ICG: Improving Cover Image Generation via MLLM-based Prompting and Personalized Preference Alignment

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bian, Zhipeng, Zhu, Jieming, Liu, Qijiong, Lin, Wang, Cai, Guohao, Du, Zhaocheng, Sun, Jiacheng, Zhao, Zhou, Dong, Zhenhua
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917536771080192
author Bian, Zhipeng
Zhu, Jieming
Liu, Qijiong
Lin, Wang
Cai, Guohao
Du, Zhaocheng
Sun, Jiacheng
Zhao, Zhou
Dong, Zhenhua
author_facet Bian, Zhipeng
Zhu, Jieming
Liu, Qijiong
Lin, Wang
Cai, Guohao
Du, Zhaocheng
Sun, Jiacheng
Zhao, Zhou
Dong, Zhenhua
contents Recent advances in multimodal large language models (MLLMs) and diffusion models (DMs) have opened new possibilities for AI-generated content. Yet, personalized cover image generation remains underexplored, despite its critical role in boosting user engagement on digital platforms. We propose ICG, a novel framework that integrates MLLM-based prompting with personalized preference alignment to generate high-quality, contextually relevant covers. ICG extracts semantic features from item titles and reference images via meta tokens, refines them with user embeddings, and injects the resulting personalized context into the diffusion model. To address the lack of labeled supervision, we adopt a multi-reward learning strategy that combines public aesthetic and relevance rewards with a personalized preference model trained from user behavior. Unlike prior pipelines relying on handcrafted prompts and disjointed modules, ICG employs an adapter to bridge MLLMs and diffusion models for end-to-end training. Experiments demonstrate that ICG significantly improves image quality, semantic fidelity, and personalization, leading to stronger user appeal and offline recommendation accuracy in downstream tasks. As a plug-and-play adapter bridging MLLMs and diffusion models, ICG is compatible with common checkpoints and requires no ground-truth labels during optimization.
format Preprint
id arxiv_https___arxiv_org_abs_2605_27374
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ICG: Improving Cover Image Generation via MLLM-based Prompting and Personalized Preference Alignment
Bian, Zhipeng
Zhu, Jieming
Liu, Qijiong
Lin, Wang
Cai, Guohao
Du, Zhaocheng
Sun, Jiacheng
Zhao, Zhou
Dong, Zhenhua
Computation and Language
I.2.7; I.2.10
Recent advances in multimodal large language models (MLLMs) and diffusion models (DMs) have opened new possibilities for AI-generated content. Yet, personalized cover image generation remains underexplored, despite its critical role in boosting user engagement on digital platforms. We propose ICG, a novel framework that integrates MLLM-based prompting with personalized preference alignment to generate high-quality, contextually relevant covers. ICG extracts semantic features from item titles and reference images via meta tokens, refines them with user embeddings, and injects the resulting personalized context into the diffusion model. To address the lack of labeled supervision, we adopt a multi-reward learning strategy that combines public aesthetic and relevance rewards with a personalized preference model trained from user behavior. Unlike prior pipelines relying on handcrafted prompts and disjointed modules, ICG employs an adapter to bridge MLLMs and diffusion models for end-to-end training. Experiments demonstrate that ICG significantly improves image quality, semantic fidelity, and personalization, leading to stronger user appeal and offline recommendation accuracy in downstream tasks. As a plug-and-play adapter bridging MLLMs and diffusion models, ICG is compatible with common checkpoints and requires no ground-truth labels during optimization.
title ICG: Improving Cover Image Generation via MLLM-based Prompting and Personalized Preference Alignment
topic Computation and Language
I.2.7; I.2.10
url https://arxiv.org/abs/2605.27374