gudaochangsheng/MaskUnet

[CVPR 2025] Official PyTorch implementation of Not All Parameters Matter: Masking Diffusion Models for Enhancing Generation Ability

32
/ 100
Emerging

This project helps researchers and developers working with image generation models to improve the quality of their generated images. By selectively masking certain parts of the underlying U-Net model, it takes an existing diffusion model (like Stable Diffusion 1.5) and outputs higher-quality images. It's designed for machine learning engineers and researchers focused on computer vision and generative AI.

Use this if you are a machine learning researcher or engineer looking to enhance the output quality of your diffusion models without significantly increasing model complexity.

Not ideal if you are a general user looking for an out-of-the-box image generation tool without diving into model architecture or training/inference scripts.

generative-ai image-synthesis diffusion-models computer-vision deep-learning-research
No License No Package No Dependents
Maintenance 13 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 4 / 25

How are scores calculated?

Stars

32

Forks

1

Language

Python

License

Last pushed

Mar 18, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/gudaochangsheng/MaskUnet"

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