# PSR: Scaling Multi-Subject Personalized Image Generation with Pairwise Subject-Consistency Rewards

arXiv: https://arxiv.org/abs/2512.01236 · HTML: https://mlsanity.com/paper/2512.01236/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 52 references that are in the map.
- First posted on arXiv 1 Dec 2025.

## Builds on (most cited first, 30 of 45)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [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)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [Flow-GRPO: Training Flow Matching Models via Online RL](https://mlsanity.com/paper/2505.05470/) (2025)
- [DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models](https://mlsanity.com/paper/2305.16381/) (2023)
- [Directly Fine-Tuning Diffusion Models on Differentiable Rewards](https://mlsanity.com/paper/2309.17400/) (2023)
- [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)
- [OminiControl: Minimal and Universal Control for Diffusion Transformer](https://mlsanity.com/paper/2411.15098/) (2024)
- [PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding](https://mlsanity.com/paper/2312.04461/) (2023)
- [Aligning Text-to-Image Diffusion Models with Reward Backpropagation](https://mlsanity.com/paper/2310.03739/) (2023)
- [OmniGen2: Towards Instruction-Aligned Multimodal Generation](https://mlsanity.com/paper/2506.18871/) (2025)
- [HPSv3: Towards Wide-Spectrum Human Preference Score](https://mlsanity.com/paper/2508.03789/) (2025)
- [T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT](https://mlsanity.com/paper/2505.00703/) (2025)
- [VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation](https://mlsanity.com/paper/2412.21059/) (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)

## Built on by (most cited first, 9 of 9)

- [Scaling Multi-Reference Image Generation with Dynamic Reward Optimization](https://mlsanity.com/paper/2606.26947/) (2026)
- [Advances in GRPO for Generation Models: A Survey](https://mlsanity.com/paper/2603.06623/) (2026)
- [When Identities Collapse: A Stress-Test Benchmark for Multi-Subject Personalization](https://mlsanity.com/paper/2603.26078/) (2026)
- [UniCustom: Unified Visual Conditioning for Multi-Reference Image Generation](https://mlsanity.com/paper/2605.12088/) (2026)
- [MIBE: Multi-subject Interaction Benchmark and Evaluator for Personalized Image Generation](https://mlsanity.com/paper/2607.01383/) (2026)
- [MPIE-Bench: Benchmarking Anatomically Plausible Multi-Person Interaction Editing](https://mlsanity.com/paper/2607.27616/) (2026)
- [Squeezing Capacity from Multimodal Large Language Models for Subject-driven Generation](https://mlsanity.com/paper/2605.26111/) (2026)
- [CopyCat: Improving Fine-Grained Subject Consistency in Subject-to-Image Models within Seconds](https://mlsanity.com/paper/2608.00674/) (2026)
- [Visual Jev Rewards: Reference-Bound Verification for Multi-Subject Image Generation](https://mlsanity.com/paper/2610.09328/) (2026)

## Abstract (arXiv)

Personalized generation models for a single subject have demonstrated remarkable effectiveness, highlighting their significant potential. However, when extended to multiple subjects, existing models often exhibit degraded performance, particularly in maintaining subject consistency and adhering to textual prompts. We attribute these limitations to the absence of high-quality multi-subject datasets and refined post-training strategies. To address these challenges, we propose a scalable multi-subject data generation pipeline that leverages powerful single-subject generation models to construct diverse and high-quality multi-subject training data. Through this dataset, we first enable single-subject personalization models to acquire knowledge of synthesizing multi-image and multi-subject scenarios. Furthermore, to enhance both subject consistency and text controllability, we design a set of Pairwise Subject-Consistency Rewards and general-purpose rewards, which are incorporated into a refined reinforcement learning stage. To comprehensively evaluate multi-subject personalization, we introduce a new benchmark that assesses model performance using seven subsets across three dimensions. Extensive experiments demonstrate the effectiveness of our approach in advancing multi-subject personalized image generation. Github Link: https://github.com/wang-shulei/PSR