WensongSong/Insert-Anything

Insert Anything

Wensong Song · Hong Jinag · Zongxing Yang · Ruijie Quan · Yi Yang


Zhejiang University   |   Harvard University   |   Nanyang Technological University

News

• [2025.4.22] Release AnyInsertion dataset on HuggingFace.
• [2025.4.22] Support online demo on HuggingFace.
• [2025.4.22] Release inference & demo code on GitHub, and mask-prompt pretrained checkpoint.

Model Introduction

The currently released checkpoint is 20250321_steps5000_pytorch_lora_weights.safetensors, which is for mask-prompt image insertion. Future versions of the checkpoints will be released as updates.

Citation

@misc{song2025insertanythingimageinsertion,
      title={Insert Anything: Image Insertion via In-Context Editing in DiT}, 
      author={Wensong Song and Hong Jiang and Zongxing Yang and Ruijie Quan and Yi Yang},
      year={2025},
      eprint={2504.15009},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2504.15009}, 
}