sangyun884/fast-ode

Official PyTorch implementation for the paper Minimizing Trajectory Curvature of ODE-based Generative Models, ICML 2023

26
/ 100
Experimental

This project helps machine learning researchers create high-quality images from scratch using generative models more efficiently. It takes datasets of images (like CIFAR-10 or FFHQ) as input, and outputs new, distinct images that resemble the original dataset, but are generated faster than previous methods. This is designed for researchers or practitioners working on advanced image generation tasks who need to optimize model performance and speed.

No commits in the last 6 months.

Use this if you are a machine learning researcher focused on generative models and need to produce synthetic images with reduced sampling time while maintaining image quality.

Not ideal if you are looking for a plug-and-play image generation tool without diving into model training and optimization.

generative-AI image-synthesis deep-learning-research computational-efficiency machine-learning-engineering
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 9 / 25

How are scores calculated?

Stars

91

Forks

6

Language

Python

License

Last pushed

Feb 14, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/sangyun884/fast-ode"

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