parser.add_argument(
|
||||
"--metadata_title",
|
||||
type=str,
|
||||
|
||||
@@ -626,6 +626,7 @@ class LatentsCachingStrategy:
|
||||
for key in npz.files:
|
||||
kwargs[key] = npz[key]
|
||||
|
||||
# TODO float() is needed if vae is in bfloat16. Remove it if vae is float16.
|
||||
kwargs["latents" + key_reso_suffix] = latents_tensor.float().cpu().numpy()
|
||||
kwargs["original_size" + key_reso_suffix] = np.array(original_size)
|
||||
kwargs["crop_ltrb" + key_reso_suffix] = np.array(crop_ltrb)
|
||||
|
||||
218
library/strategy_hunyuan_image.py
Normal file
218
library/strategy_hunyuan_image.py
Normal file
@@ -0,0 +1,218 @@
|
||||
import os
|
||||
from typing import Any, List, Optional, Tuple, Union
|
||||
import torch
|
||||
import numpy as np
|
||||
from transformers import AutoTokenizer, Qwen2Tokenizer
|
||||
|
||||
from library import hunyuan_image_text_encoder, hunyuan_image_vae, train_util
|
||||
from library.strategy_base import LatentsCachingStrategy, TextEncodingStrategy, TokenizeStrategy, TextEncoderOutputsCachingStrategy
|
||||
|
||||
from library.utils import setup_logging
|
||||
|
||||
setup_logging()
|
||||
import logging
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class HunyuanImageTokenizeStrategy(TokenizeStrategy):
|
||||
def __init__(self, tokenizer_cache_dir: Optional[str] = None) -> None:
|
||||
self.vlm_tokenizer = self._load_tokenizer(
|
||||
Qwen2Tokenizer, hunyuan_image_text_encoder.QWEN_2_5_VL_IMAGE_ID, tokenizer_cache_dir=tokenizer_cache_dir
|
||||
)
|
||||
self.byt5_tokenizer = self._load_tokenizer(
|
||||
AutoTokenizer, hunyuan_image_text_encoder.BYT5_TOKENIZER_PATH, subfolder="", tokenizer_cache_dir=tokenizer_cache_dir
|
||||
)
|
||||
|
||||
def tokenize(self, text: Union[str, List[str]]) -> List[torch.Tensor]:
|
||||
text = [text] if isinstance(text, str) else text
|
||||
|
||||
vlm_tokens, vlm_mask = hunyuan_image_text_encoder.get_qwen_tokens(self.vlm_tokenizer, text)
|
||||
|
||||
# byt5_tokens, byt5_mask = hunyuan_image_text_encoder.get_byt5_text_tokens(self.byt5_tokenizer, text)
|
||||
byt5_tokens = []
|
||||
byt5_mask = []
|
||||
for t in text:
|
||||
tokens, mask = hunyuan_image_text_encoder.get_byt5_text_tokens(self.byt5_tokenizer, t)
|
||||
if tokens is None:
|
||||
tokens = torch.zeros((1, 1), dtype=torch.long)
|
||||
mask = torch.zeros((1, 1), dtype=torch.long)
|
||||
byt5_tokens.append(tokens)
|
||||
byt5_mask.append(mask)
|
||||
max_len = max([m.shape[1] for m in byt5_mask])
|
||||
byt5_tokens = torch.cat([torch.nn.functional.pad(t, (0, max_len - t.shape[1]), value=0) for t in byt5_tokens], dim=0)
|
||||
byt5_mask = torch.cat([torch.nn.functional.pad(m, (0, max_len - m.shape[1]), value=0) for m in byt5_mask], dim=0)
|
||||
|
||||
return [vlm_tokens, vlm_mask, byt5_tokens, byt5_mask]
|
||||
|
||||
|
||||
class HunyuanImageTextEncodingStrategy(TextEncodingStrategy):
|
||||
def __init__(self) -> None:
|
||||
pass
|
||||
|
||||
def encode_tokens(
|
||||
self, tokenize_strategy: TokenizeStrategy, models: List[Any], tokens: List[torch.Tensor]
|
||||
) -> List[torch.Tensor]:
|
||||
vlm_tokens, vlm_mask, byt5_tokens, byt5_mask = tokens
|
||||
|
||||
qwen2vlm, byt5 = models
|
||||
|
||||
# autocast and no_grad are handled in hunyuan_image_text_encoder
|
||||
vlm_embed, vlm_mask = hunyuan_image_text_encoder.get_qwen_prompt_embeds_from_tokens(qwen2vlm, vlm_tokens, vlm_mask)
|
||||
|
||||
# ocr_mask, byt5_embed, byt5_mask = hunyuan_image_text_encoder.get_byt5_prompt_embeds_from_tokens(
|
||||
# byt5, byt5_tokens, byt5_mask
|
||||
# )
|
||||
ocr_mask, byt5_embed, byt5_updated_mask = [], [], []
|
||||
for i in range(byt5_tokens.shape[0]):
|
||||
ocr_m, byt5_e, byt5_m = hunyuan_image_text_encoder.get_byt5_prompt_embeds_from_tokens(
|
||||
byt5, byt5_tokens[i : i + 1], byt5_mask[i : i + 1]
|
||||
)
|
||||
ocr_mask.append(torch.zeros((1,), dtype=torch.long) + (1 if ocr_m[0] else 0)) # 1 or 0
|
||||
byt5_embed.append(byt5_e)
|
||||
byt5_updated_mask.append(byt5_m)
|
||||
|
||||
ocr_mask = torch.cat(ocr_mask, dim=0).to(torch.bool) # [B]
|
||||
byt5_embed = torch.cat(byt5_embed, dim=0)
|
||||
byt5_updated_mask = torch.cat(byt5_updated_mask, dim=0)
|
||||
|
||||
return [vlm_embed, vlm_mask, byt5_embed, byt5_updated_mask, ocr_mask]
|
||||
|
||||
|
||||
class HunyuanImageTextEncoderOutputsCachingStrategy(TextEncoderOutputsCachingStrategy):
|
||||
HUNYUAN_IMAGE_TEXT_ENCODER_OUTPUTS_NPZ_SUFFIX = "_hi_te.npz"
|
||||
|
||||
def __init__(
|
||||
self, cache_to_disk: bool, batch_size: int, skip_disk_cache_validity_check: bool, is_partial: bool = False
|
||||
) -> None:
|
||||
super().__init__(cache_to_disk, batch_size, skip_disk_cache_validity_check, is_partial)
|
||||
|
||||
def get_outputs_npz_path(self, image_abs_path: str) -> str:
|
||||
return (
|
||||
os.path.splitext(image_abs_path)[0]
|
||||
+ HunyuanImageTextEncoderOutputsCachingStrategy.HUNYUAN_IMAGE_TEXT_ENCODER_OUTPUTS_NPZ_SUFFIX
|
||||
)
|
||||
|
||||
def is_disk_cached_outputs_expected(self, npz_path: str):
|
||||
if not self.cache_to_disk:
|
||||
return False
|
||||
if not os.path.exists(npz_path):
|
||||
return False
|
||||
if self.skip_disk_cache_validity_check:
|
||||
return True
|
||||
|
||||
try:
|
||||
npz = np.load(npz_path)
|
||||
if "vlm_embed" not in npz:
|
||||
return False
|
||||
if "vlm_mask" not in npz:
|
||||
return False
|
||||
if "byt5_embed" not in npz:
|
||||
return False
|
||||
if "byt5_mask" not in npz:
|
||||
return False
|
||||
if "ocr_mask" not in npz:
|
||||
return False
|
||||
except Exception as e:
|
||||
logger.error(f"Error loading file: {npz_path}")
|
||||
raise e
|
||||
|
||||
return True
|
||||
|
||||
def load_outputs_npz(self, npz_path: str) -> List[np.ndarray]:
|
||||
data = np.load(npz_path)
|
||||
vln_embed = data["vlm_embed"]
|
||||
vlm_mask = data["vlm_mask"]
|
||||
byt5_embed = data["byt5_embed"]
|
||||
byt5_mask = data["byt5_mask"]
|
||||
ocr_mask = data["ocr_mask"]
|
||||
return [vln_embed, vlm_mask, byt5_embed, byt5_mask, ocr_mask]
|
||||
|
||||
def cache_batch_outputs(
|
||||
self, tokenize_strategy: TokenizeStrategy, models: List[Any], text_encoding_strategy: TextEncodingStrategy, infos: List
|
||||
):
|
||||
huyuan_image_text_encoding_strategy: HunyuanImageTextEncodingStrategy = text_encoding_strategy
|
||||
captions = [info.caption for info in infos]
|
||||
|
||||
tokens_and_masks = tokenize_strategy.tokenize(captions)
|
||||
with torch.no_grad():
|
||||
vlm_embed, vlm_mask, byt5_embed, byt5_mask, ocr_mask = huyuan_image_text_encoding_strategy.encode_tokens(
|
||||
tokenize_strategy, models, tokens_and_masks
|
||||
)
|
||||
|
||||
if vlm_embed.dtype == torch.bfloat16:
|
||||
vlm_embed = vlm_embed.float()
|
||||
if byt5_embed.dtype == torch.bfloat16:
|
||||
byt5_embed = byt5_embed.float()
|
||||
|
||||
vlm_embed = vlm_embed.cpu().numpy()
|
||||
vlm_mask = vlm_mask.cpu().numpy()
|
||||
byt5_embed = byt5_embed.cpu().numpy()
|
||||
byt5_mask = byt5_mask.cpu().numpy()
|
||||
ocr_mask = ocr_mask.cpu().numpy()
|
||||
|
||||
for i, info in enumerate(infos):
|
||||
vlm_embed_i = vlm_embed[i]
|
||||
vlm_mask_i = vlm_mask[i]
|
||||
byt5_embed_i = byt5_embed[i]
|
||||
byt5_mask_i = byt5_mask[i]
|
||||
ocr_mask_i = ocr_mask[i]
|
||||
|
||||
if self.cache_to_disk:
|
||||
np.savez(
|
||||
info.text_encoder_outputs_npz,
|
||||
vlm_embed=vlm_embed_i,
|
||||
vlm_mask=vlm_mask_i,
|
||||
byt5_embed=byt5_embed_i,
|
||||
byt5_mask=byt5_mask_i,
|
||||
ocr_mask=ocr_mask_i,
|
||||
)
|
||||
else:
|
||||
info.text_encoder_outputs = (vlm_embed_i, vlm_mask_i, byt5_embed_i, byt5_mask_i, ocr_mask_i)
|
||||
|
||||
|
||||
class HunyuanImageLatentsCachingStrategy(LatentsCachingStrategy):
|
||||
HUNYUAN_IMAGE_LATENTS_NPZ_SUFFIX = "_hi.npz"
|
||||
|
||||
def __init__(self, cache_to_disk: bool, batch_size: int, skip_disk_cache_validity_check: bool) -> None:
|
||||
super().__init__(cache_to_disk, batch_size, skip_disk_cache_validity_check)
|
||||
|
||||
@property
|
||||
def cache_suffix(self) -> str:
|
||||
return HunyuanImageLatentsCachingStrategy.HUNYUAN_IMAGE_LATENTS_NPZ_SUFFIX
|
||||
|
||||
def get_latents_npz_path(self, absolute_path: str, image_size: Tuple[int, int]) -> str:
|
||||
return (
|
||||
os.path.splitext(absolute_path)[0]
|
||||
+ f"_{image_size[0]:04d}x{image_size[1]:04d}"
|
||||
+ HunyuanImageLatentsCachingStrategy.HUNYUAN_IMAGE_LATENTS_NPZ_SUFFIX
|
||||
)
|
||||
|
||||
def is_disk_cached_latents_expected(self, bucket_reso: Tuple[int, int], npz_path: str, flip_aug: bool, alpha_mask: bool):
|
||||
return self._default_is_disk_cached_latents_expected(32, bucket_reso, npz_path, flip_aug, alpha_mask, multi_resolution=True)
|
||||
|
||||
def load_latents_from_disk(
|
||||
self, npz_path: str, bucket_reso: Tuple[int, int]
|
||||
) -> Tuple[Optional[np.ndarray], Optional[List[int]], Optional[List[int]], Optional[np.ndarray], Optional[np.ndarray]]:
|
||||
return self._default_load_latents_from_disk(32, npz_path, bucket_reso) # support multi-resolution
|
||||
|
||||
# TODO remove circular dependency for ImageInfo
|
||||
def cache_batch_latents(
|
||||
self, vae: hunyuan_image_vae.HunyuanVAE2D, image_infos: List, flip_aug: bool, alpha_mask: bool, random_crop: bool
|
||||
):
|
||||
# encode_by_vae = lambda img_tensor: vae.encode(img_tensor).sample()
|
||||
def encode_by_vae(img_tensor):
|
||||
# no_grad is handled in _default_cache_batch_latents
|
||||
nonlocal vae
|
||||
with torch.autocast(device_type=vae.device.type, dtype=vae.dtype):
|
||||
return vae.encode(img_tensor).sample()
|
||||
|
||||
vae_device = vae.device
|
||||
vae_dtype = vae.dtype
|
||||
|
||||
self._default_cache_batch_latents(
|
||||
encode_by_vae, vae_device, vae_dtype, image_infos, flip_aug, alpha_mask, random_crop, multi_resolution=True
|
||||
)
|
||||
|
||||
if not train_util.HIGH_VRAM:
|
||||
train_util.clean_memory_on_device(vae.device)
|
||||
@@ -1744,7 +1744,39 @@ class BaseDataset(torch.utils.data.Dataset):
|
||||
# [[clip_l, clip_g, t5xxl], [clip_l, clip_g, t5xxl], ...] -> [torch.stack(clip_l), torch.stack(clip_g), torch.stack(t5xxl)]
|
||||
if len(tensors_list) == 0 or tensors_list[0] == None or len(tensors_list[0]) == 0 or tensors_list[0][0] is None:
|
||||
return None
|
||||
return [torch.stack([converter(x[i]) for x in tensors_list]) for i in range(len(tensors_list[0]))]
|
||||
|
||||
# old implementation without padding: all elements must have same length
|
||||
# return [torch.stack([converter(x[i]) for x in tensors_list]) for i in range(len(tensors_list[0]))]
|
||||
|
||||
# new implementation with padding support
|
||||
result = []
|
||||
for i in range(len(tensors_list[0])):
|
||||
tensors = [x[i] for x in tensors_list]
|
||||
if tensors[0].ndim == 0:
|
||||
# scalar value: e.g. ocr mask
|
||||
result.append(torch.stack([converter(x[i]) for x in tensors_list]))
|
||||
continue
|
||||
|
||||
min_len = min([len(x) for x in tensors])
|
||||
max_len = max([len(x) for x in tensors])
|
||||
|
||||
if min_len == max_len:
|
||||
# no padding
|
||||
result.append(torch.stack([converter(x) for x in tensors]))
|
||||
else:
|
||||
# padding
|
||||
tensors = [converter(x) for x in tensors]
|
||||
if tensors[0].ndim == 1:
|
||||
# input_ids or mask
|
||||
result.append(
|
||||
torch.stack([(torch.nn.functional.pad(x, (0, max_len - x.shape[0]))) for x in tensors])
|
||||
)
|
||||
else:
|
||||
# text encoder outputs
|
||||
result.append(
|
||||
torch.stack([(torch.nn.functional.pad(x, (0, 0, 0, max_len - x.shape[0]))) for x in tensors])
|
||||
)
|
||||
return result
|
||||
|
||||
# set example
|
||||
example = {}
|
||||
@@ -3588,6 +3620,7 @@ def get_sai_model_spec_dataclass(
|
||||
sd3: str = None,
|
||||
flux: str = None,
|
||||
lumina: str = None,
|
||||
hunyuan_image: str = None,
|
||||
optional_metadata: dict[str, str] | None = None,
|
||||
) -> sai_model_spec.ModelSpecMetadata:
|
||||
"""
|
||||
@@ -3617,6 +3650,8 @@ def get_sai_model_spec_dataclass(
|
||||
model_config["flux"] = flux
|
||||
if lumina is not None:
|
||||
model_config["lumina"] = lumina
|
||||
if hunyuan_image is not None:
|
||||
model_config["hunyuan_image"] = hunyuan_image
|
||||
|
||||
# Use the dataclass function directly
|
||||
return sai_model_spec.build_metadata_dataclass(
|
||||
@@ -3987,11 +4022,21 @@ def add_training_arguments(parser: argparse.ArgumentParser, support_dreambooth:
|
||||
choices=["no", "fp16", "bf16"],
|
||||
help="use mixed precision / 混合精度を使う場合、その精度",
|
||||
)
|
||||
parser.add_argument("--full_fp16", action="store_true", help="fp16 training including gradients / 勾配も含めてfp16で学習する")
|
||||
parser.add_argument(
|
||||
"--full_bf16", action="store_true", help="bf16 training including gradients / 勾配も含めてbf16で学習する"
|
||||
"--full_fp16",
|
||||
action="store_true",
|
||||
help="fp16 training including gradients, some models are not supported / 勾配も含めてfp16で学習する、一部のモデルではサポートされていません",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--full_bf16",
|
||||
action="store_true",
|
||||
help="bf16 training including gradients, some models are not supported / 勾配も含めてbf16で学習する、一部のモデルではサポートされていません",
|
||||
) # TODO move to SDXL training, because it is not supported by SD1/2
|
||||
parser.add_argument("--fp8_base", action="store_true", help="use fp8 for base model / base modelにfp8を使う")
|
||||
parser.add_argument(
|
||||
"--fp8_base",
|
||||
action="store_true",
|
||||
help="use fp8 for base model, some models are not supported / base modelにfp8を使う、一部のモデルではサポートされていません",
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"--ddp_timeout",
|
||||
@@ -6305,6 +6350,11 @@ def line_to_prompt_dict(line: str) -> dict:
|
||||
prompt_dict["renorm_cfg"] = float(m.group(1))
|
||||
continue
|
||||
|
||||
m = re.match(r"fs (.+)", parg, re.IGNORECASE)
|
||||
if m:
|
||||
prompt_dict["flow_shift"] = m.group(1)
|
||||
continue
|
||||
|
||||
except ValueError as ex:
|
||||
logger.error(f"Exception in parsing / 解析エラー: {parg}")
|
||||
logger.error(ex)
|
||||
|
||||
88
networks/convert_hunyuan_image_lora_to_comfy.py
Normal file
88
networks/convert_hunyuan_image_lora_to_comfy.py
Normal file
@@ -0,0 +1,88 @@
|
||||
import argparse
|
||||
from safetensors.torch import save_file
|
||||
from safetensors import safe_open
|
||||
import torch
|
||||
|
||||
|
||||
from library import train_util
|
||||
from library.utils import setup_logging
|
||||
|
||||
setup_logging()
|
||||
import logging
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def main(args):
|
||||
# load source safetensors
|
||||
logger.info(f"Loading source file {args.src_path}")
|
||||
state_dict = {}
|
||||
with safe_open(args.src_path, framework="pt") as f:
|
||||
metadata = f.metadata()
|
||||
for k in f.keys():
|
||||
state_dict[k] = f.get_tensor(k)
|
||||
|
||||
logger.info(f"Converting...")
|
||||
|
||||
# Key mapping tables: (sd-scripts format, ComfyUI format)
|
||||
double_blocks_mappings = [
|
||||
("img_mlp_fc1", "img_mlp_0"),
|
||||
("img_mlp_fc2", "img_mlp_2"),
|
||||
("img_mod_linear", "img_mod_lin"),
|
||||
("txt_mlp_fc1", "txt_mlp_0"),
|
||||
("txt_mlp_fc2", "txt_mlp_2"),
|
||||
("txt_mod_linear", "txt_mod_lin"),
|
||||
]
|
||||
|
||||
single_blocks_mappings = [
|
||||
("modulation_linear", "modulation_lin"),
|
||||
]
|
||||
|
||||
keys = list(state_dict.keys())
|
||||
count = 0
|
||||
|
||||
for k in keys:
|
||||
new_k = k
|
||||
|
||||
if "double_blocks" in k:
|
||||
mappings = double_blocks_mappings
|
||||
elif "single_blocks" in k:
|
||||
mappings = single_blocks_mappings
|
||||
else:
|
||||
continue
|
||||
|
||||
# Apply mappings based on conversion direction
|
||||
for src_key, dst_key in mappings:
|
||||
if args.reverse:
|
||||
# ComfyUI to sd-scripts: swap src and dst
|
||||
new_k = new_k.replace(dst_key, src_key)
|
||||
else:
|
||||
# sd-scripts to ComfyUI: use as-is
|
||||
new_k = new_k.replace(src_key, dst_key)
|
||||
|
||||
if new_k != k:
|
||||
state_dict[new_k] = state_dict.pop(k)
|
||||
count += 1
|
||||
# print(f"Renamed {k} to {new_k}")
|
||||
|
||||
logger.info(f"Converted {count} keys")
|
||||
|
||||
# Calculate hash
|
||||
if metadata is not None:
|
||||
logger.info(f"Calculating hashes and creating metadata...")
|
||||
model_hash, legacy_hash = train_util.precalculate_safetensors_hashes(state_dict, metadata)
|
||||
metadata["sshs_model_hash"] = model_hash
|
||||
metadata["sshs_legacy_hash"] = legacy_hash
|
||||
|
||||
# save destination safetensors
|
||||
logger.info(f"Saving destination file {args.dst_path}")
|
||||
save_file(state_dict, args.dst_path, metadata=metadata)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser(description="Convert LoRA format")
|
||||
parser.add_argument("src_path", type=str, default=None, help="source path, sd-scripts format")
|
||||
parser.add_argument("dst_path", type=str, default=None, help="destination path, ComfyUI format")
|
||||
parser.add_argument("--reverse", action="store_true", help="reverse conversion direction")
|
||||
args = parser.parse_args()
|
||||
main(args)
|
||||
@@ -10,9 +10,8 @@ import torch
|
||||
from safetensors.torch import load_file, save_file
|
||||
from safetensors import safe_open
|
||||
from tqdm import tqdm
|
||||
from library import flux_utils, sai_model_spec, model_util, sdxl_model_util
|
||||
import lora
|
||||
from library.utils import MemoryEfficientSafeOpen
|
||||
from library import flux_utils, sai_model_spec
|
||||
from library.safetensors_utils import MemoryEfficientSafeOpen
|
||||
from library.utils import setup_logging
|
||||
from networks import lora_flux
|
||||
|
||||
|
||||
@@ -713,6 +713,10 @@ class LoRANetwork(torch.nn.Module):
|
||||
LORA_PREFIX_TEXT_ENCODER_CLIP = "lora_te1"
|
||||
LORA_PREFIX_TEXT_ENCODER_T5 = "lora_te3" # make ComfyUI compatible
|
||||
|
||||
@classmethod
|
||||
def get_qkv_mlp_split_dims(cls) -> List[int]:
|
||||
return [3072] * 3 + [12288]
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
text_encoders: Union[List[CLIPTextModel], CLIPTextModel],
|
||||
@@ -842,7 +846,7 @@ class LoRANetwork(torch.nn.Module):
|
||||
break
|
||||
|
||||
# if modules_dim is None, we use default lora_dim. if modules_dim is not None, we use the specified dim (no default)
|
||||
if dim is None and modules_dim is None:
|
||||
if dim is None and modules_dim is None:
|
||||
if is_linear or is_conv2d_1x1:
|
||||
dim = default_dim if default_dim is not None else self.lora_dim
|
||||
alpha = self.alpha
|
||||
@@ -901,9 +905,9 @@ class LoRANetwork(torch.nn.Module):
|
||||
split_dims = None
|
||||
if is_flux and split_qkv:
|
||||
if "double" in lora_name and "qkv" in lora_name:
|
||||
split_dims = [3072] * 3
|
||||
(split_dims,) = self.get_qkv_mlp_split_dims()[:3] # qkv only
|
||||
elif "single" in lora_name and "linear1" in lora_name:
|
||||
split_dims = [3072] * 3 + [12288]
|
||||
split_dims = self.get_qkv_mlp_split_dims() # qkv + mlp
|
||||
|
||||
lora = module_class(
|
||||
lora_name,
|
||||
@@ -1036,9 +1040,9 @@ class LoRANetwork(torch.nn.Module):
|
||||
# split qkv
|
||||
for key in list(state_dict.keys()):
|
||||
if "double" in key and "qkv" in key:
|
||||
split_dims = [3072] * 3
|
||||
split_dims = self.get_qkv_mlp_split_dims()[:3] # qkv only
|
||||
elif "single" in key and "linear1" in key:
|
||||
split_dims = [3072] * 3 + [12288]
|
||||
split_dims = self.get_qkv_mlp_split_dims() # qkv + mlp
|
||||
else:
|
||||
continue
|
||||
|
||||
@@ -1092,9 +1096,9 @@ class LoRANetwork(torch.nn.Module):
|
||||
new_state_dict = {}
|
||||
for key in list(state_dict.keys()):
|
||||
if "double" in key and "qkv" in key:
|
||||
split_dims = [3072] * 3
|
||||
split_dims = self.get_qkv_mlp_split_dims()[:3] # qkv only
|
||||
elif "single" in key and "linear1" in key:
|
||||
split_dims = [3072] * 3 + [12288]
|
||||
split_dims = self.get_qkv_mlp_split_dims() # qkv + mlp
|
||||
else:
|
||||
new_state_dict[key] = state_dict[key]
|
||||
continue
|
||||
|
||||
378
networks/lora_hunyuan_image.py
Normal file
378
networks/lora_hunyuan_image.py
Normal file
@@ -0,0 +1,378 @@
|
||||
# temporary minimum implementation of LoRA
|
||||
# FLUX doesn't have Conv2d, so we ignore it
|
||||
# TODO commonize with the original implementation
|
||||
|
||||
# LoRA network module
|
||||
# reference:
|
||||
# https://github.com/microsoft/LoRA/blob/main/loralib/layers.py
|
||||
# https://github.com/cloneofsimo/lora/blob/master/lora_diffusion/lora.py
|
||||
|
||||
import os
|
||||
from typing import Dict, List, Optional, Type, Union
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from torch import Tensor
|
||||
import re
|
||||
|
||||
from networks import lora_flux
|
||||
from library.hunyuan_image_vae import HunyuanVAE2D
|
||||
|
||||
from library.utils import setup_logging
|
||||
|
||||
setup_logging()
|
||||
import logging
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
NUM_DOUBLE_BLOCKS = 20
|
||||
NUM_SINGLE_BLOCKS = 40
|
||||
|
||||
|
||||
def create_network(
|
||||
multiplier: float,
|
||||
network_dim: Optional[int],
|
||||
network_alpha: Optional[float],
|
||||
vae: HunyuanVAE2D,
|
||||
text_encoders: List[nn.Module],
|
||||
flux,
|
||||
neuron_dropout: Optional[float] = None,
|
||||
**kwargs,
|
||||
):
|
||||
if network_dim is None:
|
||||
network_dim = 4 # default
|
||||
if network_alpha is None:
|
||||
network_alpha = 1.0
|
||||
|
||||
# extract dim/alpha for conv2d, and block dim
|
||||
conv_dim = kwargs.get("conv_dim", None)
|
||||
conv_alpha = kwargs.get("conv_alpha", None)
|
||||
if conv_dim is not None:
|
||||
conv_dim = int(conv_dim)
|
||||
if conv_alpha is None:
|
||||
conv_alpha = 1.0
|
||||
else:
|
||||
conv_alpha = float(conv_alpha)
|
||||
|
||||
# rank/module dropout
|
||||
rank_dropout = kwargs.get("rank_dropout", None)
|
||||
if rank_dropout is not None:
|
||||
rank_dropout = float(rank_dropout)
|
||||
module_dropout = kwargs.get("module_dropout", None)
|
||||
if module_dropout is not None:
|
||||
module_dropout = float(module_dropout)
|
||||
|
||||
# split qkv
|
||||
split_qkv = kwargs.get("split_qkv", False)
|
||||
if split_qkv is not None:
|
||||
split_qkv = True if split_qkv == "True" else False
|
||||
|
||||
ggpo_beta = kwargs.get("ggpo_beta", None)
|
||||
ggpo_sigma = kwargs.get("ggpo_sigma", None)
|
||||
|
||||
if ggpo_beta is not None:
|
||||
ggpo_beta = float(ggpo_beta)
|
||||
|
||||
if ggpo_sigma is not None:
|
||||
ggpo_sigma = float(ggpo_sigma)
|
||||
|
||||
# verbose
|
||||
verbose = kwargs.get("verbose", False)
|
||||
if verbose is not None:
|
||||
verbose = True if verbose == "True" else False
|
||||
|
||||
# regex-specific learning rates
|
||||
def parse_kv_pairs(kv_pair_str: str, is_int: bool) -> Dict[str, float]:
|
||||
"""
|
||||
Parse a string of key-value pairs separated by commas.
|
||||
"""
|
||||
pairs = {}
|
||||
for pair in kv_pair_str.split(","):
|
||||
pair = pair.strip()
|
||||
if not pair:
|
||||
continue
|
||||
if "=" not in pair:
|
||||
logger.warning(f"Invalid format: {pair}, expected 'key=value'")
|
||||
continue
|
||||
key, value = pair.split("=", 1)
|
||||
key = key.strip()
|
||||
value = value.strip()
|
||||
try:
|
||||
pairs[key] = int(value) if is_int else float(value)
|
||||
except ValueError:
|
||||
logger.warning(f"Invalid value for {key}: {value}")
|
||||
return pairs
|
||||
|
||||
# parse regular expression based learning rates
|
||||
network_reg_lrs = kwargs.get("network_reg_lrs", None)
|
||||
if network_reg_lrs is not None:
|
||||
reg_lrs = parse_kv_pairs(network_reg_lrs, is_int=False)
|
||||
else:
|
||||
reg_lrs = None
|
||||
|
||||
# regex-specific dimensions (ranks)
|
||||
network_reg_dims = kwargs.get("network_reg_dims", None)
|
||||
if network_reg_dims is not None:
|
||||
reg_dims = parse_kv_pairs(network_reg_dims, is_int=True)
|
||||
else:
|
||||
reg_dims = None
|
||||
|
||||
# Too many arguments ( ^ω^)･･･
|
||||
network = HunyuanImageLoRANetwork(
|
||||
text_encoders,
|
||||
flux,
|
||||
multiplier=multiplier,
|
||||
lora_dim=network_dim,
|
||||
alpha=network_alpha,
|
||||
dropout=neuron_dropout,
|
||||
rank_dropout=rank_dropout,
|
||||
module_dropout=module_dropout,
|
||||
conv_lora_dim=conv_dim,
|
||||
conv_alpha=conv_alpha,
|
||||
split_qkv=split_qkv,
|
||||
reg_dims=reg_dims,
|
||||
ggpo_beta=ggpo_beta,
|
||||
ggpo_sigma=ggpo_sigma,
|
||||
reg_lrs=reg_lrs,
|
||||
verbose=verbose,
|
||||
)
|
||||
|
||||
loraplus_lr_ratio = kwargs.get("loraplus_lr_ratio", None)
|
||||
loraplus_unet_lr_ratio = kwargs.get("loraplus_unet_lr_ratio", None)
|
||||
loraplus_text_encoder_lr_ratio = kwargs.get("loraplus_text_encoder_lr_ratio", None)
|
||||
loraplus_lr_ratio = float(loraplus_lr_ratio) if loraplus_lr_ratio is not None else None
|
||||
loraplus_unet_lr_ratio = float(loraplus_unet_lr_ratio) if loraplus_unet_lr_ratio is not None else None
|
||||
loraplus_text_encoder_lr_ratio = float(loraplus_text_encoder_lr_ratio) if loraplus_text_encoder_lr_ratio is not None else None
|
||||
if loraplus_lr_ratio is not None or loraplus_unet_lr_ratio is not None or loraplus_text_encoder_lr_ratio is not None:
|
||||
network.set_loraplus_lr_ratio(loraplus_lr_ratio, loraplus_unet_lr_ratio, loraplus_text_encoder_lr_ratio)
|
||||
|
||||
return network
|
||||
|
||||
|
||||
# Create network from weights for inference, weights are not loaded here (because can be merged)
|
||||
def create_network_from_weights(multiplier, file, ae, text_encoders, flux, weights_sd=None, for_inference=False, **kwargs):
|
||||
if weights_sd is None:
|
||||
if os.path.splitext(file)[1] == ".safetensors":
|
||||
from safetensors.torch import load_file, safe_open
|
||||
|
||||
weights_sd = load_file(file)
|
||||
else:
|
||||
weights_sd = torch.load(file, map_location="cpu")
|
||||
|
||||
# get dim/alpha mapping, and train t5xxl
|
||||
modules_dim = {}
|
||||
modules_alpha = {}
|
||||
for key, value in weights_sd.items():
|
||||
if "." not in key:
|
||||
continue
|
||||
|
||||
lora_name = key.split(".")[0]
|
||||
if "alpha" in key:
|
||||
modules_alpha[lora_name] = value
|
||||
elif "lora_down" in key:
|
||||
dim = value.size()[0]
|
||||
modules_dim[lora_name] = dim
|
||||
# logger.info(lora_name, value.size(), dim)
|
||||
|
||||
split_qkv = False # split_qkv is not needed to care, because state_dict is qkv combined
|
||||
|
||||
module_class = lora_flux.LoRAInfModule if for_inference else lora_flux.LoRAModule
|
||||
|
||||
network = HunyuanImageLoRANetwork(
|
||||
text_encoders,
|
||||
flux,
|
||||
multiplier=multiplier,
|
||||
modules_dim=modules_dim,
|
||||
modules_alpha=modules_alpha,
|
||||
module_class=module_class,
|
||||
split_qkv=split_qkv,
|
||||
)
|
||||
return network, weights_sd
|
||||
|
||||
|
||||
class HunyuanImageLoRANetwork(lora_flux.LoRANetwork):
|
||||
TARGET_REPLACE_MODULE_DOUBLE = ["MMDoubleStreamBlock"]
|
||||
TARGET_REPLACE_MODULE_SINGLE = ["MMSingleStreamBlock"]
|
||||
LORA_PREFIX_HUNYUAN_IMAGE_DIT = "lora_unet" # make ComfyUI compatible
|
||||
|
||||
@classmethod
|
||||
def get_qkv_mlp_split_dims(cls) -> List[int]:
|
||||
return [3584] * 3 + [14336]
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
text_encoders: list[nn.Module],
|
||||
unet,
|
||||
multiplier: float = 1.0,
|
||||
lora_dim: int = 4,
|
||||
alpha: float = 1,
|
||||
dropout: Optional[float] = None,
|
||||
rank_dropout: Optional[float] = None,
|
||||
module_dropout: Optional[float] = None,
|
||||
conv_lora_dim: Optional[int] = None,
|
||||
conv_alpha: Optional[float] = None,
|
||||
module_class: Type[object] = lora_flux.LoRAModule,
|
||||
modules_dim: Optional[Dict[str, int]] = None,
|
||||
modules_alpha: Optional[Dict[str, int]] = None,
|
||||
split_qkv: bool = False,
|
||||
reg_dims: Optional[Dict[str, int]] = None,
|
||||
ggpo_beta: Optional[float] = None,
|
||||
ggpo_sigma: Optional[float] = None,
|
||||
reg_lrs: Optional[Dict[str, float]] = None,
|
||||
verbose: Optional[bool] = False,
|
||||
) -> None:
|
||||
nn.Module.__init__(self)
|
||||
self.multiplier = multiplier
|
||||
|
||||
self.lora_dim = lora_dim
|
||||
self.alpha = alpha
|
||||
self.conv_lora_dim = conv_lora_dim
|
||||
self.conv_alpha = conv_alpha
|
||||
self.dropout = dropout
|
||||
self.rank_dropout = rank_dropout
|
||||
self.module_dropout = module_dropout
|
||||
self.split_qkv = split_qkv
|
||||
self.reg_dims = reg_dims
|
||||
self.reg_lrs = reg_lrs
|
||||
|
||||
self.loraplus_lr_ratio = None
|
||||
self.loraplus_unet_lr_ratio = None
|
||||
self.loraplus_text_encoder_lr_ratio = None
|
||||
|
||||
if modules_dim is not None:
|
||||
logger.info(f"create LoRA network from weights")
|
||||
self.in_dims = [0] * 5 # create in_dims
|
||||
# verbose = True
|
||||
else:
|
||||
logger.info(f"create LoRA network. base dim (rank): {lora_dim}, alpha: {alpha}")
|
||||
logger.info(
|
||||
f"neuron dropout: p={self.dropout}, rank dropout: p={self.rank_dropout}, module dropout: p={self.module_dropout}"
|
||||
)
|
||||
# if self.conv_lora_dim is not None:
|
||||
# logger.info(
|
||||
# f"apply LoRA to Conv2d with kernel size (3,3). dim (rank): {self.conv_lora_dim}, alpha: {self.conv_alpha}"
|
||||
# )
|
||||
|
||||
if ggpo_beta is not None and ggpo_sigma is not None:
|
||||
logger.info(f"LoRA-GGPO training sigma: {ggpo_sigma} beta: {ggpo_beta}")
|
||||
|
||||
if self.split_qkv:
|
||||
logger.info(f"split qkv for LoRA")
|
||||
|
||||
# create module instances
|
||||
def create_modules(
|
||||
is_dit: bool,
|
||||
text_encoder_idx: Optional[int],
|
||||
root_module: torch.nn.Module,
|
||||
target_replace_modules: List[str],
|
||||
filter: Optional[str] = None,
|
||||
default_dim: Optional[int] = None,
|
||||
) -> List[lora_flux.LoRAModule]:
|
||||
assert is_dit, "only DIT is supported now"
|
||||
|
||||
prefix = self.LORA_PREFIX_HUNYUAN_IMAGE_DIT
|
||||
|
||||
loras = []
|
||||
skipped = []
|
||||
for name, module in root_module.named_modules():
|
||||
if target_replace_modules is None or module.__class__.__name__ in target_replace_modules:
|
||||
if target_replace_modules is None: # dirty hack for all modules
|
||||
module = root_module # search all modules
|
||||
|
||||
for child_name, child_module in module.named_modules():
|
||||
is_linear = child_module.__class__.__name__ == "Linear"
|
||||
is_conv2d = child_module.__class__.__name__ == "Conv2d"
|
||||
is_conv2d_1x1 = is_conv2d and child_module.kernel_size == (1, 1)
|
||||
|
||||
if is_linear or is_conv2d:
|
||||
lora_name = prefix + "." + (name + "." if name else "") + child_name
|
||||
lora_name = lora_name.replace(".", "_")
|
||||
|
||||
if filter is not None and not filter in lora_name:
|
||||
continue
|
||||
|
||||
dim = None
|
||||
alpha = None
|
||||
|
||||
if modules_dim is not None:
|
||||
# モジュール指定あり
|
||||
if lora_name in modules_dim:
|
||||
dim = modules_dim[lora_name]
|
||||
alpha = modules_alpha[lora_name]
|
||||
elif self.reg_dims is not None:
|
||||
for reg, d in self.reg_dims.items():
|
||||
if re.search(reg, lora_name):
|
||||
dim = d
|
||||
alpha = self.alpha
|
||||
logger.info(f"LoRA {lora_name} matched with regex {reg}, using dim: {dim}")
|
||||
break
|
||||
|
||||
# if modules_dim is None, we use default lora_dim. if modules_dim is not None, we use the specified dim (no default)
|
||||
if dim is None and modules_dim is None:
|
||||
if is_linear or is_conv2d_1x1:
|
||||
dim = default_dim if default_dim is not None else self.lora_dim
|
||||
alpha = self.alpha
|
||||
elif self.conv_lora_dim is not None:
|
||||
dim = self.conv_lora_dim
|
||||
alpha = self.conv_alpha
|
||||
|
||||
if dim is None or dim == 0:
|
||||
# skipした情報を出力
|
||||
if is_linear or is_conv2d_1x1 or (self.conv_lora_dim is not None):
|
||||
skipped.append(lora_name)
|
||||
continue
|
||||
|
||||
# qkv split
|
||||
split_dims = None
|
||||
if is_dit and split_qkv:
|
||||
if "double" in lora_name and "qkv" in lora_name:
|
||||
split_dims = self.get_qkv_mlp_split_dims()[:3] # qkv only
|
||||
elif "single" in lora_name and "linear1" in lora_name:
|
||||
split_dims = self.get_qkv_mlp_split_dims() # qkv + mlp
|
||||
|
||||
lora = module_class(
|
||||
lora_name,
|
||||
child_module,
|
||||
self.multiplier,
|
||||
dim,
|
||||
alpha,
|
||||
dropout=dropout,
|
||||
rank_dropout=rank_dropout,
|
||||
module_dropout=module_dropout,
|
||||
split_dims=split_dims,
|
||||
ggpo_beta=ggpo_beta,
|
||||
ggpo_sigma=ggpo_sigma,
|
||||
)
|
||||
loras.append(lora)
|
||||
|
||||
if target_replace_modules is None:
|
||||
break # all modules are searched
|
||||
return loras, skipped
|
||||
|
||||
# create LoRA for U-Net
|
||||
target_replace_modules = (
|
||||
HunyuanImageLoRANetwork.TARGET_REPLACE_MODULE_DOUBLE + HunyuanImageLoRANetwork.TARGET_REPLACE_MODULE_SINGLE
|
||||
)
|
||||
|
||||
self.unet_loras: List[Union[lora_flux.LoRAModule, lora_flux.LoRAInfModule]]
|
||||
self.unet_loras, skipped_un = create_modules(True, None, unet, target_replace_modules)
|
||||
self.text_encoder_loras = []
|
||||
|
||||
logger.info(f"create LoRA for HunyuanImage-2.1: {len(self.unet_loras)} modules.")
|
||||
if verbose:
|
||||
for lora in self.unet_loras:
|
||||
logger.info(f"\t{lora.lora_name:50} {lora.lora_dim}, {lora.alpha}")
|
||||
|
||||
skipped = skipped_un
|
||||
if verbose and len(skipped) > 0:
|
||||
logger.warning(
|
||||
f"because dim (rank) is 0, {len(skipped)} LoRA modules are skipped / dim (rank)が0の為、次の{len(skipped)}個のLoRAモジュールはスキップされます:"
|
||||
)
|
||||
for name in skipped:
|
||||
logger.info(f"\t{name}")
|
||||
|
||||
# assertion
|
||||
names = set()
|
||||
for lora in self.text_encoder_loras + self.unet_loras:
|
||||
assert lora.lora_name not in names, f"duplicated lora name: {lora.lora_name}"
|
||||
names.add(lora.lora_name)
|
||||
@@ -1,3 +1,4 @@
|
||||
import gc
|
||||
import importlib
|
||||
import argparse
|
||||
import math
|
||||
@@ -10,11 +11,11 @@ import time
|
||||
import json
|
||||
from multiprocessing import Value
|
||||
import numpy as np
|
||||
import toml
|
||||
|
||||
from tqdm import tqdm
|
||||
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from torch.types import Number
|
||||
from library.device_utils import init_ipex, clean_memory_on_device
|
||||
|
||||
@@ -175,7 +176,7 @@ class NetworkTrainer:
|
||||
if val_dataset_group is not None:
|
||||
val_dataset_group.verify_bucket_reso_steps(64)
|
||||
|
||||
def load_target_model(self, args, weight_dtype, accelerator) -> tuple:
|
||||
def load_target_model(self, args, weight_dtype, accelerator) -> tuple[str, nn.Module, nn.Module, Optional[nn.Module]]:
|
||||
text_encoder, vae, unet, _ = train_util.load_target_model(args, weight_dtype, accelerator)
|
||||
|
||||
# モデルに xformers とか memory efficient attention を組み込む
|
||||
@@ -185,6 +186,9 @@ class NetworkTrainer:
|
||||
|
||||
return model_util.get_model_version_str_for_sd1_sd2(args.v2, args.v_parameterization), text_encoder, vae, unet
|
||||
|
||||
def load_unet_lazily(self, args, weight_dtype, accelerator, text_encoders) -> tuple[nn.Module, List[nn.Module]]:
|
||||
raise NotImplementedError()
|
||||
|
||||
def get_tokenize_strategy(self, args):
|
||||
return strategy_sd.SdTokenizeStrategy(args.v2, args.max_token_length, args.tokenizer_cache_dir)
|
||||
|
||||
@@ -475,6 +479,15 @@ class NetworkTrainer:
|
||||
|
||||
return loss.mean()
|
||||
|
||||
def cast_text_encoder(self, args):
|
||||
return True # default for other than HunyuanImage
|
||||
|
||||
def cast_vae(self, args):
|
||||
return True # default for other than HunyuanImage
|
||||
|
||||
def cast_unet(self, args):
|
||||
return True # default for other than HunyuanImage
|
||||
|
||||
def train(self, args):
|
||||
session_id = random.randint(0, 2**32)
|
||||
training_started_at = time.time()
|
||||
@@ -583,37 +596,18 @@ class NetworkTrainer:
|
||||
|
||||
# mixed precisionに対応した型を用意しておき適宜castする
|
||||
weight_dtype, save_dtype = train_util.prepare_dtype(args)
|
||||
vae_dtype = torch.float32 if args.no_half_vae else weight_dtype
|
||||
vae_dtype = (torch.float32 if args.no_half_vae else weight_dtype) if self.cast_vae(args) else None
|
||||
|
||||
# モデルを読み込む
|
||||
# load target models: unet may be None for lazy loading
|
||||
model_version, text_encoder, vae, unet = self.load_target_model(args, weight_dtype, accelerator)
|
||||
if vae_dtype is None:
|
||||
vae_dtype = vae.dtype
|
||||
logger.info(f"vae_dtype is set to {vae_dtype} by the model since cast_vae() is false")
|
||||
|
||||
# text_encoder is List[CLIPTextModel] or CLIPTextModel
|
||||
text_encoders = text_encoder if isinstance(text_encoder, list) else [text_encoder]
|
||||
|
||||
# 差分追加学習のためにモデルを読み込む
|
||||
sys.path.append(os.path.dirname(__file__))
|
||||
accelerator.print("import network module:", args.network_module)
|
||||
network_module = importlib.import_module(args.network_module)
|
||||
|
||||
if args.base_weights is not None:
|
||||
# base_weights が指定されている場合は、指定された重みを読み込みマージする
|
||||
for i, weight_path in enumerate(args.base_weights):
|
||||
if args.base_weights_multiplier is None or len(args.base_weights_multiplier) <= i:
|
||||
multiplier = 1.0
|
||||
else:
|
||||
multiplier = args.base_weights_multiplier[i]
|
||||
|
||||
accelerator.print(f"merging module: {weight_path} with multiplier {multiplier}")
|
||||
|
||||
module, weights_sd = network_module.create_network_from_weights(
|
||||
multiplier, weight_path, vae, text_encoder, unet, for_inference=True
|
||||
)
|
||||
module.merge_to(text_encoder, unet, weights_sd, weight_dtype, accelerator.device if args.lowram else "cpu")
|
||||
|
||||
accelerator.print(f"all weights merged: {', '.join(args.base_weights)}")
|
||||
|
||||
# 学習を準備する
|
||||
# prepare dataset for latents caching if needed
|
||||
if cache_latents:
|
||||
vae.to(accelerator.device, dtype=vae_dtype)
|
||||
vae.requires_grad_(False)
|
||||
@@ -640,6 +634,32 @@ class NetworkTrainer:
|
||||
if val_dataset_group is not None:
|
||||
self.cache_text_encoder_outputs_if_needed(args, accelerator, unet, vae, text_encoders, val_dataset_group, weight_dtype)
|
||||
|
||||
if unet is None:
|
||||
# lazy load unet if needed. text encoders may be freed or replaced with dummy models for saving memory
|
||||
unet, text_encoders = self.load_unet_lazily(args, weight_dtype, accelerator, text_encoders)
|
||||
|
||||
# 差分追加学習のためにモデルを読み込む
|
||||
sys.path.append(os.path.dirname(__file__))
|
||||
accelerator.print("import network module:", args.network_module)
|
||||
network_module = importlib.import_module(args.network_module)
|
||||
|
||||
if args.base_weights is not None:
|
||||
# base_weights が指定されている場合は、指定された重みを読み込みマージする
|
||||
for i, weight_path in enumerate(args.base_weights):
|
||||
if args.base_weights_multiplier is None or len(args.base_weights_multiplier) <= i:
|
||||
multiplier = 1.0
|
||||
else:
|
||||
multiplier = args.base_weights_multiplier[i]
|
||||
|
||||
accelerator.print(f"merging module: {weight_path} with multiplier {multiplier}")
|
||||
|
||||
module, weights_sd = network_module.create_network_from_weights(
|
||||
multiplier, weight_path, vae, text_encoder, unet, for_inference=True
|
||||
)
|
||||
module.merge_to(text_encoder, unet, weights_sd, weight_dtype, accelerator.device if args.lowram else "cpu")
|
||||
|
||||
accelerator.print(f"all weights merged: {', '.join(args.base_weights)}")
|
||||
|
||||
# prepare network
|
||||
net_kwargs = {}
|
||||
if args.network_args is not None:
|
||||
@@ -669,7 +689,7 @@ class NetworkTrainer:
|
||||
return
|
||||
network_has_multiplier = hasattr(network, "set_multiplier")
|
||||
|
||||
# TODO remove `hasattr`s by setting up methods if not defined in the network like (hacky but works):
|
||||
# TODO remove `hasattr` by setting up methods if not defined in the network like below (hacky but will work):
|
||||
# if not hasattr(network, "prepare_network"):
|
||||
# network.prepare_network = lambda args: None
|
||||
|
||||
@@ -827,12 +847,13 @@ class NetworkTrainer:
|
||||
unet.to(dtype=unet_weight_dtype) # do not move to device because unet is not prepared by accelerator
|
||||
|
||||
unet.requires_grad_(False)
|
||||
unet.to(dtype=unet_weight_dtype)
|
||||
if self.cast_unet(args):
|
||||
unet.to(dtype=unet_weight_dtype)
|
||||
for i, t_enc in enumerate(text_encoders):
|
||||
t_enc.requires_grad_(False)
|
||||
|
||||
# in case of cpu, dtype is already set to fp32 because cpu does not support fp8/fp16/bf16
|
||||
if t_enc.device.type != "cpu":
|
||||
if t_enc.device.type != "cpu" and self.cast_text_encoder(args):
|
||||
t_enc.to(dtype=te_weight_dtype)
|
||||
|
||||
# nn.Embedding not support FP8
|
||||
@@ -858,7 +879,8 @@ class NetworkTrainer:
|
||||
# default implementation is: unet = accelerator.prepare(unet)
|
||||
unet = self.prepare_unet_with_accelerator(args, accelerator, unet) # accelerator does some magic here
|
||||
else:
|
||||
unet.to(accelerator.device, dtype=unet_weight_dtype) # move to device because unet is not prepared by accelerator
|
||||
# move to device because unet is not prepared by accelerator
|
||||
unet.to(accelerator.device, dtype=unet_weight_dtype if self.cast_unet(args) else None)
|
||||
if train_text_encoder:
|
||||
text_encoders = [
|
||||
(accelerator.prepare(t_enc) if flag else t_enc)
|
||||
@@ -1302,6 +1324,8 @@ class NetworkTrainer:
|
||||
del t_enc
|
||||
text_encoders = []
|
||||
text_encoder = None
|
||||
gc.collect()
|
||||
clean_memory_on_device(accelerator.device)
|
||||
|
||||
# For --sample_at_first
|
||||
optimizer_eval_fn()
|
||||
|
||||
Reference in New Issue
Block a user