zituitui/BELM
[NeurIPS 2024] Official implementation of "BELM: Bidirectional Explicit Linear Multi-step Sampler for Exact Inversion in Diffusion Models".
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.
Stars
140
Forks
8
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
xie-lab-ml/Golden-Noise-for-Diffusion-Models
[ICCV2025] The code of our work "Golden Noise for Diffusion Models: A Learning Framework".
yulewang97/ERDiff
[NeurIPS 2023 Spotlight] Official Repo for "Extraction and Recovery of Dpatio-temporal Structure...
UNIC-Lab/RadioDiff
This is the code for the paper "RadioDiff: An Effective Generative Diffusion Model for...
pantheon5100/pid_diffusion
This repository is the official implementation of the paper: Physics Informed Distillation for...
zju-pi/diff-sampler
An open-source toolbox for fast sampling of diffusion models. Official implementations of our...