AlexMaOLS/EluCD

Elucidating The Design Space of Classifier-Guided Diffusion Generation

27
/ 100
Experimental

This project helps researchers and developers working with image generation models to achieve higher quality results. It takes existing diffusion models like DDPM or EDM, along with readily available pre-trained image classifiers (e.g., ResNet), and combines them to produce more accurate and visually coherent images conditioned on specific categories. The primary users are machine learning researchers and practitioners focused on generative AI for image synthesis.

No commits in the last 6 months.

Use this if you are generating conditional images using diffusion models and want to improve the fidelity and relevance of the generated output by leveraging off-the-shelf image classifiers.

Not ideal if you are looking for a general-purpose image generation tool without needing to integrate specific classifier guidance, or if you are not working with established diffusion model architectures.

generative-ai image-synthesis diffusion-models computer-vision 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

33

Forks

1

Language

Python

License

MIT

Last pushed

Jan 20, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/AlexMaOLS/EluCD"

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