PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918057037791232 |
|---|---|
| author | Chen, SiXiang Lai, Jianyu Gao, Jialin Ye, Tian Chen, Haoyu Shi, Hengyu Shao, Shitong Lin, Yunlong Fei, Song Xing, Zhaohu Jin, Yeying Luo, Junfeng Wei, Xiaoming Zhu, Lei |
| author_facet | Chen, SiXiang Lai, Jianyu Gao, Jialin Ye, Tian Chen, Haoyu Shi, Hengyu Shao, Shitong Lin, Yunlong Fei, Song Xing, Zhaohu Jin, Yeying Luo, Junfeng Wei, Xiaoming Zhu, Lei |
| contents | Generating aesthetic posters is more challenging than simple design images: it requires not only precise text rendering but also the seamless integration of abstract artistic content, striking layouts, and overall stylistic harmony. To address this, we propose PosterCraft, a unified framework that abandons prior modular pipelines and rigid, predefined layouts, allowing the model to freely explore coherent, visually compelling compositions. PosterCraft employs a carefully designed, cascaded workflow to optimize the generation of high-aesthetic posters: (i) large-scale text-rendering optimization on our newly introduced Text-Render-2M dataset; (ii) region-aware supervised fine-tuning on HQ-Poster100K; (iii) aesthetic-text-reinforcement learning via best-of-n preference optimization; and (iv) joint vision-language feedback refinement. Each stage is supported by a fully automated data-construction pipeline tailored to its specific needs, enabling robust training without complex architectural modifications. Evaluated on multiple experiments, PosterCraft significantly outperforms open-source baselines in rendering accuracy, layout coherence, and overall visual appeal-approaching the quality of SOTA commercial systems. Our code, models, and datasets can be found in the Project page: https://ephemeral182.github.io/PosterCraft |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_10741 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework Chen, SiXiang Lai, Jianyu Gao, Jialin Ye, Tian Chen, Haoyu Shi, Hengyu Shao, Shitong Lin, Yunlong Fei, Song Xing, Zhaohu Jin, Yeying Luo, Junfeng Wei, Xiaoming Zhu, Lei Computer Vision and Pattern Recognition Generating aesthetic posters is more challenging than simple design images: it requires not only precise text rendering but also the seamless integration of abstract artistic content, striking layouts, and overall stylistic harmony. To address this, we propose PosterCraft, a unified framework that abandons prior modular pipelines and rigid, predefined layouts, allowing the model to freely explore coherent, visually compelling compositions. PosterCraft employs a carefully designed, cascaded workflow to optimize the generation of high-aesthetic posters: (i) large-scale text-rendering optimization on our newly introduced Text-Render-2M dataset; (ii) region-aware supervised fine-tuning on HQ-Poster100K; (iii) aesthetic-text-reinforcement learning via best-of-n preference optimization; and (iv) joint vision-language feedback refinement. Each stage is supported by a fully automated data-construction pipeline tailored to its specific needs, enabling robust training without complex architectural modifications. Evaluated on multiple experiments, PosterCraft significantly outperforms open-source baselines in rendering accuracy, layout coherence, and overall visual appeal-approaching the quality of SOTA commercial systems. Our code, models, and datasets can be found in the Project page: https://ephemeral182.github.io/PosterCraft |
| title | PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.10741 |