ComfyUI Extension: ComfyUI_StreamDiffusion

Authored by jesenzhang

Created

Updated

155 stars

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

This is a simple implementation StreamDiffusion(A Pipeline-Level Solution for Real-Time Interactive Generation) for ComfyUI

Looking for a different extension?

Custom Nodes (2)

README

ComfyUI_StreamDiffusion

This is a simple implementation StreamDiffusion<a href="https://github.com/cumulo-autumn/StreamDiffusion.git" > for ComfyUI

StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation

Authors: Akio Kodaira, Chenfeng Xu, Toshiki Hazama, Takanori Yoshimoto, Kohei Ohno, Shogo Mitsuhori, Soichi Sugano, Hanying Cho, Zhijian Liu, Kurt Keutzer

StreamDiffusion is an innovative diffusion pipeline designed for real-time interactive generation. It introduces significant performance enhancements to current diffusion-based image generation techniques.

arXiv Hugging Face Papers

Simple Use

you can download the workflow image below , and import into ComfyUI

<p align="center"> <img src="./workflow.png" width=90%> </p>

img2img

img2img can be done by send a image to the image imput in the sampler node,but the batch_size must be 1.

StreamDiffusion_Sampler

Input Latent is not implemented for now.

Lora stack

You can set Lora stack by using LoRA Stacker from Efficiency Nodes.

Support

Thank you for being awesome!

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Learn more