# ComposeMe: Attribute-Specific Image Prompts for Controllable Human Image Generation

arXiv: https://arxiv.org/abs/2509.18092 · HTML: https://mlsanity.com/paper/2509.18092/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 60 references that are in the map.
- First posted on arXiv 22 Sep 2025.

## Builds on (most cited first, 30 of 36)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models](https://mlsanity.com/paper/2305.18292/) (2023)
- [Break-A-Scene: Extracting Multiple Concepts from a Single Image](https://mlsanity.com/paper/2305.16311/) (2023)
- [StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On](https://mlsanity.com/paper/2312.01725/) (2023)
- [Less-to-More Generalization: Unlocking More Controllability by In-Context Generation](https://mlsanity.com/paper/2504.02160/) (2025)
- [OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on](https://mlsanity.com/paper/2403.01779/) (2024)
- [StyleGAN-Human: A Data-Centric Odyssey of Human Generation](https://mlsanity.com/paper/2204.11823/) (2022)
- [MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance](https://mlsanity.com/paper/2406.07209/) (2024)
- [OMG: Occlusion-friendly Personalized Multi-concept Generation in Diffusion Models](https://mlsanity.com/paper/2403.10983/) (2024)
- [LoRA-Composer: Leveraging Low-Rank Adaptation for Multi-Concept Customization in Training-Free Diffusion Models](https://mlsanity.com/paper/2403.11627/) (2024)
- [TokenVerse: Versatile Multi-concept Personalization in Token Modulation Space](https://mlsanity.com/paper/2501.12224/) (2025)
- [λ-ECLIPSE: Multi-Concept Personalized Text-to-Image Diffusion Models by Leveraging CLIP Latent Space](https://mlsanity.com/paper/2402.05195/) (2024)
- [MoA: Mixture-of-Attention for Subject-Context Disentanglement in Personalized Image Generation](https://mlsanity.com/paper/2404.11565/) (2024)
- [LCM-Lookahead for Encoder-based Text-to-Image Personalization](https://mlsanity.com/paper/2404.03620/) (2024)
- [UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image Personalization](https://mlsanity.com/paper/2408.05939/) (2024)
- [Resolving Multi-Condition Confusion for Finetuning-Free Personalized Image Generation](https://mlsanity.com/paper/2409.17920/) (2024)
- [InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity](https://mlsanity.com/paper/2503.16418/) (2025)
- [MyStyle: A Personalized Generative Prior](https://mlsanity.com/paper/2203.17272/) (2022)
- [Nested Attention: Semantic-aware Attention Values for Concept Personalization](https://mlsanity.com/paper/2501.01407/) (2025)
- [Dynamic Concepts Personalization from Single Videos](https://mlsanity.com/paper/2502.14844/) (2025)

## Built on by (most cited first, 7 of 7)

- [Canvas-to-Image: Compositional Image Generation with Multimodal Controls](https://mlsanity.com/paper/2511.21691/) (2025)
- [Preventing Shortcuts in Adapter Training via Providing the Shortcuts](https://mlsanity.com/paper/2510.20887/) (2025)
- [Omni-Attribute: Open-vocabulary Attribute Encoder for Visual Concept Personalization](https://mlsanity.com/paper/2512.10955/) (2025)
- [Garments2Look: A Multi-Reference Dataset for High-Fidelity Outfit-Level Virtual Try-On with Clothing and Accessories](https://mlsanity.com/paper/2603.14153/) (2026)
- [CanvasComposer: Personalized Group Photo Generation via a Multi-Reference Canvas](https://mlsanity.com/paper/2510.20820/) (2025)
- [OmniCustom: Sync Audio-Video Customization Via Joint Audio-Video Generation Model](https://mlsanity.com/paper/2602.12304/) (2026)
- [FFAvatar: Few-Shot, Feed-Forward, and Generalizable Avatar Reconstruction](https://mlsanity.com/paper/2605.15320/) (2026)

## Abstract (arXiv)

Generating high-fidelity images of humans with fine-grained control over attributes such as hairstyle and clothing remains a core challenge in personalized text-to-image synthesis. While prior methods emphasize identity preservation from a reference image, they lack modularity and fail to provide disentangled control over specific visual attributes. We introduce a new paradigm for attribute-specific image prompting, in which distinct sets of reference images are used to guide the generation of individual aspects of human appearance, such as hair, clothing, and identity. Our method encodes these inputs into attribute-specific tokens, which are injected into a pre-trained text-to-image diffusion model. This enables compositional and disentangled control over multiple visual factors, even across multiple people within a single image. To promote natural composition and robust disentanglement, we curate a cross-reference training dataset featuring subjects in diverse poses and expressions, and propose a multi-attribute cross-reference training strategy that encourages the model to generate faithful outputs from misaligned attribute inputs while adhering to both identity and textual conditioning. Extensive experiments show that our method achieves state-of-the-art performance in accurately following both visual and textual prompts. Our framework paves the way for more configurable human image synthesis by combining visual prompting with text-driven generation. Webpage is available at: https://snap-research.github.io/composeme/.