open-mmlab/mmagic

[New Models] Support On Distillation of Guided Diffusion Models

オープン

#1,294 opened on 2022/10/13

 (2 件のコメント) (3 件のリアクション) (1 人の担当者)Python (836 件のフォーク)batch import
good first issuehelp wanted

Repository metrics

Stars
 (4,894 個のスター)
PR merge metrics
 (30d に merged PR はありません)

説明

Model/Dataset/Scheduler description

Classifier-free guided diffusion models have recently been shown to be highly effective at high-resolution image generation, and they have been widely used in large-scale diffusion frameworks including DALL-E 2, GLIDE and Imagen.

The proposed model is able to generate images visually comparable to that of the original model using as few as 4 sampling steps on ImageNet 64x64 and CIFAR-10, achieving FID/IS scores comparable to that of the original model while being up to 256 times faster to sample from.

Open source status

  • The model implementation is available
  • The model weights are available.

Provide useful links for the implementation

Paper: On Distillation of Guided Diffusion Models

コントリビューターガイド