PIPBench: A Profile-Inclusive Framework for Personalized Image Generation Evaluation
Not on the map. Why?
Abstract (arXiv)
Recent text-to-image models such as DALLE-3 excel at following diverse prompts yet remain blind to individual aesthetic preferences. We study personalized image generation, where models must align outputs with a user's implicit visual preferences based on a few historically preferred images and a short prompt. To this end, we introduce PIPBench, the first profile-inclusive benchmark for evaluating personalized image generation. We further propose a novel data construction pipeline that leverages psychological and demographic profiling dimensions for both real-user data collection and scalable agent-based data generation. Using PIPBench, we conduct a thorough evaluation of representative line of methods. Our experiments reveal key limitations in existing methods, suggesting new challenges and opportunities for personalized text-to-image synthesis. Project page: https://wuyuhang05.github.io/PIPBench/
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 30 of its 46 references that are in the map. First posted on arXiv 7 Jul 2026.
Builds on
30 of 46 references.
References · 30
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
- 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
- 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
- 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
- 2025Qwen2.5-VL Technical Reportcited by 5,587
- 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
- 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
- 2025Qwen3-VL Technical Reportcited by 2,793
- 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,424
- 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,245
- 2023ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generationcited by 1,045
- 2025Qwen-Image Technical Reportcited by 1,044
18 more
- 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 991
- 2025OpenAI GPT-5 System Cardcited by 989
- 2023Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generationcited by 977
- 2023Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystackcited by 279
- 2023Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfercited by 196
- 2024DreamBench++: A Human-Aligned Benchmark for Personalized Image Generationcited by 131
- 2024GenAI Arena: An Open Evaluation Platform for Generative Modelscited by 82
- 2019POG: Personalized Outfit Generation for Fashion Recommendation at Alibaba iFashioncited by 64
- 2023ArtBank: Artistic Style Transfer with Pre-trained Diffusion Model and Implicit Style Prompt Bankcited by 36
- 2025Investigating Non-Transitivity in LLM-as-a-Judgecited by 34
- 2023Tailored Visions: Enhancing Text-to-Image Generation with Personalized Prompt Rewritingcited by 23
- 2023FABRIC: Personalizing Diffusion Models with Iterative Feedbackcited by 19
- 2024ViPer: Visual Personalization of Generative Models via Individual Preference Learningcited by 17
- 2024Personalized Image Generation with Large Multimodal Modelscited by 15
- 2025Draw Your Mind: Personalized Generation via Condition-Level Modeling in Text-to-Image Diffusion Modelscited by 5
- 2025Learning User Preferences for Image Generation Modelcited by 5
- 2025Instant Preference Alignment for Text-to-Image Diffusion Modelscited by 4
- 2025PrefGen: Multimodal Preference Learning for Preference-Conditioned Image Generationcited by 3
Built on by
Citing papers per year: 2026: 1.
1 paper.