VainF/Diff-Pruning

[NeurIPS 2023] Structural Pruning for Diffusion Models

38
/ 100
Emerging

This project helps machine learning engineers and researchers optimize diffusion models for faster image generation and lower computational costs. You input a pre-trained diffusion model and a desired pruning ratio, and it outputs a smaller, more efficient diffusion model that retains high-quality image generation capabilities. This is for professionals working with generative AI who need to deploy models more efficiently.

218 stars. No commits in the last 6 months.

Use this if you need to reduce the computational footprint and inference time of large diffusion models while maintaining their creative output quality.

Not ideal if you are a casual user looking for an out-of-the-box image generation tool without needing to optimize model performance.

generative-AI deep-learning-optimization image-synthesis AI-model-deployment computational-efficiency
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

218

Forks

16

Language

Python

License

Apache-2.0

Last pushed

Jul 08, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/VainF/Diff-Pruning"

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