Rayhane-mamah/Efficient-VDVAE

Official Pytorch and JAX implementation of "Efficient-VDVAE: Less is more"

43
/ 100
Emerging

This project provides pre-trained models and code for generating realistic images efficiently. It takes datasets of images (like faces, animals, or objects) and produces new, high-quality images that resemble the input data. Researchers and practitioners working in computer vision and generative AI can use these models to create synthetic images for various applications.

199 stars. No commits in the last 6 months.

Use this if you need to generate high-fidelity images from existing datasets using a memory and compute-efficient hierarchical VAE model.

Not ideal if you are looking for a simple, out-of-the-box solution for casual image manipulation or editing, as this targets advanced generative model development.

image-generation computer-vision-research generative-ai synthetic-data-creation deep-learning-models
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

199

Forks

26

Language

Python

License

MIT

Last pushed

Aug 15, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Rayhane-mamah/Efficient-VDVAE"

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