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

arXiv: https://arxiv.org/abs/2605.27374 · HTML: https://mlsanity.com/paper/2605.27374/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 18 of its 37 references that are in the map.
- First posted on arXiv 8 Apr 2026.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)
- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)
- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)

## Builds on (most cited first, 18 of 18)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing](https://mlsanity.com/paper/2305.14720/) (2023)
- [Generating Images with Multimodal Language Models](https://mlsanity.com/paper/2305.17216/) (2023)
- [Transfer between Modalities with MetaQueries](https://mlsanity.com/paper/2504.06256/) (2025)
- [Making LLaMA SEE and Draw with SEED Tokenizer](https://mlsanity.com/paper/2310.01218/) (2023)
- [JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation](https://mlsanity.com/paper/2411.07975/) (2024)
- [ILLUME: Illuminating Your LLMs to See, Draw, and Self-Enhance](https://mlsanity.com/paper/2412.06673/) (2024)
- [MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation](https://mlsanity.com/paper/2404.05674/) (2024)
- [A New Creative Generation Pipeline for Click-Through Rate with Stable Diffusion Model](https://mlsanity.com/paper/2401.10934/) (2024)
- [LLMGA: Multimodal Large Language Model based Generation Assistant](https://mlsanity.com/paper/2311.16500/) (2023)
- [A User-Friendly Framework for Generating Model-Preferred Prompts in Text-to-Image Synthesis](https://mlsanity.com/paper/2402.12760/) (2024)
- [Conditional Vector Graphics Generation for Music Cover Images](https://mlsanity.com/paper/2205.07301/) (2022)

## Built on by (most cited first, 2 of 2)

- [Agentic Visual Generation: From Generative Models to Agentic Control](https://mlsanity.com/paper/2609.06758/) (2026)
- [UrbanWell: Benchmarking Multimodal Large Language Models for Spatio-Temporal Urban Wellbeing Analytics](https://mlsanity.com/paper/2606.15890/) (2026)

## Abstract (arXiv)

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.