Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2507.09573 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912479338037248 |
|---|---|
| author | Wang, Zhe Zhang, Jingbo Wei, Tianyi Su, Wanchao Wang, Can |
| author_facet | Wang, Zhe Zhang, Jingbo Wei, Tianyi Su, Wanchao Wang, Can |
| contents | Artistic typography aims to stylize input characters with visual effects that are both creative and legible. Traditional approaches rely heavily on manual design, while recent generative models, particularly diffusion-based methods, have enabled automated character stylization. However, existing solutions remain limited in interactivity, lacking support for localized edits, iterative refinement, multi-character composition, and open-ended prompt interpretation. We introduce WordCraft, an interactive artistic typography system that integrates diffusion models to address these limitations. WordCraft features a training-free regional attention mechanism for precise, multi-region generation and a noise blending that supports continuous refinement without compromising visual quality. To support flexible, intent-driven generation, we incorporate a large language model to parse and structure both concrete and abstract user prompts. These components allow our framework to synthesize high-quality, stylized typography across single- and multi-character inputs across multiple languages, supporting diverse user-centered workflows. Our system significantly enhances interactivity in artistic typography synthesis, opening up creative possibilities for artists and designers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_09573 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | WordCraft: Interactive Artistic Typography with Attention Awareness and Noise Blending Wang, Zhe Zhang, Jingbo Wei, Tianyi Su, Wanchao Wang, Can Computer Vision and Pattern Recognition Artistic typography aims to stylize input characters with visual effects that are both creative and legible. Traditional approaches rely heavily on manual design, while recent generative models, particularly diffusion-based methods, have enabled automated character stylization. However, existing solutions remain limited in interactivity, lacking support for localized edits, iterative refinement, multi-character composition, and open-ended prompt interpretation. We introduce WordCraft, an interactive artistic typography system that integrates diffusion models to address these limitations. WordCraft features a training-free regional attention mechanism for precise, multi-region generation and a noise blending that supports continuous refinement without compromising visual quality. To support flexible, intent-driven generation, we incorporate a large language model to parse and structure both concrete and abstract user prompts. These components allow our framework to synthesize high-quality, stylized typography across single- and multi-character inputs across multiple languages, supporting diverse user-centered workflows. Our system significantly enhances interactivity in artistic typography synthesis, opening up creative possibilities for artists and designers. |
| title | WordCraft: Interactive Artistic Typography with Attention Awareness and Noise Blending |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.09573 |