https://github.com/nunchaku-tech/ComfyUI-nunchaku
ComfyUI Plugin of Nunchaku
https://github.com/nunchaku-tech/ComfyUI-nunchaku
comfyui diffusion flux genai mlsys quantization
Last synced: about 1 month ago
JSON representation
ComfyUI Plugin of Nunchaku
- Host: GitHub
- URL: https://github.com/nunchaku-tech/ComfyUI-nunchaku
- Owner: nunchaku-tech
- License: apache-2.0
- Created: 2025-03-12T03:10:57.000Z (7 months ago)
- Default Branch: main
- Last Pushed: 2025-08-21T20:43:45.000Z (about 2 months ago)
- Last Synced: 2025-08-21T22:55:25.960Z (about 2 months ago)
- Topics: comfyui, diffusion, flux, genai, mlsys, quantization
- Language: Python
- Homepage: https://nunchaku.tech/docs/ComfyUI-nunchaku/
- Size: 2.79 MB
- Stars: 1,901
- Watchers: 19
- Forks: 66
- Open Issues: 53
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- AiTreasureBox - nunchaku-tech/ComfyUI-nunchaku - 10-08_2318_0](https://img.shields.io/github/stars/nunchaku-tech/ComfyUI-nunchaku.svg)|ComfyUI Plugin of Nunchaku| (Repos)
- awesome-comfyui - **ComfyUI-nunchaku** - training training quantization paradigm for diffusion models, which quantize both the weights and activations of FLUX.1 to 4 bits, achieving 3.5× memory and 8.7× latency reduction on a 16GB laptop 4090 GPU. See more details: https://github.com/mit-han-lab/nunchaku (Workflows (3242) sorted by GitHub Stars)
README
Paper | Docs | Website | Blog | Demo | Hugging Face | ModelScope
English | 中文
This repository provides the ComfyUI plugin for [**Nunchaku**](https://github.com/nunchaku-tech/nunchaku), an efficient inference engine for 4-bit neural networks quantized with [SVDQuant](http://arxiv.org/abs/2411.05007). For the quantization library, check out [DeepCompressor](https://github.com/nunchaku-tech/deepcompressor).
Join our user groups on [**Slack**](https://join.slack.com/t/nunchaku/shared_invite/zt-3170agzoz-NgZzWaTrEj~n2KEV3Hpl5Q), [**Discord**](https://discord.gg/Wk6PnwX9Sm) and [**WeChat**](https://huggingface.co/datasets/nunchaku-tech/cdn/resolve/main/nunchaku/assets/wechat.jpg) for discussions—details [here](https://github.com/nunchaku-tech/nunchaku/issues/149). If you have any questions, run into issues, or are interested in contributing, feel free to share your thoughts with us!
# Nunchaku ComfyUI Plugin
## News
- **[2025-08-23]** 🚀 **v1.0.0** adds support for [Qwen-Image](https://huggingface.co/Qwen/Qwen-Image)! Check [this workflow](example_workflows/nunchaku-qwen-image.json) to get started. LoRA support is coming soon.
- **[2025-07-17]** 📘 The official [**ComfyUI-nunchaku documentation**](https://nunchaku.tech/docs/ComfyUI-nunchaku/) is now live! Explore comprehensive guides and resources to help you get started.
- **[2025-06-29]** 🔥 **v0.3.3** now supports [FLUX.1-Kontext-dev](https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev)! Download the quantized model from [Hugging Face](https://huggingface.co/nunchaku-tech/nunchaku-flux.1-kontext-dev) or [ModelScope](https://modelscope.cn/models/nunchaku-tech/nunchaku-flux.1-kontext-dev) and use this [workflow](./example_workflows/nunchaku-flux.1-kontext-dev.json) to get started.
- **[2025-06-11]** Starting from **v0.3.2**, you can now **easily install or update the [Nunchaku](https://github.com/nunchaku-tech/nunchaku) wheel** using this [workflow](https://github.com/nunchaku-tech/ComfyUI-nunchaku/blob/main/example_workflows/install_wheel.json)!
- **[2025-06-07]** 🚀 **Release Patch v0.3.1!** We bring back **FB Cache** support and fix **4-bit text encoder loading**. PuLID nodes are now optional and won’t interfere with other nodes. We've also added a **NunchakuWheelInstaller** node to help you install the correct [Nunchaku](https://github.com/nunchaku-tech/nunchaku) wheel.
More
- **[2025-06-01]** 🚀 **Release v0.3.0!** This update adds support for multiple-batch inference, [**ControlNet-Union-Pro 2.0**](https://huggingface.co/Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro-2.0) and initial integration of [**PuLID**](https://github.com/ToTheBeginning/PuLID). You can now load Nunchaku FLUX models as a single file, and our upgraded [**4-bit T5 encoder**](https://huggingface.co/nunchaku-tech/nunchaku-t5) now matches **FP8 T5** in quality!
- **[2025-04-16]** 🎥 Released tutorial videos in both [**English**](https://youtu.be/YHAVe-oM7U8?si=cM9zaby_aEHiFXk0) and [**Chinese**](https://www.bilibili.com/video/BV1BTocYjEk5/?share_source=copy_web&vd_source=8926212fef622f25cc95380515ac74ee) to assist installation and usage.
- **[2025-04-09]** 📢 Published the [April roadmap](https://github.com/nunchaku-tech/nunchaku/issues/266) and an [FAQ](https://github.com/nunchaku-tech/nunchaku/discussions/262) to help the community get started and stay up to date with Nunchaku’s development.
- **[2025-04-05]** 🚀 **Release v0.2.0!** This release introduces [**multi-LoRA**](example_workflows/nunchaku-flux.1-dev.json) and [**ControlNet**](example_workflows/nunchaku-flux.1-dev-controlnet-union-pro.json) support, with enhanced performance using FP16 attention and First-Block Cache. We've also added [**20-series GPU**](examples/flux.1-dev-turing.py) compatibility and official workflows for [FLUX.1-redux](example_workflows/nunchaku-flux.1-redux-dev.json)!
## Getting Started
- [Installation Guide](https://nunchaku.tech/docs/ComfyUI-nunchaku/get_started/installation.html)
- [Usage Tutorial](https://nunchaku.tech/docs/ComfyUI-nunchaku/get_started/usage.html)
- [Example Workflows](https://nunchaku.tech/docs/ComfyUI-nunchaku/workflows/toc.html)
- [Node Reference](https://nunchaku.tech/docs/ComfyUI-nunchaku/nodes/toc.html)
- [API Reference](https://nunchaku.tech/docs/ComfyUI-nunchaku/api/toc.html)
- [Custom Model Quantization: DeepCompressor](https://github.com/mit-han-lab/deepcompressor)
- [Contribution Guide](https://nunchaku.tech/docs/ComfyUI-nunchaku/developer/contribution_guide.html)
- [Frequently Asked Questions](https://nunchaku.tech/docs/nunchaku/faq/faq.html)