DreamPoster：面向圖像條件生成海報設計的統一框架

摘要

我們推出DreamPoster，這是一個文本到圖像生成框架，能夠智慧地從用戶提供的圖像和文本提示中合成高品質海報，同時保持內容的忠實度，並支持靈活的解析度和佈局輸出。具體而言，DreamPoster基於我們的T2I模型Seedream3.0，統一處理不同類型的海報生成任務。在數據集構建方面，我們提出了一個系統化的數據註釋流程，精確標註海報圖像中的文本內容和排版層次信息，並採用全面的方法來構建包含源材料（如原始圖形/文本）及其對應最終海報輸出的配對數據集。此外，我們實施了一種漸進式訓練策略，使模型能夠分層次地獲得多任務生成能力，同時保持高品質的生成效果。在我們的測試基準上的評估顯示，DreamPoster在現有方法中表現優異，達到了88.55%的高可用率，相比之下，GPT-4o為47.56%，SeedEdit3.0為25.96%。DreamPoster將在吉夢及其他字節跳動應用中上線。

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.

DreamPoster：面向圖像條件生成海報設計的統一框架

DreamPoster: A Unified Framework for Image-Conditioned Generative Poster Design

摘要

Support