PixelDiT-ImageNet

<p align="center"> <img src="https://raw.githubusercontent.com/NVlabs/PixelDiT/master/assets/pixeldit-logo.png" height="60" /> </p> <h2 align="center">PixelDiT: Pixel Diffusion Transformers for Image Generation</h2> <p align="center"> <a href="https://www.yongshengyu.com/">Yongsheng Yu</a>^1,2 &nbsp; <a href="https://wxiong.me/">Wei Xiong</a>^1† &nbsp; <a href="https://weilinie.github.io/">Weili Nie</a>¹ &nbsp; <a href="https://shengcn.github.io/">Yichen Sheng</a>¹ &nbsp; <a href="http://behindthepixels.io/">Shiqiu Liu</a>¹ &nbsp; <a href="https://www.cs.rochester.edu/u/jluo/">Jiebo Luo</a>² </p> <p align="center"> ¹NVIDIA &nbsp; ²University of Rochester <br> ^†Project Lead and Main Advising </p> <p align="center"> <a href="https://pixeldit.github.io/"><img src="https://img.shields.io/badge/Website-Project_Page-2ea44f" /></a> &nbsp; <a href="https://arxiv.org/abs/2511.20645"><img src="https://img.shields.io/badge/arXiv-2511.20645-b31b1b.svg" /></a> &nbsp; <a href="https://github.com/NVlabs/PixelDiT"><img src="https://img.shields.io/badge/GitHub-Code-blue" /></a> </p>

Pre-trained Checkpoints

All evaluations use FlowDPMSolver with 100 steps. 50K samples. Metrics follow the ADM evaluation protocol.

Usage

Installation

pip install -r requirements.txt

Evaluation (Generate 50K Samples)

cd c2i/

# ImageNet 256x256 (epoch 320, best FID)
torchrun --nproc_per_node=8 main.py predict \
  -c configs/pix256_xl.yaml \
  --ckpt_path=imagenet256_pixeldit_xl_epoch320.ckpt \
  --model.diffusion_sampler.class_path=src.diffusion.FlowDPMSolverSampler \
  --model.diffusion_sampler.init_args.num_steps=100 \
  --model.diffusion_sampler.init_args.guidance=2.75 \
  --model.diffusion_sampler.init_args.timeshift=1.0 \
  --model.diffusion_sampler.init_args.guidance_interval_min=0.1 \
  --model.diffusion_sampler.init_args.guidance_interval_max=0.9 \
  --per_run_seed=false --seed_everything=1000

# ImageNet 512x512
torchrun --nproc_per_node=8 main.py predict \
  -c configs/pix512_xl.yaml \
  --ckpt_path=imagenet512_pixeldit_xl.ckpt \
  --model.diffusion_sampler.class_path=src.diffusion.FlowDPMSolverSampler \
  --model.diffusion_sampler.init_args.num_steps=100 \
  --model.diffusion_sampler.init_args.guidance=3.5 \
  --model.diffusion_sampler.init_args.timeshift=2.0 \
  --model.diffusion_sampler.init_args.guidance_interval_min=0.1 \
  --model.diffusion_sampler.init_args.guidance_interval_max=1.0 \
  --per_run_seed=false --seed_everything=10000

After generating samples, compute FID with the ADM evaluation toolkit.

Citation

@inproceedings{yu2025pixeldit,
      title={PixelDiT: Pixel Diffusion Transformers for Image Generation},
      author={Yongsheng Yu and Wei Xiong and Weili Nie and Yichen Sheng and Shiqiu Liu and Jiebo Luo},
      booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
      year={2026},
}

License

This model is released under the NSCLv1 License. The work and any derivative works may only be used for non-commercial (research or evaluation) purposes.