konpatp/diffae

Official implementation of Diffusion Autoencoders

49
/ 100
Emerging

This project helps graphic designers, artists, and researchers working with digital images to create or modify realistic images. You can input existing images and then generate new variations, manipulate specific features like hair color or expressions, or seamlessly blend images. It's designed for anyone needing to generate diverse image content or alter existing images with fine-grained control.

959 stars. No commits in the last 6 months.

Use this if you need to generate high-quality, realistic images or precisely control the modification of specific features within images, such as facial characteristics or scene elements.

Not ideal if you're looking for a simple, one-click photo editor for casual use or if your primary need is for non-image data generation.

generative-art image-synthesis digital-imaging media-creation visual-effects
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

959

Forks

158

Language

Jupyter Notebook

License

MIT

Last pushed

Sep 12, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/konpatp/diffae"

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