Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up
EPFL-VILAB 's Collections
FlexTok Tokenizers & VAEs
4M Models
4M Tokenizers
Omnidata depth & normals models

FlexTok Tokenizers & VAEs

updated Apr 1

Flexible 1D tokenizers and VAEs from https://flextok.epfl.ch/

Upvote
-

  • EPFL-VILAB/flextok_d18_d28_dfn

    3B • Updated Mar 19 • 9.85k • 1

  • EPFL-VILAB/flextok_d18_d28_in1k

    3B • Updated Mar 19 • 19

  • EPFL-VILAB/flextok_d18_d18_in1k

    0.9B • Updated Mar 19 • 58

  • EPFL-VILAB/flextok_d12_d12_in1k

    0.3B • Updated Mar 19 • 275

  • EPFL-VILAB/flextok_vae_c16

    Updated Mar 19 • 155

  • EPFL-VILAB/flextok_vae_c8

    Updated Mar 19 • 55

  • EPFL-VILAB/flextok_vae_c4

    Updated Mar 19 • 15

  • Running on Zero
    8
    8

    FlexTok

    🖼

    FlexTok flexible sequence length autoencoding demo


  • FlexTok: Resampling Images into 1D Token Sequences of Flexible Length

    Paper • 2502.13967 • Published Feb 19 • 1
Upvote
-
  • Collection guide
  • Browse collections
Company
TOS Privacy About Jobs
Website
Models Datasets Spaces Pricing Docs