- paper : https://arxiv.org/pdf/2006.11239
- data(MNIST) : https://huggingface.co/datasets/ylecun/mnist
- data(MNIST modified with size(32, 32)) : https://huggingface.co/datasets/junyeong-nero/mnist_32by32
- DDPM : https://dataflowr.github.io/website/modules/18a-diffusion/
- UNet : https://velog.io/@lighthouse97/UNet%EC%9D%98-%EC%9D%B4%ED%95%B4
- traing with PyTorch : https://pytorch.org/tutorials/beginner/introyt/trainingyt.html
- ViT : https://hipgyung.tistory.com/entry/%EC%89%BD%EA%B2%8C-%EC%9D%B4%ED%95%B4%ED%95%98%EB%8A%94-ViTVision-Transformer-%EB%85%BC%EB%AC%B8-%EB%A6%AC%EB%B7%B0-An-Image-is-Worth-16x16-Words-Transformers-for-Image-Recognition-at-Scale
- DiT : https://kyujinpy.tistory.com/132