Files
82dfce256f feat: new tests for nunchaku comfyui from lmxyy & ttio2tech, tested and verified on comfyui 0.3.63 upstream and 0.3.60 LTS (#641) (#650)
* 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>
2025-10-14 00:46:20 -04:00

42 lines
1.1 KiB
ReStructuredText

ComfyUI-nunchaku Documentation
==============================
This is the documentation for https://github.com/nunchaku-tech/ComfyUI-nunchaku.
**Nunchaku** is a high-performance inference engine optimized for low-bit diffusion models and LLMs,
as introduced in our paper `SVDQuant <paper_svdquant_>`_.
Check out `DeepCompressor <github_deepcompressor_>`_ for the quantization library.
.. toctree::
:maxdepth: 1
:caption: Getting Started
get_started/installation.rst
get_started/usage.rst
.. toctree::
:maxdepth: 1
:caption: References
workflows/toc.rst
nodes/toc.rst
api/toc.rst
.. toctree::
:maxdepth: 1
:caption: Useful Links
:titlesonly:
Nunchaku Backend <https://github.com/nunchaku-tech/nunchaku>
Custom Model Quantization: DeepCompressor <https://github.com/nunchaku-tech/deepcompressor>
Frequently Asked Questions (FAQ) <https://nunchaku.tech/docs/nunchaku/faq/faq.html>
.. toctree::
:maxdepth: 1
:caption: Other Resources
developer/contribution_guide.rst
developer/build_docs.rst
developer/docstring.rst
developer/build_comfyui_desktop.rst