# Premier: Personalized Preference Modulation with Learnable User Embedding in Text-to-Image Generation

arXiv: https://arxiv.org/abs/2603.20725 · HTML: https://mlsanity.com/paper/2603.20725/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and multimodal model alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 45 of its 50 references that are in the map.
- First posted on arXiv 21 Mar 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)

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

- [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)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [Emerging Properties in Unified Multimodal Pretraining](https://mlsanity.com/paper/2505.14683/) (2025)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [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)
- [Understanding and Improving Layer Normalization](https://mlsanity.com/paper/1911.07013/) (2019)
- [Optimizing Prompts for Text-to-Image Generation](https://mlsanity.com/paper/2212.09611/) (2022)
- [InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation](https://mlsanity.com/paper/2404.02733/) (2024)
- [LEDITS++: Limitless Image Editing using Text-to-Image Models](https://mlsanity.com/paper/2311.16711/) (2023)
- [Prodigy: An Expeditiously Adaptive Parameter-Free Learner](https://mlsanity.com/paper/2306.06101/) (2023)
- [Diffuse and Disperse: Image Generation with Representation Regularization](https://mlsanity.com/paper/2506.09027/) (2025)
- [XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation](https://mlsanity.com/paper/2506.21416/) (2025)
- [TokenVerse: Versatile Multi-concept Personalization in Token Modulation Space](https://mlsanity.com/paper/2501.12224/) (2025)
- [Dynamic Prompt Optimizing for Text-to-Image Generation](https://mlsanity.com/paper/2404.04095/) (2024)
- [Exploring the Role of Large Language Models in Prompt Encoding for Diffusion Models](https://mlsanity.com/paper/2406.11831/) (2024)
- [StyleAdapter: A Unified Stylized Image Generation Model](https://mlsanity.com/paper/2309.01770/) (2023)
- [StyleTokenizer: Defining Image Style by a Single Instance for Controlling Diffusion Models](https://mlsanity.com/paper/2409.02543/) (2024)
- [OmniStyle: Filtering High Quality Style Transfer Data at Scale](https://mlsanity.com/paper/2505.14028/) (2025)
- [EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM](https://mlsanity.com/paper/2412.09618/) (2024)
- [Tailored Visions: Enhancing Text-to-Image Generation with Personalized Prompt Rewriting](https://mlsanity.com/paper/2310.08129/) (2023)
- [Personalized Preference Fine-tuning of Diffusion Models](https://mlsanity.com/paper/2501.06655/) (2025)
- [The Devil is in the Prompts: Retrieval-Augmented Prompt Optimization for Text-to-Video Generation](https://mlsanity.com/paper/2504.11739/) (2025)

## Built on by (most cited first, 3 of 3)

- [FreeStyle: Free Control of Style-Content Dual-Reference Generation from Community LoRA Mining](https://mlsanity.com/paper/2606.20506/) (2026)
- [Deeply Interleaved Text-Image Contexts for Multimodal LLMs Assessment](https://mlsanity.com/paper/2609.02573/) (2026)
- [Personalize at Test Time: Learning User Preferences for Image Generation](https://mlsanity.com/paper/2610.09015/) (2026)

## Abstract (arXiv)

Text-to-image generation has advanced rapidly, yet it still struggles to capture the nuanced user preferences. Existing approaches typically rely on multimodal large language models to infer user preferences, but the derived prompts or latent codes rarely reflect them faithfully, leading to suboptimal personalization. We present Premier, a novel preference modulation framework for personalized image generation. Premier represents each user's preference as a learnable embedding and introduces a preference adapter that fuses the user embedding with the text prompt. To enable accurate and fine-grained preference control, the fused preference embedding is further used to modulate the generative process. To enhance the distinctness of individual preference and improve alignment between outputs and user-specific styles, we incorporate a dispersion loss that enforces separation among user embeddings. When user data are scarce, new users are represented as linear combinations of existing preference embeddings learned during training, enabling effective generalization. Experiments show that Premier outperforms prior methods under the same history length, achieving stronger preference alignment and superior performance on text consistency, ViPer proxy metrics, and expert evaluations.