Semantic Image Synthesis via Diffusion Models (SDM)

Training and Test

We use python3.9.

• Train the SDM model with Jittor:

  python image_train.py --input_path /root/data/train_resized

• Test the SDM model with Jittor:

  python image_sample.py --input_path /root/data/train_resized --img_path /root/data/val_B_labels_resized --output_path ./output

Acknowledge

Our code is developed based on WeilunWang/semantic-diffusion-model: Official Implementation of Semantic Image Synthesis via Diffusion Models (github.com).

Paper

Weilun Wang, Jianmin Bao, Wengang Zhou, Dongdong Chen, Dong Chen, Lu Yuan, Houqiang Li