byeongjun-park/DTR

[ICLR 2024] Official pytorch implementation of "Denoising Task Routing for Diffusion Models"

27
/ 100
Experimental

This project helps machine learning engineers and researchers accelerate the training and improve the quality of their image generation models. It takes an existing diffusion model architecture and optimizes how it handles different denoising steps. The result is faster convergence and higher-quality generated images, without adding new parameters.

No commits in the last 6 months.

Use this if you are working with diffusion models for image generation and want to significantly improve their performance and training speed with minimal effort.

Not ideal if you are looking for a completely new image generation model rather than an optimization for existing diffusion model architectures.

image-generation generative-ai machine-learning-engineering deep-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 4 / 25

How are scores calculated?

Stars

25

Forks

1

Language

Python

License

MIT

Last pushed

Feb 19, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/byeongjun-park/DTR"

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