diegovalsesia/MMD-DDM

Fast Inference in Denoising Diffusion Models via MMD Finetuning

38
/ 100
Emerging

Generating high-quality images or other data samples using advanced AI models (Denoising Diffusion Models) often takes a very long time, requiring many steps. This project helps researchers and practitioners in AI make these models generate samples much faster. It takes an existing, pre-trained diffusion model and fine-tunes it to significantly reduce the number of steps needed to create high-quality outputs, improving the speed-quality trade-off.

No commits in the last 6 months.

Use this if you need to generate high-quality images or other complex data samples quickly using Denoising Diffusion Models and are finding the process too slow.

Not ideal if you are looking for a tool to train a diffusion model from scratch, as this focuses on finetuning existing models for faster inference.

AI-image-generation computational-efficiency generative-modeling machine-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

18

Forks

7

Language

Python

License

MIT

Last pushed

Dec 04, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/diegovalsesia/MMD-DDM"

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