Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.08784 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914547729694720 |
|---|---|
| author | Cui, Benlei Zeng, Fangao Jiang, Weitao Zhai, Yuwen Hong, Haiwen Huang, Longtao Xue, Hui Shang, Wenxiang Huang, Pipei |
| author_facet | Cui, Benlei Zeng, Fangao Jiang, Weitao Zhai, Yuwen Hong, Haiwen Huang, Longtao Xue, Hui Shang, Wenxiang Huang, Pipei |
| contents | Product poster generation poses distinct challenges beyond general poster design, requiring both faithful preservation of product appearance and precise control over dense, multi-line text layouts. Prior methods typically adopt inpainting frameworks augmented with auxiliary modules such as ControlNet and OCR encoders. However, these approaches introduce architectural complexity and computational overhead while still suffering from text errors and subject extension artifacts. We present SimplePoster, a simple yet effective inpainting-based framework that achieves faithful subject preservation and accurate, position-controllable text rendering without external controllers. Our approach builds on two observations: (1) full-parameter fine-tuning of the base model effectively suppresses subject extension, outperforming ControlNet-based alternatives; and (2) a zero-cost character-level position encoding enables geometry-aware text generation without dedicated layout modules. Experiments show that SimplePoster achieves a $98.7\%$ subject preservation rate, compared to $55.2\%$ for SeedEdit 3.0 and $85.3\%$ for PosterMaker, while also improving text rendering accuracy. Code, models, benchmark and a part of training data will be available at https://github.com/Alibaba-YuFeng/SIMPLEPOSTER |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_08784 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | simpleposter: a simple baseline for product poster generation Cui, Benlei Zeng, Fangao Jiang, Weitao Zhai, Yuwen Hong, Haiwen Huang, Longtao Xue, Hui Shang, Wenxiang Huang, Pipei Computer Vision and Pattern Recognition Product poster generation poses distinct challenges beyond general poster design, requiring both faithful preservation of product appearance and precise control over dense, multi-line text layouts. Prior methods typically adopt inpainting frameworks augmented with auxiliary modules such as ControlNet and OCR encoders. However, these approaches introduce architectural complexity and computational overhead while still suffering from text errors and subject extension artifacts. We present SimplePoster, a simple yet effective inpainting-based framework that achieves faithful subject preservation and accurate, position-controllable text rendering without external controllers. Our approach builds on two observations: (1) full-parameter fine-tuning of the base model effectively suppresses subject extension, outperforming ControlNet-based alternatives; and (2) a zero-cost character-level position encoding enables geometry-aware text generation without dedicated layout modules. Experiments show that SimplePoster achieves a $98.7\%$ subject preservation rate, compared to $55.2\%$ for SeedEdit 3.0 and $85.3\%$ for PosterMaker, while also improving text rendering accuracy. Code, models, benchmark and a part of training data will be available at https://github.com/Alibaba-YuFeng/SIMPLEPOSTER |
| title | simpleposter: a simple baseline for product poster generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.08784 |