# UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward

arXiv: https://arxiv.org/abs/2509.06818 · HTML: https://mlsanity.com/paper/2509.06818/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 41 references that are in the map.
- First posted on arXiv 8 Sep 2025.

## Builds on (most cited first, 30 of 35)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?](https://mlsanity.com/paper/2504.13837/) (2025)
- [Emerging Properties in Unified Multimodal Pretraining](https://mlsanity.com/paper/2505.14683/) (2025)
- [ByteTrack: Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2110.06864/) (2021)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [Movie Gen: A Cast of Media Foundation Models](https://mlsanity.com/paper/2410.13720/) (2024)
- [InstantID: Zero-shot Identity-Preserving Generation in Seconds](https://mlsanity.com/paper/2401.07519/) (2024)
- [ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation](https://mlsanity.com/paper/2302.13848/) (2023)
- [DanceGRPO: Unleashing GRPO on Visual Generation](https://mlsanity.com/paper/2505.07818/) (2025)
- [OmniGen: Unified Image Generation](https://mlsanity.com/paper/2409.11340/) (2024)
- [OmniGen2: Towards Instruction-Aligned Multimodal Generation](https://mlsanity.com/paper/2506.18871/) (2025)
- [OmniControl: Control Any Joint at Any Time for Human Motion Generation](https://mlsanity.com/paper/2310.08580/) (2023)
- [In-Context LoRA for Diffusion Transformers](https://mlsanity.com/paper/2410.23775/) (2024)
- [Less-to-More Generalization: Unlocking More Controllability by In-Context Generation](https://mlsanity.com/paper/2504.02160/) (2025)
- [PuLID: Pure and Lightning ID Customization via Contrastive Alignment](https://mlsanity.com/paper/2404.16022/) (2024)
- [MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance](https://mlsanity.com/paper/2406.07209/) (2024)
- [UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics](https://mlsanity.com/paper/2412.07774/) (2024)
- [DreamO: A Unified Framework for Image Customization](https://mlsanity.com/paper/2504.16915/) (2025)

## Built on by (most cited first, 19 of 19)

- [WithAnyone: Towards Controllable and ID Consistent Image Generation](https://mlsanity.com/paper/2510.14975/) (2025)
- [Lance: Unified Multimodal Modeling by Multi-Task Synergy](https://mlsanity.com/paper/2605.18678/) (2026)
- [iMontage: Unified, Versatile, Highly Dynamic Many-to-many Image Generation](https://mlsanity.com/paper/2511.20635/) (2025)
- [OpenSubject: Leveraging Video-Derived Identity and Diversity Priors for Subject-driven Image Generation and Manipulation](https://mlsanity.com/paper/2512.08294/) (2025)
- [DVI: Disentangling Semantic and Visual Identity for Training-Free Personalized Generation](https://mlsanity.com/paper/2512.18964/) (2025)
- [FlexID: Training-Free Flexible Identity Injection via Intent-Aware Modulation for Text-to-Image Generation](https://mlsanity.com/paper/2602.07554/) (2026)
- [Inject Where It Matters: Training-Free Spatially-Adaptive Identity Preservation for Text-to-Image Personalization](https://mlsanity.com/paper/2602.13994/) (2026)
- [Scaling Multi-Reference Image Generation with Dynamic Reward Optimization](https://mlsanity.com/paper/2606.26947/) (2026)
- [Ar2Can: An Architect and an Artist Leveraging a Canvas for Multi-Human Generation](https://mlsanity.com/paper/2511.22690/) (2025)
- [UniCustom: Unified Visual Conditioning for Multi-Reference Image Generation](https://mlsanity.com/paper/2605.12088/) (2026)
- [Towards Generalized Multi-Image Editing for Unified Multimodal Models](https://mlsanity.com/paper/2601.05572/) (2026)
- [Hierarchical Concept-to-Appearance Guidance for Multi-Subject Image Generation](https://mlsanity.com/paper/2602.03448/) (2026)
- [FreeFuse: Multi-Subject LoRA Fusion via Adaptive Token-Level Routing at Test Time](https://mlsanity.com/paper/2510.23515/) (2025)
- [AnyPhoto: Multi-Person Identity Preserving Image Generation with ID Adaptive Modulation on Location Canvas](https://mlsanity.com/paper/2603.14770/) (2026)
- [Squeezing Capacity from Multimodal Large Language Models for Subject-driven Generation](https://mlsanity.com/paper/2605.26111/) (2026)
- [CRAFT: Constrained Reward via Attention Fine-Tuning for Subject Personalization without Composed Targets](https://mlsanity.com/paper/2608.14403/) (2026)
- [WithEveryone: Unified Planning and Identity Grounding for Group Image Generation](https://mlsanity.com/paper/2608.20336/) (2026)
- [JewelTry: Mask-Free Scale Aware Jewelry Virtual Try-On](https://mlsanity.com/paper/2609.16626/) (2026)
- [From Prompting to Composing: A Spatial Canvas Interface for Poster Generation](https://mlsanity.com/paper/2610.12230/) (2026)

## Abstract (arXiv)

Recent advancements in image customization exhibit a wide range of application prospects due to stronger customization capabilities. However, since we humans are more sensitive to faces, a significant challenge remains in preserving consistent identity while avoiding identity confusion with multi-reference images, limiting the identity scalability of customization models. To address this, we present UMO, a Unified Multi-identity Optimization framework, designed to maintain high-fidelity identity preservation and alleviate identity confusion with scalability. With "multi-to-multi matching" paradigm, UMO reformulates multi-identity generation as a global assignment optimization problem and unleashes multi-identity consistency for existing image customization methods generally through reinforcement learning on diffusion models. To facilitate the training of UMO, we develop a scalable customization dataset with multi-reference images, consisting of both synthesised and real parts. Additionally, we propose a new metric to measure identity confusion. Extensive experiments demonstrate that UMO not only improves identity consistency significantly, but also reduces identity confusion on several image customization methods, setting a new state-of-the-art among open-source methods along the dimension of identity preserving. Code and model: https://github.com/bytedance/UMO