jolibrain/joliGEN

Generative AI Image and Video Toolset with GANs and Diffusion for Real-World Applications

57
/ 100
Established

Implements semantic-preserving image-to-image translation across GANs, diffusion, and consistency models with customizable discriminators (projected, vision-aided, transformer-based) and generators (ResNet, ViT, UNet, HDiT) that maintain bounding boxes, masks, and class labels during transformation. Includes a production-ready REST API server, FID/PSNR quality metrics, and advanced augmentation strategies (APA, discriminator noise injection) for unpaired training on tasks like sim-to-real, object insertion/removal, and style transfer while preserving annotations.

280 stars.

No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

280

Forks

41

Language

Python

License

Last pushed

Mar 17, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/jolibrain/joliGEN"

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