Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2503.23353 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916666335559680 |
|---|---|
| author | Luo, Xiangyang Cheng, Junhao Xie, Yifan Zhang, Xin Feng, Tao Liu, Zhou Ma, Fei Yu, Fei |
| author_facet | Luo, Xiangyang Cheng, Junhao Xie, Yifan Zhang, Xin Feng, Tao Liu, Zhou Ma, Fei Yu, Fei |
| contents | Open-ended story visualization is a challenging task that involves generating coherent image sequences from a given storyline. One of the main difficulties is maintaining character consistency while creating natural and contextually fitting scenes--an area where many existing methods struggle. In this paper, we propose an enhanced Transformer module that uses separate self attention and cross attention mechanisms, leveraging prior knowledge from pre-trained diffusion models to ensure logical scene creation. The isolated self attention mechanism improves character consistency by refining attention maps to reduce focus on irrelevant areas and highlight key features of the same character. Meanwhile, the isolated cross attention mechanism independently processes each character's features, avoiding feature fusion and further strengthening consistency. Notably, our method is training-free, allowing the continuous generation of new characters and storylines without re-tuning. Both qualitative and quantitative evaluations show that our approach outperforms current methods, demonstrating its effectiveness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_23353 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Object Isolated Attention for Consistent Story Visualization Luo, Xiangyang Cheng, Junhao Xie, Yifan Zhang, Xin Feng, Tao Liu, Zhou Ma, Fei Yu, Fei Computer Vision and Pattern Recognition Artificial Intelligence Open-ended story visualization is a challenging task that involves generating coherent image sequences from a given storyline. One of the main difficulties is maintaining character consistency while creating natural and contextually fitting scenes--an area where many existing methods struggle. In this paper, we propose an enhanced Transformer module that uses separate self attention and cross attention mechanisms, leveraging prior knowledge from pre-trained diffusion models to ensure logical scene creation. The isolated self attention mechanism improves character consistency by refining attention maps to reduce focus on irrelevant areas and highlight key features of the same character. Meanwhile, the isolated cross attention mechanism independently processes each character's features, avoiding feature fusion and further strengthening consistency. Notably, our method is training-free, allowing the continuous generation of new characters and storylines without re-tuning. Both qualitative and quantitative evaluations show that our approach outperforms current methods, demonstrating its effectiveness. |
| title | Object Isolated Attention for Consistent Story Visualization |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2503.23353 |