Diffree / README.md
LiruiZhao's picture
Update README.md
02db928 verified
|
raw
history blame
1.18 kB
metadata
title: Diffree
emoji: πŸ–Ό
colorFrom: purple
colorTo: red
sdk: gradio
sdk_version: 4.26.0
app_file: app.py
pinned: false
license: mit

Diffree

[πŸ“œ Arxiv]       [πŸ” Code]

Diffree is a diffusion model that enables the addition of new objects to images using only text descriptions, seamlessly integrating them with consistent background and spatial context.

In this repo, we provide the πŸ€— Hugging Face demo for Diffree, and you can also download our model via πŸ€— Checkpoint.

Citation

If you found this work useful, please consider citing:

@article{zhao2024diffree,
  title={Diffree: Text-Guided Shape Free Object Inpainting with Diffusion Model},
  author={Zhao, Lirui and Yang, Tianshuo and Shao, Wenqi and Zhang, Yuxin and Qiao, Yu and Luo, Ping and Zhang, Kaipeng and Ji, Rongrong},
  journal={arXiv preprint arXiv:2407.16982},
  year={2024}
}