VictorMylle/Kohya-ss-sd-scripts
1
0
Fork 1
mirror of https://github.com/kohya-ss/sd-scripts.git synced 2026-04-09 06:45:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

add README

Browse Source
This commit is contained in:
minux302
2024-11-29 23:55:52 +09:00
parent 9dff44d785
commit 575f583fd9
1 changed files with 17 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
README.md
View File

@@ -28,6 +28,7 @@ Nov 14, 2024:
- [Key Features for FLUX.1 LoRA training](#key-features-for-flux1-lora-training) - [Key Features for FLUX.1 LoRA training](#key-features-for-flux1-lora-training)
- [Specify rank for each layer in FLUX.1](#specify-rank-for-each-layer-in-flux1) - [Specify rank for each layer in FLUX.1](#specify-rank-for-each-layer-in-flux1)
- [Specify blocks to train in FLUX.1 LoRA training](#specify-blocks-to-train-in-flux1-lora-training) - [Specify blocks to train in FLUX.1 LoRA training](#specify-blocks-to-train-in-flux1-lora-training)
- [FLUX.1 ControlNet training](#flux1-controlnet-training)
- [FLUX.1 OFT training](#flux1-oft-training) - [FLUX.1 OFT training](#flux1-oft-training)
- [Inference for FLUX.1 with LoRA model](#inference-for-flux1-with-lora-model) - [Inference for FLUX.1 with LoRA model](#inference-for-flux1-with-lora-model)
- [FLUX.1 fine-tuning](#flux1-fine-tuning) - [FLUX.1 fine-tuning](#flux1-fine-tuning)
@@ -245,6 +246,22 @@ example:
If you specify one of `train_double_block_indices` or `train_single_block_indices`, the other will be trained as usual. If you specify one of `train_double_block_indices` or `train_single_block_indices`, the other will be trained as usual.
### FLUX.1 ControlNet training
We have added a new training script for ControlNet training. The script is flux_train_control_net.py. See --help for options.
Sample command is below. It will work with 80GB VRAM GPUs.
```
accelerate launch --mixed_precision bf16 --num_cpu_threads_per_process 1 flux_train_control_net.py
--pretrained_model_name_or_path flux1-dev.safetensors --clip_l clip_l.safetensors --t5xxl t5xxl_fp16.safetensors
--ae ae.safetensors --save_model_as safetensors --sdpa --persistent_data_loader_workers
--max_data_loader_n_workers 1 --seed 42 --gradient_checkpointing --mixed_precision bf16
--optimizer_type adamw8bit --learning_rate 2e-5
--highvram --max_train_epochs 1 --save_every_n_steps 1000 --dataset_config dataset.toml
--output_dir /path/to/output/dir --output_name flux-cn
--timestep_sampling shift --discrete_flow_shift 3.1582 --model_prediction_type raw --guidance_scale 1.0 --deepspeed
```
### FLUX.1 OFT training ### FLUX.1 OFT training
You can train OFT with almost the same options as LoRA, such as `--timestamp_sampling`. The following points are different. You can train OFT with almost the same options as LoRA, such as `--timestamp_sampling`. The following points are different.