taldatech/soft-intro-vae-pytorch
[CVPR 2021 Oral] Official PyTorch implementation of Soft-IntroVAE from the paper "Soft-IntroVAE: Analyzing and Improving Introspective Variational Autoencoders"
This project helps researchers and engineers working with image or 3D data generate realistic new samples and detect unusual or unexpected data points. You input a dataset of existing images, 2D plots, or 3D point clouds, and it provides a model that can create entirely new, diverse samples mimicking your original data. It also helps identify data points that deviate significantly from the learned distribution.
198 stars. No commits in the last 6 months.
Use this if you need to generate high-quality synthetic images, 2D patterns, or 3D object representations, or if you want to identify anomalies in visual or spatial datasets.
Not ideal if your primary goal is simple data compression or if you are not working with image, 2D, or 3D spatial data.
Stars
198
Forks
30
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Jun 27, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/taldatech/soft-intro-vae-pytorch"
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...
lavinal712/AutoencoderKL
Train Your VAE: A VAE Training and Finetuning Script for SD/FLUX
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.