IDDM v1.2.2

What's Changed

• feat: Update about attention. by @chairc in #155
• chore: Optimized flash-attn. by @chairc in #156
• fix: Fix the issue of ddpm generation noise in Latent mode. by @chairc in #157
• chore: Update version and README by @chairc in #158

Full Changelog: v1.2.1...v1.2.2

Weights

Note: The weight include model, ema_model and optimizer.

Diffusion Models

• celebahq-120-weight.pt: Trained on a dataset of 30,000 people face, and image size is 120 (celebahq-120-weight.pt)
• animate-ganyu-120-weight.pt: Trained on a dataset of 500 animate ganyu face, and image size is 120 (animate-ganyu-120-weight.pt)
• neu-cls-64-weight.pt: Trained on a dataset of 7,226 defect, and image size is 64 (neu-cls-64-weight.pt)
• neu-120-weight.pt: Trained on a dataset of 1,800 defect, and image size is 120 (neu-120-weight.pt)
• cifar-64-weight.pt: Trained on a dataset of 60,000 images, and image size is 64 (cifar10-64-weight.pt)
• animate-face-64-weight.pt: Trained on a dataset of 63,565 animate face, and image size is 64 (animate-face-64-weight.pt)

Autoencoder Models

• neu-autoencoder-512-weight.pt: Trained on a dataset of 1,800 defect, and image size is 512 (neu-autoencoder-512-weight.pt)
• voc-autoencoder-512-weight.pt: Trained on a dataset of 33,240 images, and image size is 512 (voc-autoencoder-512-weight.pt)

Latent Diffusion Models

• neu-64-latent-weight.pt: Trained on a dataset of 1,800 defect, and image size is 64 (neu-64-latent-weight.pt)