About this Model

This model copy weights from stabilityai/sd-vae-ft-ema, but with the last DownEncoderBlock2D and the first UpDecoderBlock2D removed. As a result, this model cannot be used without finetuning. The purpose is to obtain a VAE with a scale factor of 4.

Downloads last month: 3

Inference Providers NEW

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