open-mmlab/mmagic

[New Models] Support On Distillation of Guided Diffusion Models

Open

#1,294 opened on Oct 13, 2022

View on GitHub
 (2 comments) (3 reactions) (1 assignee)Python (836 forks)batch import
good first issuehelp wanted

Repository metrics

Stars
 (4,894 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

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

Contributor guide

Research direction
Read the paper on distillation of guided diffusion models, understand the algorithm, and explore the existing diffusion model implementations in mmagic to identify where to add support for distillation. Look for similar features or modules that can be reused.
Tech stack
python
Domain
ai
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
3-5 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
PythonGit
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
45