puar-playground/TextLap-COCO

TextLap (Image layout)

This model is fine-tuned on lmsys/vicuna-7b-v1.5 using image layout data extracted from the MS-COCO dataset.

The inference code and prompt format is availabe at the GitHub repo: TextLap.

Reference

@article{chen2024textlap,
  title={TextLap: Customizing Language Models for Text-to-Layout Planning},
  author={Chen, Jian and Zhang, Ruiyi and Zhou, Yufan and Healey, Jennifer and Gu, Jiuxiang and Xu, Zhiqiang and Chen, Changyou},
  journal={arXiv preprint arXiv:2410.12844},
  year={2024}
}