hugpadhugpad

Motif-Technologies / Motif-VAE

Image Generation1.2B6014Updated Jul 31, 2026
Hugging Face

Downloads

60

Likes

14

Last updated

Jul 31, 2026

License

mit

Motif VAE is a 3D causal video VAE with 4x temporal and 32x spatial compression and a 128-channel latent space, built as a high-compression tokenizer for latent video diffusion models. A 256x256x17-frame clip encodes to a (128, 5, 8, 8) latent, which is 1/16 the spatio-tempora…

Tasks & library

  • image to image
  • diffusers

Tags

  • diffusers
  • video-vae
  • vae
  • video-generation
  • tokenizer
  • pytorch

Technical specifications

Parameters1.2B
Librarydiffusers
LanguagesNot available
Licensemit