zituitui/LML-diffusion-sampler

[ICCV 2025] Official implementation of "Unleashing High-Quality Image Generation in Diffusion Sampling Using Second-Order Levenberg-Marquardt-Langevin".

37
/ 100
Emerging

This project offers an improved method for generating high-quality images from text descriptions or other inputs using diffusion models. It takes your existing diffusion model (like Stable Diffusion) and applies a sophisticated sampling technique to produce more realistic and detailed images. Image creators, digital artists, and researchers working with generative AI would use this to enhance their visual outputs.

No commits in the last 6 months.

Use this if you are a machine learning practitioner or researcher who wants to get better visual quality from your diffusion models, especially when generating images with Stable Diffusion or other compatible frameworks like diffusers.

Not ideal if you are looking for a completely new image generation model or if you don't already work with diffusion models and their underlying code.

Generative AI Image Synthesis Deep Learning AI Art Computer Vision
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 15 / 25
Community 15 / 25

How are scores calculated?

Stars

13

Forks

4

Language

Python

License

MIT

Last pushed

Sep 02, 2025

Commits (30d)

0

Get this data via API

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

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