metadata
license: apache-2.0
pipeline_tag: image-to-image
VeraRetouch: A Lightweight Fully Differentiable Framework for Multi-Task Reasoning Photo Retouching
VeraRetouch is a lightweight and fully differentiable framework for multi-task photo retouching. It employs a 0.5B Vision-Language Model (VLM) as the central intelligence to formulate retouching plans based on instructions and scene semantics, combined with a fully differentiable Retouch Renderer for direct end-to-end pixel-level training.
Paper | Project Page | GitHub
🚀 Quick Start
⚙️ Environment Setup
# Clone the repository
git clone https://github.com/OpenVeraTeam/VeraRetouch.git
cd VeraRetouch
# Create and activate conda environment
conda create -n vera-retouch python=3.10
conda activate vera-retouch
pip install -r requirements.txt
🎨 Inference Modes
VeraRetouch supports three primary inference modes via inference.py. Ensure you have downloaded the weights and placed them in the ./checkpoints directory.
Auto Retouch
Automatically enhances an image based on scene analysis.
python inference.py --mode auto \
--model-path ./checkpoints/VeraRetouch \
--img_paths ./data_samples/input/sample_flower.jpg \
--save_dir ./data_samples/output/
Style Retouch
Retouches an image based on a specific user prompt.
python inference.py --mode style \
--prompt "I want a dreamy bright pink style." \
--model-path ./checkpoints/VeraRetouch \
--img_paths ./data_samples/input/sample_flower.jpg \
--save_dir ./data_samples/output/
Param Retouch
Applies retouching based on specific operator parameters.
python inference.py --mode style \
--instruction_path ./data_samples/param.json \
--model-path ./checkpoints/VeraRetouch \
--img_paths ./data_samples/input/sample_flower.jpg \
--save_dir ./data_samples/output/
Citation
@article{guo2026veraretouch,
title={VeraRetouch: A Lightweight Fully Differentiable Framework for Multi-Task Reasoning Photo Retouching},
author={Guo, Yihong and Lyu, Youwei and Tang, Jiajun and Zhou, Yizhuo and Wang, Hongliang and Chen, Jinwei and Zou, Changqing and Fan, Qingnan},
journal={arXiv preprint arXiv:2604.27375},
year={2026}
}