Papers
arxiv:2603.20725

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

Published on Mar 21
Authors:
,
,
,
,
,
,

Abstract

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.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2603.20725
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2603.20725 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2603.20725 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2603.20725 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.