mit-han-lab/distrifuser

[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models

48
/ 100
Emerging

This project helps artists, designers, and researchers generate very high-resolution images using AI diffusion models like Stable Diffusion XL, but much faster than before. It takes a text prompt and turns it into a detailed, large-format image. This is ideal for anyone needing large, high-quality AI-generated visuals for creative projects or research, especially those who work with multiple GPUs.

724 stars. No commits in the last 6 months. Available on PyPI.

Use this if you need to generate extremely large and detailed images from text prompts using diffusion models and want to significantly speed up the process by utilizing multiple GPUs.

Not ideal if you are generating small images or only have access to a single GPU, as the benefits of distributed processing won't apply.

AI-art-generation digital-imaging creative-workflow high-resolution-imaging generative-AI
Stale 6m
Maintenance 0 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 13 / 25

How are scores calculated?

Stars

724

Forks

34

Language

Python

License

MIT

Last pushed

Dec 02, 2024

Commits (30d)

0

Dependencies

4

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/mit-han-lab/distrifuser"

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