Lune

ICLR2025顶会

MetaDesigner: Advancing Artistic Typography through AI-Driven, User-Centric, and Multilingual WordArt Synthesis

Jun-Yan He, Zhi-Qi Cheng, Chenyang Li, Jingdong Sun, Qi He, Wangmeng Xiang, Hanyuan Chen, Jin-Peng Lan, Xianhui Lin, Kang Zhu, Bin Luo, Yifeng Geng

问 Lune

摘要

MetaDesigner introduces a transformative framework for artistic typography synthesis, powered by Large Language Models (LLMs) and grounded in a user-centric design paradigm. Its foundation is a multi-agent system comprising the Pipeline, Glyph, and Texture agents, which collectively orchestrate the creation of customizable WordArt, ranging from semantic enhancements to intricate textural elements. A central feedback mechanism leverages insights from both multimodal models and user evaluations, enabling iterative refinement of design parameters. Through this iterative process, MetaDesigner dynamically adjusts hyperparameters to align with user-defined stylistic and thematic preferences, consistently delivering WordArt that excels in visual quality and contextual resonance. Empirical evaluations underscore the system's versatility and effectiveness across diverse WordArt applications, yielding outputs that are both aesthetically compelling and context-sensitive.

问 Lune

尽管问,回答会引用原文。

Lune 会读完全文和相关的 Paper,每个回答都附上所依据的原文段落。

可以从这些问题问起

Lune 的依据

全文 · 引用它的 2 篇顶会 Paper · 相关的 Paper

获取答案

免费开始,无需绑卡

引用它的顶会 Paper2

  1. POPoS: Improving Efficient and Robust Facial Landmark Detection with Parallel Optimal Position SearchChong-Yang Xiang, Jun-Yan He, Zhi-Qi Cheng, Xiao Wu 等AAAI 2025 · 3 次引用
  2. OneFont: A Unified Agent for End-to-End Font CreationYingxin Lai, Yufei Liu, Guoqing Yang, Jiaxing Chai 等AAAI 2026

它引用的 Paper23

  1. Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 次引用
  2. Diffusion Models Beat GANs on Image SynthesisPrafulla Dhariwal, Alexander Quinn NicholNeurIPS 2021 · 13,211 次引用
  3. High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 13,123 次引用
  4. Photorealistic Text-to-Image Diffusion Models with Deep Language UnderstandingChitwan Saharia, William Chan, Saurabh Saxena, Lala Li 等NeurIPS 2022 · 8,965 次引用
  5. Adding Conditional Control to Text-to-Image Diffusion ModelsLvmin Zhang, Anyi Rao, Maneesh AgrawalaICCV 2023 · 6,759 次引用

相关 Paper

  1. PosterGen: Aesthetic-Aware Multi-Modal Paper-to-Poster Generation Via Multi-Agent LLMsZhilin Zhang, Xiang Zhang, Jiaqi Wei, Yiwei Xu, Chenyu YouCVPR Findings 2026
  2. V-Stylist: Video Stylization via Collaboration and Reflection of MLLM AgentsZhengrong Yue, Shaobin Zhuang, Kunchang Li, Yanbo Ding 等CVPR 2025
  3. WRitEer: A Multi-Objective, Preference-Driven Multi-Agent Framework for Human-Like Advanced Text GenerationJunchuan Yu, Yuyang SunAAAI 2026
  4. DS-Fusion: Artistic Typography via Discriminated and Stylized DiffusionMaham Tanveer, Yizhi Wang, Ali Mahdavi-Amiri, Hao ZhangICCV 2023 · 37 次引用
  5. ChatPattern: Layout Pattern Customization via Natural LanguageZixiao Wang, Yunheng Shen, Xufeng Yao, Wenqian Zhao 等DAC 2024 · 9 次引用
黄昏的海面,两侧是细线勾勒的悬崖