VDMv-8 trained on MNIST with trainable noise schedule

Checkpoints for an image generation model trained on MNIST.

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) trained for the article "DiffEnc: Variational Diffusion with a Learned Encoder" (https://arxiv.org/abs/2310.19789).

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

The model was trained on MNIST for 2 million steps with a batch size of 128.

Random seeds: 1, 2, 13, 42, 70