v22.1.0
- 2023/10/10 (v22.1.0)
- Remove support for torch 1 to align with kohya_ss sd-scripts code base.
- Add Intel ARC GPU support with IPEX support on Linux / WSL
- Users needs to set these manually:
- Mixed precision to BF16,
- Attention to SDPA,
- Optimizer to: AdamW (or any other non 8 bit one).
- Run setup with:
./setup.sh --use-ipex
- Run the GUI with:
./gui.sh --use-ipex
- Users needs to set these manually:
- Merging main branch of sd-scripts:
tag_images_by_wd_14_tagger.py
now supports Onnx. If you use Onnx, TensorFlow is not required anymore. #864 Thanks to Isotr0py!--onnx
option is added. If you use Onnx, specify--onnx
option.- Please install Onnx and other required packages.
- Uninstall TensorFlow.
pip install tensorboard==2.14.1
This is required for the specified version of protobuf.pip install protobuf==3.20.3
This is required for Onnx.pip install onnx==1.14.1
pip install onnxruntime-gpu==1.16.0
orpip install onnxruntime==1.16.0
--append_tags
option is added totag_images_by_wd_14_tagger.py
. This option appends the tags to the existing tags, instead of replacing them. #858 Thanks to a-l-e-x-d-s-9!- OFT is now supported.
- You can use
networks.oft
for the network module insdxl_train_network.py
. The usage is the same asnetworks.lora
. Some options are not supported. sdxl_gen_img.py
also supports OFT as--network_module
.- OFT only supports SDXL currently. Because current OFT tweaks Q/K/V and O in the transformer, and SD1/2 have extremely fewer transformers than SDXL.
- The implementation is heavily based on laksjdjf's OFT implementation. Thanks to laksjdjf!
- You can use
- Other bug fixes and improvements.
What's Changed
- "Chinese User.bat and useful readme" by @boombbo in #1564
- Update lora_gui.py by @DevArqSangoi in #1572
- Add IPEX by @Disty0 in #1499
- fix: linting, spelling add international English localisation by @sammcj in #1589
- v22.1.0 by @bmaltais in #1594
New Contributors
Full Changelog: v22.0.1...v22.1.0