# Perceptual Flow Matching for Few-Step Generative Modeling

Chuyang Zhao¹ Yifei Song² Hongfa Wang³ Jianlong Yuan¹ Yuan Zhang¹ Siming Fu¹ Zhineng Chen² Huilin Deng⁴ Haoyang Huang¹ Nan Duan¹†

¹Joy Future Academy ²Fudan University ³Tsinghua University ⁴USTC

## 📰 News - [2026/07/23] We release the training and inference code and checkpoints of PFM on SD3. ## Introduction We propose Perceptual Flow Matching (PFM) — a simple framework for few-step generation in flow-matching models. By supervising flow matching in a perceptual feature space instead of the conventional VAE latent space, PFM reduces sampling steps from 35–50 to 4–8 while preserving generation quality.

Perceptual Flow Matching Method Overview

## Usage ### Environment Setup ```bash conda create -n pfm python=3.10 -y conda activate pfm pip install -r requirements.txt ``` ### Training | Task | Dataset | LoRA | Perceptual Model | Backbone | GFT Scale | Script | |------|---------|------|-----------------|----------|-----------|--------| | T2I | COCO | ✗ | VGG+DINO | SD3-Medium | 1.0 | [train_sd3_coco_vgg+dino.sh](scripts/train_sd3_coco_vgg+dino.sh) | | T2I | COCO | ✓ | VGG+DINO | SD3-Medium | 2.0 | [train_sd3_lora_coco_vgg+dino.sh](scripts/train_sd3_lora_coco_vgg+dino.sh) | | T2I | COCO | ✗ | ConvNeXt+CLIP+DINO | SD3-Medium | 3.5 | [train_sd3_coco_clip+dino+convnext.sh](scripts/train_sd3_coco_clip+dino+convnext.sh) | ### Inference ```bash cd /path/to/PFM export PYTHONPATH=$PYTHONPATH:$(pwd) torchrun --nproc_per_node=8 pfm/eval_sd3.py \ --checkpoint /path/to/checkpoint/step_500.pth \ --val_prompts_file evaluations/PartiPrompts.jsonl \ --sampling_methods consistency \ --num_steps 4,8 \ --output_dir outputs/sd3_pfm/eval \ --max_samples 64 ``` ## Acknowledgements This project is built upon [HunyuanVideo](https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5), [JoyAI-Image](https://github.com/jd-opensource/JoyAI-Image), and [FastVideo](https://github.com/hao-ai-lab/fastvideo). We thank the authors for their great work. ## Contact For any questions, please contact [Chuyang Zhao](mailto:chuyang.zhao@outlook.com)(chuyang.zhao@outlook.com). We are hiring interns at [JoyAI Research](https://research.joyai.com/). If you are interested, please send your resume to [zhaochuyang.3@jd.com](mailto:zhaochuyang.3@jd.com). ## Citation ```bibtex @misc{zhao2026perceptualflowmatchingfewstep, title={Perceptual Flow Matching for Few-Step Generative Modeling}, author={Chuyang Zhao and Yifei Song and Hongfa Wang and Jianlong Yuan and Yuan Zhang and Siming Fu and Zhineng Chen and Huilin Deng and Haoyang Huang and Nan Duan}, year={2026}, eprint={2607.03524}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2607.03524}, } ``` ## License This project is released under the [Apache-2.0](LICENSE) license.