Sparse Autoencoder in CIELAB color space

  • LAB input, RGB output
  • Scaling, Rotational equivalency

The latent representation should not produce artifacts under rotations or hue changes. However, it does not obey reflection symmetry.

Downloads last month

-

Downloads are not tracked for this model. How to track
Safetensors
Model size
13.7M params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support