English

Multitwine: Multi-Object Compositing with Text and Layout Control

Computer Vision and Pattern Recognition 2025-02-10 v1

Abstract

We introduce the first generative model capable of simultaneous multi-object compositing, guided by both text and layout. Our model allows for the addition of multiple objects within a scene, capturing a range of interactions from simple positional relations (e.g., next to, in front of) to complex actions requiring reposing (e.g., hugging, playing guitar). When an interaction implies additional props, like `taking a selfie', our model autonomously generates these supporting objects. By jointly training for compositing and subject-driven generation, also known as customization, we achieve a more balanced integration of textual and visual inputs for text-driven object compositing. As a result, we obtain a versatile model with state-of-the-art performance in both tasks. We further present a data generation pipeline leveraging visual and language models to effortlessly synthesize multimodal, aligned training data.

Keywords

Cite

@article{arxiv.2502.05165,
  title  = {Multitwine: Multi-Object Compositing with Text and Layout Control},
  author = {Gemma Canet Tarrés and Zhe Lin and Zhifei Zhang and He Zhang and Andrew Gilbert and John Collomosse and Soo Ye Kim},
  journal= {arXiv preprint arXiv:2502.05165},
  year   = {2025}
}
R2 v1 2026-06-28T21:36:36.235Z