VictorMylle/Kohya-ss-sd-scripts
1
0
Fork 1
mirror of https://github.com/kohya-ss/sd-scripts.git synced 2026-04-08 06:28:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

update README

Browse Source
This commit is contained in:
Kohya S
2024-09-10 21:20:38 +09:00
parent d10ff62a78
commit 65b8a064f6
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@@ -12,7 +12,7 @@ The command to install PyTorch is as follows:
### Recent Updates
Sep 10, 2024:
In FLUX.1 LoRA training, individual learning rates can be specified for CLIP-L and T5XXL. By specifying multiple numbers in `--text_encoder_lr`, you can set the learning rates for CLIP-L and T5XXL separately. Specify like `--text_encoder_lr 1e-4 1e-5`. If you specify only one, the learning rates for CLIP-L and T5XXL will be the same.
In FLUX.1 LoRA training, individual learning rates can be specified for CLIP-L and T5XXL. By specifying multiple numbers in `--text_encoder_lr`, you can set the learning rates for CLIP-L and T5XXL separately. Specify like `--text_encoder_lr 1e-4 1e-5`. The first value is the learning rate for CLIP-L, and the second value is for T5XXL. If you specify only one, the learning rates for CLIP-L and T5XXL will be the same.
Sep 9, 2024:
Added `--negative_prompt` and `--cfg_scale` to `flux_minimal_inference.py`. Negative prompts can be used.
@@ -145,7 +145,7 @@ The effect of `--timestep_sampling sigmoid` and `--sigmoid_scale` (when `--times
- Remove `--network_train_unet_only` from your command.
- Add `train_t5xxl=True` to `--network_args` to train T5XXL LoRA. CLIP-L is also trained at the same time.
- T5XXL output can be cached for CLIP-L LoRA training. So, `--cache_text_encoder_outputs` or `--cache_text_encoder_outputs_to_disk` is also available.
- The learning rates for CLIP-L and T5XXL can be specified separately. Multiple numbers can be specified in `--text_encoder_lr`. For example, `--text_encoder_lr 1e-4 1e-5`. If you specify only one, the learning rates for CLIP-L and T5XXL will be the same. If `--text_encoder_lr` is not specified, the default learning rate `--learning_rate` is used for both CLIP-L and T5XXL.
- The learning rates for CLIP-L and T5XXL can be specified separately. Multiple numbers can be specified in `--text_encoder_lr`. For example, `--text_encoder_lr 1e-4 1e-5`. The first value is the learning rate for CLIP-L, and the second value is for T5XXL. If you specify only one, the learning rates for CLIP-L and T5XXL will be the same. If `--text_encoder_lr` is not specified, the default learning rate `--learning_rate` is used for both CLIP-L and T5XXL.
- The trained LoRA can be used with ComfyUI.
- Note: `flux_extract_lora.py`, `convert_flux_lora.py`and `merge_flux_lora.py` do not support CLIP-L and T5XXL LoRA yet.