Extensions/ComfyUI-nunchaku
ComfyUI Extension

ComfyUI-nunchaku

Nunchaku ComfyUI Node. Nunchaku is the inference that supports SVDQuant. SVDQuant is a new post-training training quantization paradigm for diffusion models, which…

By nunchaku-ai·Created about a year ago·Updated 6 months ago· 2,909
nunchaku-tech/ComfyUI-nunchaku
Nodes16
On cloudLocal install
CategoryNunchaku
Stars2,909
Updated6 months ago

Nodes (16)

FLUX Depth Preprocessor (Deprecated)

The deprecated FLUX depth map node

Nunchaku
Nunchaku FLUX DiT Loader

The 4-bit Flux loader that's faster than fp8 or GGUF

Nunchaku
Nunchaku FLUX IP-Adapter Apply

Image-prompt a 4-bit Flux from a reference

Nunchaku
Nunchaku FLUX LoRA Loader

Load a LoRA into a 4-bit Nunchaku Flux model

Nunchaku
Nunchaku FLUX LoRA Stack

Stack up to 15 LoRAs on a 4-bit Flux in one node

Nunchaku
Nunchaku FLUX PuLID Apply V2

Inject a reference face into a 4-bit Flux

Nunchaku
Nunchaku IP-Adapter Loader

Set up IP-Adapter for a 4-bit Nunchaku model

Nunchaku
Nunchaku Model Merger

Reassemble a split Nunchaku model into one file

Nunchaku
Nunchaku Pulid Apply (Deprecated)

The older PuLID face-apply node (use the V2)

Nunchaku
Nunchaku Pulid Loader (Deprecated)

The older PuLID loader (use the V2)

Nunchaku
Nunchaku PuLID Loader V2

Load PuLID face identity onto a 4-bit Flux

Nunchaku
Nunchaku Qwen-Image DiT Loader

Run 20B Qwen-Image in 4-bit on a normal GPU

Nunchaku
Nunchaku Text Encoder Loader (Deprecated)

The older 4-bit T5 loader (use V2 instead)

Nunchaku
Nunchaku Text Encoder Loader V2

Load the 4-bit T5 encoder for Flux

Nunchaku
Nunchaku Installer

The node that installs Nunchaku's actual engine

Nunchaku
Nunchaku Z-Image DiT Loader

Run Z-Image Turbo in 4-bit, even faster

Nunchaku
Readme
<div align="center" id="nunchaku_logo"> <img src="https://huggingface.co/datasets/nunchaku-ai/cdn/resolve/main/logo/v2/nunchaku-compact-transparent.png" alt="logo" width="220"></img> </div> <h3 align="center"> <a href="http://arxiv.org/abs/2411.05007"><b>Paper</b></a> | <a href="https://nunchaku.tech/docs/ComfyUI-nunchaku/"><b>Docs</b></a> | <a href="https://hanlab.mit.edu/projects/svdquant"><b>Website</b></a> | <a href="https://hanlab.mit.edu/blog/svdquant"><b>Blog</b></a> | <a href="https://demo.nunchaku.tech/"><b>Demo</b></a> | <a href="https://huggingface.co/nunchaku-ai"><b>Hugging Face</b></a> | <a href="https://modelscope.cn/organization/nunchaku-tech"><b>ModelScope</b></a> </h3> <div align="center"> <a href="https://trendshift.io/repositories/17711" target="_blank"><img src="https://trendshift.io/api/badge/repositories/17711" alt="nunchaku-ai/nunchaku | Trendshift" style="width: 120px; height: 26px;" width="120" height="26"/></a> <a href=https://discord.gg/Wk6PnwX9Sm target="_blank"><img src=https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fdiscord.com%2Fapi%2Finvites%2FWk6PnwX9Sm%3Fwith_counts%3Dtrue&query=%24.approximate_member_count&logo=discord&logoColor=white&label=Discord&color=green&suffix=%20total height=22px></a> <a href=https://huggingface.co/datasets/nunchaku-ai/cdn/resolve/main/nunchaku/assets/wechat.jpg target="_blank"><img src=https://img.shields.io/badge/WeChat-07C160?logo=wechat&logoColor=white height=22px></a> <a href=https://deepwiki.com/nunchaku-ai/ComfyUI-nunchaku target="_blank"><img src=https://deepwiki.com/badge.svg height=22px></a> </div>

This repository provides the ComfyUI plugin for Nunchaku, an efficient inference engine for 4-bit neural networks quantized with SVDQuant. For the quantization library, check out DeepCompressor.

Join our user groups on Discord and WeChat for discussions—details here. If you have any questions, run into issues, or are interested in contributing, feel free to share your thoughts with us!

Nunchaku ComfyUI Plugin

comfyui

News

  • [2026-01-12] 🚀 v1.2.0 Released! Enjoy a 20–30% Z-Image performance boost, seamless LoRA support with native ComfyUI nodes, and INT4 support for 20-series GPUs!
  • [2025-12-26] 🚀 v1.1.0: Support 4-bit Tongyi-MAI/Z-Image-Turbo! Download on Hugging Face or ModelScope, and try it with this workflow!
  • [2025-09-24] 🔥 Released 4-bit 4/8-step Qwen-Image-Edit-2509 lightning models at Hugging Face! Try them out with this workflow!
  • [2025-09-24] 🔥 Released 4-bit Qwen-Image-Edit-2509! Models are available on Hugging Face. Try them out with this workflow!
  • [2025-09-09] 🔥 Released 4-bit Qwen-Image-Edit together with the 4/8-step Lightning variants! Models are available on Hugging Face. Try them out with this workflow!
<details> <summary>More</summary>
  • [2025-09-04] 🚀 Official release of Nunchaku v1.0.0! Qwen-Image now supports asynchronous offloading, cutting Transformer VRAM usage to as little as 3 GiB with no performance loss. You can also try our pre-quantized 4/8-step Qwen-Image-Lightning models on Hugging Face or ModelScope.
  • [2025-08-23] 🚀 v1.0.0 adds support for Qwen-Image! Check this workflow to get started. LoRA support is coming soon.
  • [2025-07-17] 📘 The official ComfyUI-nunchaku documentation 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! Download the quantized model from Hugging Face or ModelScope and use this workflow to get started.
  • [2025-06-11] Starting from v0.3.2, you can now easily install or update the Nunchaku wheel using this workflow!
  • [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 wheel.
  • [2025-06-01] 🚀 Release v0.3.0! This update adds support for multiple-batch inference, ControlNet-Union-Pro 2.0 and initial integration of PuLID. You can now load Nunchaku FLUX models as a single file, and our upgraded 4-bit T5 encoder now matches FP8 T5 in quality!
  • [2025-04-16] 🎥 Released tutorial videos in both English and Chinese to assist installation and usage.
  • [2025-04-09] 📢 Published the April roadmap and an FAQ 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 and ControlNet support, with enhanced performance using FP16 attention and First-Block Cache. We've also added 20-series GPU compatibility and official workflows for FLUX.1-redux!
</details>

Getting Started

Star History

Star History Chart