PosterText: Towards Unified Visual Text Generation and Editing for E-commerce Poster
2026-08-17 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors address the challenge of automatically making both new e-commerce posters and editing existing ones easily and accurately. They treat parts of the poster text as small blocks called text patches and support four main actions: creating posters, adding, deleting, or changing these text patches, with optional style control. They developed a model named PosterText, trained through several steps to learn how to do these tasks well. They also created a large dataset and tests to measure how well their model works. Their experiments show PosterText performs well compared to other methods.
E-commerce postersText patchPoster generationPoster editingInstruction-following trainingReinforcement learningSelf-distillationCurriculum learningStyle controlDataset annotation
Authors
Xiaoan Liu, Lichen Ma, Zipeng Guo, Yu He, Xiaoyan Su, Shaojie Guo, Jingling Fu, Xiaolong Fu, Hao Yang, Tongxuan Liu, Yu Guo, Fei Wang, Xinyi Liu, Yongjun Zhang, Junshi Huang
Abstract
Automated e-commerce poster design requires both high-quality poster generation and flexible editing of existing designs. However, most existing methods either target end-to-end poster generation or follow multi-stage design pipelines, with limited capability for flexible and precise editing of existing posters. To enable unified generation and editing of e-commerce posters, we introduce Text Patch Generation and Editing, a unified task formulation that treats text patches as atomic units and covers four operations: poster generation, patch addition, patch deletion, and patch modification, with optional reference-guided style control. Based on this, we propose PosterText, a unified model trained with a four-stage curriculum, including text rendering pretraining, instruction-following training, reinforcement learning for preference alignment, and spatial guidance self-distillation for execution refinement. We further construct a large-scale dataset with patch-level annotations and a comprehensive benchmark for evaluation. Extensive experiments demonstrate that PosterText achieves competitive performance against existing generation and editing approaches, validating the effectiveness of the proposed framework.