EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling
Paper
• 2502.09509 • Published
• 8
EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling
Arxiv: https://arxiv.org/abs/2502.09509
EQ-VAE regularizes the latent space of pretrained autoencoders by enforcing equivariance under scaling and rotation transformations.
Model Description
This model is SiT-XL/2-REPA trained with latents extracted with EQ-VAE. The model is trained for 1M iterations on Imagenet 256x256.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support