SmartPhotoCrafter is an end-to-end framework for automatic photographic image editing that reformulates traditional editing as a closed-loop reasoning-to-generation process. Unlike prior methods that rely on explicit user instructions, our approach autonomously identifies aesthetic deficiencies, reasons about improvement strategies, and performs targeted edits without human prompts.

• Fully Automatic Editing – No user instructions or parameters required; the model completes the closed loop of quality assessment → reasoning → editing autonomously.
• Dual Capability – Supports both image restoration (denoising, deblurring, low-light enhancement) and image retouching (color, tone, contrast enhancement).
• Aesthetic Reasoning – Explicitly generates image quality analysis and editing suggestions, improving interpretability.
• High-Fidelity Generation – Preserves original content structure while delivering photo-realistic outputs with high tonal/color semantic sensitivity.
• Reinforcement Learning Optimization – Jointly optimizes reasoning and generation modules, aligning editing trajectories with human aesthetic preferences.

• 2026/04/07: We open-source the inference scripts.
• 2026/04/22: Our Paper on ArXiv is available!

• ✅ Release the inference code of SmartPhotoCrafter
• [ ] Release the SmartPhotoCrafter pretrained weights

Create a conda environment & install requirements

# python==3.10.0 cuda==12.4 torch==2.5
conda create -n smartphotocrafter python==3.10.0
conda activate smartphotocrafter
pip install -r requirements.txt

We provide scripts for both automatic and manual editing. Automatic editing only requires inputting one image, while manual editing requires adding a prompt.

Automatically edit reasoning scripts

bash scripts/inference/automatic-edit.sh

Manual edit reasoning scripts

bash scripts/inference/manual-eidt.sh

Script example

CUDA_VISIBLE_DEVICES=0 python infer.py \
    --model_path "ckpt/Qwen-Image-Edit-2509" \
    --dit_path "ckpt/DiT.safetensors" \
    --vlm_path "ckpt/text_encoder" \
    --image_path "example/841012.png" \
    --output_folder "example/output/automatic" \
    --seed 42 \

Coming Soon ...

Our code is modified based on Edit-R1. We adopt Qwen-Image-Edit-2509 as the base model.

All the materials, including code, checkpoints, and demos, are made available under the Creative Commons BY-NC-SA 4.0 license. You are free to copy, redistribute, remix, transform, and build upon the project for non-commercial purposes, as long as you give appropriate credit and distribute your contributions under the same license.

@article{zeng2026smartphotocrafter,
  title={SmartPhotoCrafter: Unified Reasoning, Generation and Optimization for Automatic Photographic Image Editing},
  author={Zeng, Ying and Luo, Miaosen and Li, Guangyuan and Yang, Yang and Fan, Ruiyang and Shi, Linxiao and Yang, Qirui and Zhang, Jian and Liu, Chengcheng and Zheng, Siming and others},
  journal={arXiv preprint arXiv:2604.19587},
  year={2026}
}