Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2603.05898 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911492474929152 |
|---|---|
| author | Qin, Yuxin Cao, Ke Liu, Haowei Ma, Ao Li, Fengheng Zhu, Honghe Zhang, Zheng Ling, Run Feng, Wei He, Xuanhua Zhang, Zhanjie Guo, Zhen Bian, Haoyi Lv, Jingjing Shen, Junjie Law, Ching |
| author_facet | Qin, Yuxin Cao, Ke Liu, Haowei Ma, Ao Li, Fengheng Zhu, Honghe Zhang, Zheng Ling, Run Feng, Wei He, Xuanhua Zhang, Zhanjie Guo, Zhen Bian, Haoyi Lv, Jingjing Shen, Junjie Law, Ching |
| contents | E-commerce product poster generation aims to automatically synthesize a single image that effectively conveys product information by presenting a subject, text, and a designed style. Recent diffusion models with fine-grained and efficient controllability have advanced product poster synthesis, yet they typically rely on multi-stage pipelines, and simultaneous control over subject, text, and style remains underexplored. Such naive multi-stage pipelines also show three issues: poor subject fidelity, inaccurate text, and inconsistent style. To address these issues, we propose InnoAds-Composer, a single-stage framework that enables efficient tri-conditional control tokens over subject, glyph, and style. To alleviate the quadratic overhead introduced by naive tri-conditional token concatenation, we perform importance analysis over layers and timesteps and route each condition only to the most responsive positions, thereby shortening the active token sequence. Besides, to improve the accuracy of Chinese text rendering, we design a Text Feature Enhancement Module (TFEM) that integrates features from both glyph images and glyph crops. To support training and evaluation, we also construct a high-quality e-commerce product poster dataset and benchmark, which is the first dataset that jointly contains subject, text, and style conditions. Extensive experiments demonstrate that InnoAds-Composer significantly outperforms existing product poster methods without obviously increasing inference latency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_05898 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | InnoAds-Composer: Efficient Condition Composition for E-Commerce Poster Generation Qin, Yuxin Cao, Ke Liu, Haowei Ma, Ao Li, Fengheng Zhu, Honghe Zhang, Zheng Ling, Run Feng, Wei He, Xuanhua Zhang, Zhanjie Guo, Zhen Bian, Haoyi Lv, Jingjing Shen, Junjie Law, Ching Computer Vision and Pattern Recognition E-commerce product poster generation aims to automatically synthesize a single image that effectively conveys product information by presenting a subject, text, and a designed style. Recent diffusion models with fine-grained and efficient controllability have advanced product poster synthesis, yet they typically rely on multi-stage pipelines, and simultaneous control over subject, text, and style remains underexplored. Such naive multi-stage pipelines also show three issues: poor subject fidelity, inaccurate text, and inconsistent style. To address these issues, we propose InnoAds-Composer, a single-stage framework that enables efficient tri-conditional control tokens over subject, glyph, and style. To alleviate the quadratic overhead introduced by naive tri-conditional token concatenation, we perform importance analysis over layers and timesteps and route each condition only to the most responsive positions, thereby shortening the active token sequence. Besides, to improve the accuracy of Chinese text rendering, we design a Text Feature Enhancement Module (TFEM) that integrates features from both glyph images and glyph crops. To support training and evaluation, we also construct a high-quality e-commerce product poster dataset and benchmark, which is the first dataset that jointly contains subject, text, and style conditions. Extensive experiments demonstrate that InnoAds-Composer significantly outperforms existing product poster methods without obviously increasing inference latency. |
| title | InnoAds-Composer: Efficient Condition Composition for E-Commerce Poster Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.05898 |