Skip to content

Repository files navigation

ComfyUI-SolAttn

Experimental Triton implementation of Sol-Attn for ComfyUI

Paper Code Project Page


Overview

Sol-Attn is a training-free sparse attention method for accelerating image and video generation. This community extension integrates a Triton implementation of Sol-Attn into ComfyUI.

Note

This project is a work in progress. It has currently been tested on RTX 4090 and RTX 5090 GPUs with MiniMax H3.

Usage notes

Triton kernels are compiled on first use, so the first run will be slower.

Use start_percent, end_percent, and tau to balance generation quality and speed.

Examples

Test output

minimaxattn_00003.mp4

SageAttention vs. Sol-Attn

SageAttention Sol-Attn
minimax_sage.2.mp4
minimax_solattn.mp4
Sol-Attn example result

Citation

If you find Sol-Attn useful in your work, please cite the paper:

@article{li2026solattn,
  title={Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification},
  author={Li, Haopeng and Li, Yitong and Chen, Junsong and Ye, Tian and Liu, Haozhe and Yu, Jincheng and Wang, Duomin and Zhang, Ruihua and Xie, Zeke and Xie, Enze and Han, Song},
  journal={arXiv preprint arXiv:2607.24027},
  year={2026}
}

About

No description, website, or topics provided.

Resources

Stars

155 stars

Watchers

3 watching

Forks

Releases

Packages

Contributors

Languages