Influencer: Empowering Everyday Users in Creating Promotional Posts via AI-infused Exploration and Customization
Xuye Liu, Annie Sun, Pengcheng An, Tengfei Ma, Jian Zhao
摘要
Creating promotional posts on social platforms enables everyday users to disseminate their creative outcomes, engage in community exchanges, or generate additional income from micro-businesses. However, crafting eye-catching posts with appealing images and effective captions can be challenging and time-consuming for everyday users since they are mostly design novices. We propose Influencer, an interactive tool that helps novice creators quickly generate ideas and create high-quality promotional post designs through AI. Influencer offers a multi-dimensional recommendation system for ideation through example-based image and caption suggestions. Further, Influencer implements a holistic promotional post-design system supporting context-aware exploration considering brand messages and user-specified design constraints, flexible fusion of content, and a mind-map-like layout for idea tracking. Our user study, comparing the system with industry-standard tools, along with two real-life case studies, indicates that Influencer is effective in assisting design novices to generate ideas as well as creative and diverse promotional posts with user-friendly interaction.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper2
- DesignTrace: Exploring, Iterating and Tracking Design Alternatives with GenAIXiaohan Peng, Debanjana Haldar, Wendy E. Mackay, Janin KochCHI 2026 · 被引用 3 次
- InkIdeator: Supporting Chinese-Style Visual Design Ideation via AI-Infused Exploration of Chinese PaintingsShiwei Wu, Ziyao Gao, Zhendong He, Zongtan He 等CHI 2026 · 被引用 1 次
它引用的顶会 Paper12
- Zero-Shot Text-to-Image GenerationAditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray 等ICML 2021 · 被引用 6,356 次
- OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning FrameworkPeng Wang, An Yang, Rui Men, Junyang Lin 等ICML 2022 · 被引用 1,058 次
- An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual InversionRinon Gal, Yuval Alaluf, Yuval Atzmon, Or Patashnik 等ICLR 2023 · 被引用 464 次
- CreativeConnect: Supporting Reference Recombination for Graphic Design Ideation with Generative AIDaEun Choi, Sumin Hong, Jeongeon Park, John Joon Young Chung 等CHI 2024 · 被引用 116 次
- MetaMap: Supporting Visual Metaphor Ideation through Multi-dimensional Example-based ExplorationYouwen Kang, Zhida Sun, Sitong Wang, Zeyu Huang 等CHI 2021 · 被引用 78 次
相关 Paper
- DesignWeaver: Dimensional Scaffolding for Text-to-Image Product DesignSirui Tao, Ivan Liang, Cindy Peng, Zhiqing Wang 等CHI 2025 · 被引用 19 次
- InspirationGraph for Progressive Design Space ExplorationSuxiang Ling, Yi Xiao, Yang Zhou, Ruoxuan Ma 等CHI 2026
- PSDesigner: Automated Graphic Design with a Human-Like Creative WorkflowXincheng Shuai, Song Tang, Yutong Huang, Henghui Ding 等CVPR 2026 · 被引用 1 次
- Promptify: Text-to-Image Generation through Interactive Prompt Exploration with Large Language ModelsStephen Brade, Bryan Wang, Maurício Sousa, Sageev Oore 等UIST 2023 · 被引用 179 次
- ProductMeta: An Interactive System for Metaphorical Product Design Ideation with Multimodal Large Language ModelsQinyi Zhou, Jie Deng, Yu Liu, Yun Wang 等CHI 2025 · 被引用 13 次
