D-Ogi/ComfyUI-Attention-Optimizer

Automatically benchmark and optimize attention in diffusion models. 1.5-2x speedup on RTX 4090.

42
/ 100
Emerging

This tool helps artists and designers using ComfyUI to generate images and videos much faster. It automatically tests different underlying technologies for handling image details and selects the quickest one for your specific computer hardware and chosen AI model. You provide your AI model in ComfyUI, and it outputs an optimized version that generates content up to 2-4 times faster, especially for high-resolution images or longer videos.

Use this if you are a digital artist or content creator using ComfyUI for generative AI and want to significantly speed up your image and video creation times without needing to understand complex technical details.

Not ideal if you are not using ComfyUI, or if your primary goal is to save memory rather than pure generation speed.

generative-art ai-imaging video-generation diffusion-models workflow-optimization
No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 11 / 25
Community 14 / 25

How are scores calculated?

Stars

27

Forks

5

Language

Python

License

MIT

Last pushed

Feb 09, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/D-Ogi/ComfyUI-Attention-Optimizer"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.