zituitui/BELM

[NeurIPS 2024] Official implementation of "BELM: Bidirectional Explicit Linear Multi-step Sampler for Exact Inversion in Diffusion Models".

38
/ 100
Emerging

This project offers an improved method for working with Diffusion Models, which are popular for generating and editing images. It ensures that when you generate an image and then try to 'undo' that generation to find its original noise input, the process is perfectly reversible and accurate. This allows graphic designers, artists, or researchers using diffusion models for image manipulation to reliably edit and interpolate images without losing quality or introducing inconsistencies.

140 stars. No commits in the last 6 months.

Use this if you are working with diffusion models for tasks like image editing, interpolation, or any application where maintaining exact reversibility and high image quality across multiple steps is critical.

Not ideal if your primary goal is simple image generation without a strong need for precise, reversible transformations, or if you are not using diffusion models.

image-generation image-editing computational-photography generative-AI digital-art
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

140

Forks

8

Language

Python

License

MIT

Last pushed

Jun 01, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/zituitui/BELM"

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