v21.5.8
版本发布时间: 2023-05-05 19:31:21
bmaltais/kohya_ss最新发布版本:v24.1.7(2024-09-06 19:03:10)
The release contain significant requirements changes. Make sure to re-run setup.bat to re-install all the requirements... especially since bitsandbytes module is replaced and no longer required windows dll patching. The old patches need to be removed by the setup.bat
script for proper execution. Also note that this has been tested only on my system so it may not work as weel as the previous release... so be ready to roll back to the previous release if you run into issues.
If you need to roll back run this code:
git checkout v21.5.7
.\setup.bat
- 2023/04/05 (v21.5.8)
- Add
Cache latents to disk
option to the gui. - When saving v2 models in Diffusers format in training scripts and conversion scripts, it was found that the U-Net configuration is different from those of Hugging Face's stabilityai models (this repository is
"use_linear_projection": false
, stabilityai istrue
). Please note that the weight shapes are different, so please be careful when using the weight files directly. We apologize for the inconvenience.- Since the U-Net model is created based on the configuration, it should not cause any problems in training or inference.
- Added
--unet_use_linear_projection
option toconvert_diffusers20_original_sd.py
script. If you specify this option, you can save a Diffusers format model with the same configuration as stabilityai's model from an SD format model (a single*.safetensors
or*.ckpt
file). Unfortunately, it is not possible to convert a Diffusers format model to the same format.
- Lion8bit optimizer is supported. PR #447 Thanks to sdbds!
- Currently it is optional because you need to update
bitsandbytes
version. See "Optional: Use Lion8bit" in installation instructions to use it.
- Currently it is optional because you need to update
- Multi-GPU training with DDP is supported in each training script. PR #448 Thanks to Isotr0py!
- Multi resolution noise (pyramid noise) is supported in each training script. PR #471 Thanks to pamparamm!
- See PR and this page Multi-Resolution Noise for Diffusion Model Training for details.
- Add --no-cache-dir to reduce image size @chiragjn
- Add