sd vae ft mse EU AI Act Compliance Profile

Improved Autoencoders

Utilizing

These weights are intended to be used with the 🧨 diffusers library. If you are looking for the model to use with the original CompVis Stable Diffusion codebase, come here.

How to use with 🧨 diffusers

You can integrate this fine-tuned VAE decoder to your existing diffusers workflows, by including a vae argument to the StableDiffusionPipeline

from diffusers.models import AutoencoderKL
from diffusers import StableDiffusionPipeline

model = "CompVis/stable-diffusion-v1-4"
vae = AutoencoderKL.from_pretrained("stabilityai/sd-vae-ft-mse")
pipe = StableDiffusionPipeline.from_pretrained(model, vae=vae)

Decoder Finetuning

We publish two kl-f8 autoencoder versions, finetuned from the original kl-f8 autoencoder on a 1:1 ratio of LAION-Aesthetics and LAION-Humans, an unreleased subset containing only SFW images of humans. The intent was to fine-tune on the Stable Diffusion training set (the autoencoder was originally trained on OpenImages) but also enrich the dataset with images of humans to improve the reconstruction of faces. The first, ft-EMA, was resumed from the original checkpoint, trained for 313198 steps and uses EMA weights. It uses the same loss configuration as the original checkpoint (L1 + LPIPS). The second, ft-MSE, was resumed from ft-EMA and uses EMA weights and was trained for another 280k steps using a different loss, with more emphasis on MSE reconstruction (MSE + 0.1 * LPIPS). It produces somewhat ``smoother'' outputs. The batch size for both versions was 192 (16 A100s, batch size 12 per GPU). To keep compatibility with existing models, only the decoder part was finetuned; the checkpoints can be used as a drop-in replace

Your obligations as a sd vae ft mse deployer

Track your progress

Sign up to track obligations, receive deadline reminders, and generate audit packages.

Tags

Library