eramth
/

sdxl-vae-memory-efficient

Model card Files Files and versions

A memory-efficient SDXL VAE that saves about 3GB of RAM with almost no loss of image quality during VAE decoding.

Downloads last month: 7

Safetensors

Model size

83.7M params

Tensor type

F16

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support