musikisomorphie/swd
unsupervised video and image generation
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.
Stars
57
Forks
6
Language
Python
License
—
Category
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.
Higher-rated alternatives
yao-jason/MLDS2018SPRING
Machine Learning and having it Deep and Structured (MLDS) in 2018 spring
ivarunsharma/GenaipythonExamples
A progressive, hands-on collection of Generative AI examples in Python
thtang/ADLxMLDS2017
Deep learning works for ADLxMLDS (CSIE 5431) in NTU
Victarry/Image-Generation-models
Generative models (GAN, VAE, Diffusion Models, Autoregressive Models) implemented with Pytorch,...
adamz799/Paints
Auto paint sketch(from lineart to anime illustration)