One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915137997242368 |
|---|---|
| author | Liu, Tao Wang, Kai Li, Senmao van de Weijer, Joost Khan, Fahad Shahbaz Yang, Shiqi Wang, Yaxing Yang, Jian Cheng, Ming-Ming |
| author_facet | Liu, Tao Wang, Kai Li, Senmao van de Weijer, Joost Khan, Fahad Shahbaz Yang, Shiqi Wang, Yaxing Yang, Jian Cheng, Ming-Ming |
| contents | Text-to-image generation models can create high-quality images from input prompts. However, they struggle to support the consistent generation of identity-preserving requirements for storytelling. Existing approaches to this problem typically require extensive training in large datasets or additional modifications to the original model architectures. This limits their applicability across different domains and diverse diffusion model configurations. In this paper, we first observe the inherent capability of language models, coined context consistency, to comprehend identity through context with a single prompt. Drawing inspiration from the inherent context consistency, we propose a novel training-free method for consistent text-to-image (T2I) generation, termed "One-Prompt-One-Story" (1Prompt1Story). Our approach 1Prompt1Story concatenates all prompts into a single input for T2I diffusion models, initially preserving character identities. We then refine the generation process using two novel techniques: Singular-Value Reweighting and Identity-Preserving Cross-Attention, ensuring better alignment with the input description for each frame. In our experiments, we compare our method against various existing consistent T2I generation approaches to demonstrate its effectiveness through quantitative metrics and qualitative assessments. Code is available at https://github.com/byliutao/1Prompt1Story. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_13554 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt Liu, Tao Wang, Kai Li, Senmao van de Weijer, Joost Khan, Fahad Shahbaz Yang, Shiqi Wang, Yaxing Yang, Jian Cheng, Ming-Ming Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Text-to-image generation models can create high-quality images from input prompts. However, they struggle to support the consistent generation of identity-preserving requirements for storytelling. Existing approaches to this problem typically require extensive training in large datasets or additional modifications to the original model architectures. This limits their applicability across different domains and diverse diffusion model configurations. In this paper, we first observe the inherent capability of language models, coined context consistency, to comprehend identity through context with a single prompt. Drawing inspiration from the inherent context consistency, we propose a novel training-free method for consistent text-to-image (T2I) generation, termed "One-Prompt-One-Story" (1Prompt1Story). Our approach 1Prompt1Story concatenates all prompts into a single input for T2I diffusion models, initially preserving character identities. We then refine the generation process using two novel techniques: Singular-Value Reweighting and Identity-Preserving Cross-Attention, ensuring better alignment with the input description for each frame. In our experiments, we compare our method against various existing consistent T2I generation approaches to demonstrate its effectiveness through quantitative metrics and qualitative assessments. Code is available at https://github.com/byliutao/1Prompt1Story. |
| title | One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2501.13554 |