* [feat] add nodes for z-image
* updates for fp4 state dict loading
* support lora
* remove unused lora loader
* add doc string & move NunchakuModelPatcher to common.py (avoid package confict)
* test case for z-image-turbo lora
* refine test cases
* downgrade logging
* modify test case metrics
* create example workflow and documentation for z-image-turbo txt-2-img with LoRAs
* create example workflow and documentation for running nunchaku z-image-turbo with official controlnet
* fix file name
* fix file path
* update
* [feat] add nodes for z-image
* updates for fp4 state dict loading
* unit test case for z-image-turbo text-to-image workflow
* update documentation templates for z-image
* minor fix: remove some warnings and invalid attribute access during model loading
* drop down res4lyf test case
* style: make linter happy
* modify test case metrics
* add notes for maintenance
* add github url in notes
* simplify the notes
* try to fix issue #549
* align device with offload option
* offload transformer blocks while not affecting model device
* style: make linter happy
* add test
* style: make linter happy
* no need to redownload the qwen-image files
* style: make linter happy
* resolve missing sub_folder item in yaml
* update
* rename the workflow
* style: make linter happy
* 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>
* update
* add qwen-image models
* override comfyui class for nunchaku
* update
* finished model loading
* style: make linter happy
* update
* start debugging
* style: make linter happy
* fix the init error
* model loading done
* need to figure out why the precision does not match in comfyui
* almost done
* add the example workflow
* style: make linter happy
* add some docs
* runnable on 5090
* leave the docs to tomorrow
* update dependencies
* style: make linter happy
* add the docstring
* update the workflow docs
* use 0.3.44 for tests
* add more api docs
* add the v1.0.0 info
* update requirements
* style: make linter happy
* feat:IP-adapter
* add IP-adpater workflow
* delete wrong example
* start testing ipa
* add tests
* make linter happy
* add a utility function
* add the docs of ipadapter
* style: make linter happy
* update
* chore: fix the github variables
* no need to capture output
* debug the tests
* fix the dependencies versions
* reduce the VRAM usage
* update the test score
---------
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
dengdong