nodes/jesenzhang-ComfyUI_StreamDiffusion

T

jesenzhang ceb2baefae Merge pull request #18 from ComfyNodePRs/update-publish-yaml

Update Github Action for Publishing to Comfy Registry

2025-03-18 12:47:23 +08:00

.github/workflows

chore(publish): update GitHub Actions workflow for node publishing

2025-01-20 21:26:11 +00:00

streamdiffusion

Update image_utils.py

2024-11-18 17:03:55 -07:00

__init__.py

init commit

2023-12-29 17:06:07 +08:00

LICENSE

Initial commit

2023-12-29 17:00:03 +08:00

nodes.py

delete

2023-12-29 17:26:23 +08:00

README.md

update

2023-12-29 17:41:46 +08:00

workflow.png

init commit

2023-12-29 17:06:07 +08:00

README.md

ComfyUI_StreamDiffusion

This is a simple implementation StreamDiffusion 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.

Simple Use

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

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!