lavinal712/AutoencoderKL
Train Your VAE: A VAE Training and Finetuning Script for SD/FLUX
This project helps machine learning engineers and researchers working with generative AI to train and fine-tune Variational Autoencoders (VAEs). You can input your own image datasets and a VAE architecture (like those used in Stable Diffusion or FLUX), and it outputs a trained VAE model with improved image reconstruction quality. It's designed for those developing or customizing image generation models.
Use this if you need a reliable and up-to-date script to train or fine-tune VAEs for image generation tasks, ensuring good reconstruction of input images.
Not ideal if you are an artist or designer looking for a user-friendly tool to generate images directly, as this requires coding and machine learning expertise.
Stars
76
Forks
5
Language
Python
License
MIT
Category
Last pushed
Jan 14, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/lavinal712/AutoencoderKL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jxhe/vae-lagging-encoder
PyTorch implementation of "Lagging Inference Networks and Posterior Collapse in Variational...
chaitanya100100/VAE-for-Image-Generation
Implemented Variational Autoencoder generative model in Keras for image generation and its...
taldatech/soft-intro-vae-pytorch
[CVPR 2021 Oral] Official PyTorch implementation of Soft-IntroVAE from the paper "Soft-IntroVAE:...
Rayhane-mamah/Efficient-VDVAE
Official Pytorch and JAX implementation of "Efficient-VDVAE: Less is more"
zelaki/eqvae
[ICML'25] EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling.