Nunchaku v1.0.1

What's Changed

• fix: ksampler error when the tensor is not contiguous #535 by @wallen0322 in #673
• feat: example script for Qwen-Image-Edit by @lmxyy in #679
• feat: add rank calculation in merge_safetensors by @senlyu163 in #663
• feat: support controlnet for qwenimagemodel by @ttio2tech in #681
• feat: sdxl model support by @devgdovg in #674
• chore: add qwen-image tests for v1, clean the requirements by @lmxyy in #712
• feat: support Qwen-Image-Edit-2509 by @lmxyy in #721
• feat: qwen-image-edit-2509 lightning support by @lmxyy in #728
• chore: update the workflows by @lmxyy in #739
• fix: qwen-image-edit-2509 docs and examples by @amchii in #731
• fix: handle output shape when sequence length is padded by pad_tensor by @senlyu163 in #709
• chore: add V1 flux tests by @lmxyy in #742

New Contributors

• @wallen0322 made their first contribution in #673
• @ttio2tech made their first contribution in #681
• @devgdovg made their first contribution in #674
• @amchii made their first contribution in #731

Full Changelog: v1.0.0...v1.0.1

Nunchaku Nightly v1.0.1dev20250930

fix: handle output shape when sequence length is padded by `pad_tenso…

Nunchaku Nightly v1.0.1dev20250929

fix: qwen-image-edit-2509 docs and examples (#731)

* fix: add missing scheduler to qwen-image-edit-2509 lightning example

* docs: add documentation for qwen-image-edit-2509 lightning

* docs: add Distilled Qwen-Image-Edit-2509-Lightning section and fix Hugging Face link refs

  - Add a new "Distilled Qwen-Image-Edit-2509 (Qwen-Image-Edit-2509-Lightning)" section to
    docs/source/usage/qwen-image-edit.rst, referencing
    examples/v1/qwen-image-edit-2509-lightning.py.
  - Fix incorrect reStructuredText named-reference syntax that produced relative links:
    changed occurrences like <hf_qwen-image>/<hf_qwen-image-edit>/<hf_qwen-image-lightning>
    to the correct named-reference form with trailing underscore (e.g. <hf_qwen-image_>).
    This makes those links resolve to the external URLs defined in
    docs/source/links/huggingface.txt instead of becoming relative links.
  - Files modified:
      - docs/source/usage/qwen-image-edit.rst
      - docs/source/usage/qwen-image.rst

* style: make linter happy

* fix the repo

Nunchaku Nightly v1.0.1dev20250926

docs: fix a typo

Nunchaku Nightly v1.0.1dev20250924

docs: update a visualization

Nunchaku Nightly v1.0.1dev20250923

chore: add qwen-image tests for v1, clean the requirements (#712)

* add the v1 tests

* formalize the requirements

* update

* update

* well format the dependency

* update docs

* update

* update

* update the dependency

* fix the version in ci

* well organize the dependency

* update the pr list

* update tests

* add tests for qwen-image

* add qwen-image lightning

* add tests

* update fp4 lpips

* add tests for qwen-image-edit

* update

* updat

* add 8 steps lora back

* update nvfp4 results

* add qwen-image-edit-lightning

* style: make linter happy

* do not use batch when batchsize is 1

* update

* finished all the tests

* add cn test

* style: make linter happy

* update

* add qwen-image controlnet

* update

* add fp4 metrics

* fix the tests

Nunchaku Nightly v1.0.1dev20250921

feat: sdxl model support (#674)

* feat: sdxl model support

* code style auto-modified by pre-commit hook

* refine comments

* add tests and examples for sdxl

* refine sdxl tests code

* make linter happy

* mv the locations of the examples

* move the locations of the tests

* refine tests and examples

* add API documentation for unet_sdxl.py

* usage doc for sdxl

* update docs

* update

* refine pipeline initialization

* refine tests for sdxl/sdxl-turbo

Nunchaku Nightly v1.0.1dev20250920

docs: update README

Nunchaku Nightly v1.0.1dev20250912

What's Changed

• fix: ksampler error when the tensor is not contiguous #535 by @wallen0322 in #673
• feat: example script for Qwen-Image-Edit by @lmxyy in #679
• feat: add rank calculation in merge_safetensors by @senlyu163 in #663

New Contributors

• @wallen0322 made their first contribution in #673

Full Changelog: v1.0.0...v1.0.1dev20250912

Nunchaku v1.0.0

What's Changed

• chore: fix the wheel hf uploading by @lmxyy in #599
• fix: enable correct batch processing in teacache by @Bluear7878 in #601
• chore: bump the version to v1.0.0 by @lmxyy in #602
• feat: pythonized model and QwenImage Support by @lmxyy in #593
• feat: FLUX Gradio demos support FP4 by @lmxyy in #623
• Fix ValueError in NunchakuQwenImagePipeline.prepare_latents unpacking by @ighoshsubho in #616
• feat: support Qwen-Image in ComfyUI-nunchaku by @lmxyy in #632
• feat: support lightning Qwen-Image models by @lmxyy in #641
• feat: Implement V2 FBCaching and Optimize Existing FBCache by @Bluear7878 in #621
• feat: add support for teacache in flux kontext by @BoynChan in #618
• feat: add paddings if LoRA ranks for q, k, v are different by @woct0rdho in #603
• fix: close the NVFP4 performance gap between the Python backend and C backend by @lmxyy in #647
• feat: add support for python 3.13 by @DrZhouKarl in #651
• feat: async CPU offloading for Python backend by @lmxyy in #624
• feat: simplify the implementation of the async offloading and support ComfyUI offloading by @lmxyy in #655
• docs: add the docstrings for v1.0.0 by @lmxyy in #656
• chore: release nunchaku v1.0.0 by @lmxyy in #658

New Contributors

• @ighoshsubho made their first contribution in #616
• @BoynChan made their first contribution in #618
• @woct0rdho made their first contribution in #603
• @DrZhouKarl made their first contribution in #651

Full Changelog: v0.3.2...v1.0.0