musikisomorphie/swd

unsupervised video and image generation

27
/ 100
Experimental

Implements Sliced Wasserstein distance-based generative models (SWAE and SWGAN) with progressive training for high-resolution synthesis, using custom CUDA operations to compute efficient optimal transport distances. Supports both standard and 3D progressive training pipelines on TensorFlow, enabling video generation up to 256x256 resolution through incremental layer growth—includes the TrailerFaces dataset of 200K facial expression clips extracted from movie trailers.

No commits in the last 6 months.

No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

57

Forks

6

Language

Python

License

Last pushed

Jul 23, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/musikisomorphie/swd"

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