VDMv-8 trained on CIFAR-10

Checkpoints for an image generation model trained on CIFAR-10.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).Model uses v-parametrization for the loss and is of size 8. That is the model uses 8 "down-blocks" in the U-net. See details in article.The model was trained on CIFAR-10 for 2 million steps with a batch size of 128.Random seeds: 1, 2, 13, 42, 70

本数据集包含在CIFAR-10数据集上训练得到的图像生成模型的检查点（checkpoint）。该模型基于Jax框架开发，其加载代码可查阅对应GitHub仓库。该模型为变分扩散模型（variational diffusion model, VDM，https://arxiv.org/abs/2107.00630），其训练工作出自论文《DiffEnc: 带学习编码器的变分扩散模型》（https://arxiv.org/abs/2310.19789）。该模型在损失计算中采用v参数化方式，其U-net架构包含8个下采样块（down-block），详细信息可参考上述论文。该模型在CIFAR-10数据集上以批量大小128训练了200万步。所用随机种子为1、2、13、42和70。