PhotoFramer: Multi-modal Image Composition Instruction
Paper • 2512.00993 • Published
PhotoFramer Model
The original PhotoFramer model weights are currently maintained within Adobe and cannot be released immediately. Open-sourcing them requires multiple rounds of internal approval, including a detailed legal review, which may take a quite long time.
To provide early access to the community, I have retrained a preview version of PhotoFramer and released its model weights.
This is a preview PhotoFramer ( project page / codes / paper ) model weights.
Citation
If you find our work useful for your research and applications, please cite using the BibTeX:
@inproceedings{photoframer,
title={PhotoFramer: Multi-modal Image Composition Instruction},
author={You, Zhiyuan and Wang, Ke and Zhang, He and Cai, Xin and Gu, Jinjin and Xue, Tianfan and Dong, Chao and Zhang, Zhoutong},
booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year={2026}
}