用图文自动生成高质量海报，保持内容一致且支持灵活布局。
DreamPoster: A Unified Framework for Image-Conditioned Generative Poster Design
- 基于Seedream3.0模型统一处理多种海报生成任务。
- 在测试中用户可用率达88.55%，显著优于GPT-4o和SeedEdit3.0。
- 适合需要批量生成设计海报的设计师或企业用户。
我们提出DreamPoster，一个从用户提供的图像和文本提示中智能合成高质量海报的文生图框架，同时保持内容一致性，并支持灵活的分辨率与版式输出。DreamPoster基于我们的T2I模型Seedream3.0，统一处理不同类型的海报生成。在数据集构建方面，提出系统化的标注流程，精确标注海报图像中的文本内容与排版层级信息，并采用综合方法构建包含原始素材（如原始图形/文字）及其对应最终海报输出的配对数据集。此外，实现渐进式训练策略，使模型分层获得多任务生成能力并保持高质量生成效果。在测试基准上的评估表明，DreamPoster优于现有方法，用户可用率达88.55%，远高于GPT-4o的47.56%和SeedEdit3.0的25.96%。DreamPoster将上线字节跳动旗下Jimeng等应用。
原文摘要 · Abstract (English)
We present DreamPoster, a Text-to-Image generation framework that intelligently synthesizes high-quality posters from user-provided images and text prompts while maintaining content fidelity and supporting flexible resolution and layout outputs. Specifically, DreamPoster is built upon our T2I model, Seedream3.0 to uniformly process different poster generating types. For dataset construction, we propose a systematic data annotation pipeline that precisely annotates textual content and typographic hierarchy information within poster images, while employing comprehensive methodologies to construct paired datasets comprising source materials (e.g., raw graphics/text) and their corresponding final poster outputs. Additionally, we implement a progressive training strategy that enables the model to hierarchically acquire multi-task generation capabilities while maintaining high-quality generation. Evaluations on our testing benchmarks demonstrate DreamPoster's superiority over existing methods, achieving a high usability rate of 88.55\%, compared to GPT-4o (47.56\%) and SeedEdit3.0 (25.96\%). DreamPoster will be online in Jimeng and other Bytedance Apps.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。