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 replacement for the existing autoencoder..
sd-vae-ft-mse-original huggingface.co is an AI model on huggingface.co that provides sd-vae-ft-mse-original's model effect (), which can be used instantly with this stabilityai sd-vae-ft-mse-original model. huggingface.co supports a free trial of the sd-vae-ft-mse-original model, and also provides paid use of the sd-vae-ft-mse-original. Support call sd-vae-ft-mse-original model through api, including Node.js, Python, http.
sd-vae-ft-mse-original huggingface.co is an online trial and call api platform, which integrates sd-vae-ft-mse-original's modeling effects, including api services, and provides a free online trial of sd-vae-ft-mse-original, you can try sd-vae-ft-mse-original online for free by clicking the link below.
stabilityai sd-vae-ft-mse-original online free url in huggingface.co:
sd-vae-ft-mse-original is an open source model from GitHub that offers a free installation service, and any user can find sd-vae-ft-mse-original on GitHub to install. At the same time, huggingface.co provides the effect of sd-vae-ft-mse-original install, users can directly use sd-vae-ft-mse-original installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
sd-vae-ft-mse-original install url in huggingface.co: