Skip to content
项目

cloneofsimo/minDiffusion has 1,209 GitHub stars and 158 forks. GitHot measured 0 stars in 24 hours, 0 in 7 days, and +2 in 15 days. Last checked 2026-11-19 10:11 UTC. Last push 2022-06-28.

这些数字如何统计

实测星标增长

24小时
0
7天
0
15天
+2
1个月
正在收集历史

各周期内的星标净变化,周期相互重叠,并非每日新增。缺失的测量保持空白。星标代表关注度,不代表软件质量。

关于

Self-contained, minimalistic implementation of diffusion models with Pytorch.

机器学习

README.md

原文

minDiffusion

Goal of this educational repository is to provide a self-contained, minimalistic implementation of diffusion models using Pytorch.

Many implementations of diffusion models can be a bit overwhelming. Here, superminddpm : under 200 lines of code, fully self contained implementation of DDPM with Pytorch is a good starting point for anyone who wants to get started with Denoising Diffusion Models, without having to spend time on the details.

Simply:

$ python superminddpm.py

Above script is self-contained. (Of course, you need to have pytorch and torchvision installed. Latest version should suffice. We do not use any cutting edge features.)

If you want to use the bit more refactored code, that runs CIFAR10 dataset:

$ python train_cifar10.py

Above result took about 2 hours of training on single 3090 GPU. Top 8 images are generated, bottom 8 are ground truth.

Here is another example, trained on 100 epochs (about 1.5 hours)

Currently has:

  • Tiny implementation of DDPM
  • MNIST, CIFAR dataset.
  • Simple unet structure. + Simple Time embeddings.
  • CelebA dataset.

TODOS

  • DDIM
  • Classifier Guidance
  • Multimodality

Updates!

  • Using more parameter yields better result for MNIST.
  • More comments in superminddpm.py