We present PartComposer: a framework for part-level concept learning from single-image examples that enables text-to-image diffusion models to compose novel objects from meaningful components. Existing methods either struggle with effectively learning fine-grained concepts or require a large dataset as input. We propose a dynamic data synthesis pipeline generating diverse part compositions to address one-shot data scarcity. Most importantly, we propose to maximize the mutual information between denoised latents and structured concept codes via a concept predictor, enabling direct regulation on concept disentanglement and re-composition supervision. Our method achieves strong disentanglement and controllable composition, outperforming subject and part-level baselines when mixing concepts from the same, or different, object categories.
@article{arxiv.2506.03004,
title = {PartComposer: Learning and Composing Part-Level Concepts from Single-Image Examples},
author = {Junyu Liu and R. Kenny Jones and Daniel Ritchie},
journal= {arXiv preprint arXiv:2506.03004},
year = {2025}
}