InternScience/AdaptiveDiffusion

[NeurIPS'24] Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy

35
/ 100
Emerging

This project helps anyone working with AI image or video generation models to speed up their creative workflow. It takes an existing diffusion model (like those used for text-to-image or text-to-video) and, without needing new training, produces images or videos significantly faster. This means artists, marketers, or content creators can generate visual assets more quickly.

No commits in the last 6 months.

Use this if you need to accelerate the generation speed of existing diffusion models for images or videos without compromising output quality through retraining.

Not ideal if you are looking for a completely new diffusion model or need to fine-tune existing models with custom datasets.

AI-art-generation content-creation digital-media image-generation video-production
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

73

Forks

6

Language

Python

License

Apache-2.0

Last pushed

Jan 22, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/InternScience/AdaptiveDiffusion"

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