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.
@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}
}