DiffEnc-32-8 trained on ImageNet32

Checkpoints for an image generation model trained on ImageNet32.

The model was made in Jax. See the github repository for code to load the checkpoints.

The model is a variational diffusion model (VDM, https://arxiv.org/abs/2107.00630) with an added trainable time-dependent encoder trained for the article "DiffEnc: Variational Diffusion with a Learned Encoder" (https://arxiv.org/abs/2310.19789).

Model uses v-parametrization for the loss. The diffusion model is of size 32 and the encoder is of size 8. That is, the diffusion model uses 32 "down-blocks" in the U-net. See details in article.

Model was trained on ImageNet32 for 1.5 million steps.

Random seeds: 1, 2, 13