* bump requires-python
* model patcher now implements everything it needs for comfyui
* index
* Support LTS and Vanilla ComfyUI
* Fix version string when installed as package (not material)
* style: make linter happy
* update init.py
* Update nunchaku index
* Bump dependencies, include config and workflows when installed using pip/uv
* Update installation instructions to include ComfyUI LTS
* Update requirements for nunchaku>=1.0.1
* Fix torch210 key
* Fix pep 508 spec
* Improve tests (still more to go)
* Fix comfyui_controlnet_aux flaws
* Update tests (all should pass)
* Organize the tests in this runner
* Update contribution guide
* Install uv
* Dependencies now resolve with correct conflicts with uv's most stringent resolution
* Mediapipe hasn't been built for 3.13 yet, so we can't use it here
* Remove controlnet-aux dep
* make linter happy
* make the linter happy
* optimize the loading
* update installation
* update
* update contribution guide
* update qwenimage
* need to figure out why the toml parsing doesn't owk
* update
* update
* update
* style: make linter happy
* update
* add pulid requirement
* update docs
* update
* update
* update
* update
* update
* organize the pyproject.toml
* update
* update
* update
* passing all tests
* update
* update
* update
* update
* update
* remove a useless class
* update
* update
* fix a typo
---------
Co-authored-by: doctorpangloss <@hiddenswitch.com>
Co-authored-by: doctorpangloss <2229300+doctorpangloss@users.noreply.github.com>
* add script for building comfyui desktop with nunchaku
* add readme to the scripty
* style: make linter happy
* update
* add dependencies opencv and insightface
* update rst
* update
* update
* update
* switch to the nunchaku fork
* update
* add a workflow for the build
* update the workflow
* update
* update workflow
* update
* update
* commit
* make linter happy
* do not trigger ci for fork
---------
Co-authored-by: Muyang Li <lmxyy1999@foxmail.com>
* style: make linter happy
* make linter happy
* remove the comments
* update
* update
* update fp8 t5
* ready for test
* update the test score
* update the test score
* update pulid models
* add the deprecation information
* chore: upgrade the diffusers version
* update
* update
* update
* update
* separate a wrapper
* finished the PuLID loader
* new pulid forward
* offload pulid_ca
* update
* runnable now
* add pulid tests
* bump the version to 0.3.2dev2
* update the nunchaku dependencies
* update the pulid model
* debugging the workflow
* debugging the workflow
* debugging the workflow
* debugging the workflow
* debugging the paths
* debugging the paths
* debugging the paths
* debugging the paths
* fix the paths
* better linter
* update deprecation information
* support both model loading
* finished merge models
* update a fill removal workflow
* add legacy test scripts
* add a conversion workflow
* fix the suffix
* update workflows
* download the new models
* start implementing the 4-bit t5
* figuring out how to overwrite
* figuring out how to overwrite
* default workflow is runnable
* my customized loader for work naive clip
* ready to add tests
* ready for tests
* update
* fix the random seed
* fill lora does not work
* update tests
* update tests
* add pyyaml in test dependencies
* fix tests
* fix tests
* adjust the expected psnr
* fix the depth lora lpips
* fix the values
* fix: fix the test ci
* multiple y
* need to install manager
* create folders when downloading models
* fix: fix a typo when downloading test data
* fix the paths
* add more debugging info
* debugging tests
* add the dependencies for PuLID
* add the dependencies for PuLID
* start the tests
* start the tests
* add flux.1-dev test
* chore: finished the first test
* add flux_schnell
* add auto downloading
* wrap up three workflows
* wrap up three workflows
* add three scripts
* fix: fix cn2
* download the cn-upscaler
* add tests for cn upscaler
* add redux script
* finalize all the test scripts
* format the scripts
* format the scripts
* revert the version
* the first test ci
