EnVision-Research/DDSM

Denoising Diffusion Step-aware Models (ICLR2024)

27
/ 100
Experimental

This project helps researchers and practitioners in machine learning generate high-quality images more efficiently using diffusion models. It takes an existing diffusion model and optimizes its computational steps. The output is a significantly faster image generation process without compromising the visual quality of the generated images, benefiting anyone who frequently generates images for research or application.

No commits in the last 6 months.

Use this if you need to significantly reduce the computational cost and time of generating images using diffusion models, while maintaining excellent image quality.

Not ideal if you are not working with diffusion models for image generation, or if your primary concern is not computational efficiency.

image-generation machine-learning-research computational-optimization generative-ai
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 3 / 25

How are scores calculated?

Stars

62

Forks

1

Language

Python

License

MIT

Last pushed

Feb 06, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/EnVision-Research/DDSM"

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