Modelpublic

rdm0/autoencoderkl-sd0-init

sourceHugging Faceupdated 8mo agoView on Hugging Face

0likes4downloads

README.md10 linesDownload Raw Back to root

1---2library_name: diffusers3---4 5# About this Model6 7This model copy weights from `stabilityai/sd-vae-ft-ema`, but with the last `DownEncoderBlock2D` and the first `UpDecoderBlock2D` removed.8As a result, this model cannot be used without finetuning.9The purpose is to obtain a VAE with a scale factor of 4.10