Saved in:
Bibliographic Details
Main Authors: Hu, Xiwei, Chen, Haokun, Qi, Zhongqi, Zhang, Hui, Hong, Dexiang, Shao, Jie, Wu, Xinglong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.04218
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913929492430848
author Hu, Xiwei
Chen, Haokun
Qi, Zhongqi
Zhang, Hui
Hong, Dexiang
Shao, Jie
Wu, Xinglong
author_facet Hu, Xiwei
Chen, Haokun
Qi, Zhongqi
Zhang, Hui
Hong, Dexiang
Shao, Jie
Wu, Xinglong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_04218
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DreamPoster: A Unified Framework for Image-Conditioned Generative Poster Design
Hu, Xiwei
Chen, Haokun
Qi, Zhongqi
Zhang, Hui
Hong, Dexiang
Shao, Jie
Wu, Xinglong
Computer Vision and Pattern Recognition
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.
title DreamPoster: A Unified Framework for Image-Conditioned Generative Poster Design
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.04218