Hugging Face's logo

StonyBrook-CVLab
/
sd-3.5-large-vae-path

Diffusers
Safetensors
Model card Files Community
sd-3.5-large-vae-path / README.md
AlexGraikos's picture
AlexGraikos
Update README.md
c827265 verified
preview code
|
raw
history blame contribute delete
441 Bytes

[Paper]

StabilityAI KL-f8-c16 (SD3.5 VAE) autoencoder finetuned on digital histopathology images.

The original autoencoder is taken from StabilityAI.

We fine-tune the decoder on histopathology images using an L1 reconstruction loss, a PatchGAN adversarial loss and a pathology-specific perceptual loss (UNI).