Skip to content

README.md

Latest commit

 

History

History
32 lines (21 loc) · 1.1 KB

README.md

File metadata and controls

32 lines (21 loc) · 1.1 KB

Generative Models

5类生成模型demo (GAN, VAE, GPT, Diffusion, Flow)

1. Diffusion models

This folder DDPM–DDIM–ClassifierFree provides minimal, easy-to-read implementations** of key diffusion models, including DDPM, DDIM, and conditional diffusion (classifier-free guidance).
It contains both the source code and pretrained model checkpoints.

If you find this work helpful for your research, please consider citing our paper(https://arxiv.org/abs/2512.07201):

@misc{yu2025understandingdiffusionmodelscode,
      title={Understanding Diffusion Models via Code Execution}, 
      author={Cheng Yu},
      year={2025},
      eprint={2512.07201},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2512.07201}, 
}

2. Flow

pre-trained model (nice_block100_hf=pixels.pth) can be down load here: link

通过网盘分享的文件：nice_block100_hf=pixels.pth 链接: https://pan.baidu.com/s/1Vv83B8rJoyNe0-Oo_JChnQ?pwd=1234 提取码: 1234