DeCorStory: Gram-Schmidt Prompt Embedding Decorrelation for Consistent Storytelling
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918318134263808 |
|---|---|
| author | Sarkar, Ayushman Yu, Zhenyu Idris, Mohd Yamani Idna |
| author_facet | Sarkar, Ayushman Yu, Zhenyu Idris, Mohd Yamani Idna |
| contents | Maintaining visual and semantic consistency across frames is a key challenge in text-to-image storytelling. Existing training-free methods, such as One-Prompt-One-Story, concatenate all prompts into a single sequence, which often induces strong embedding correlation and leads to color leakage, background blending, and identity drift. We propose DeCorStory, a training-free inference-time framework that explicitly reduces inter-frame semantic interference. DeCorStory applies Gram-Schmidt prompt embedding decorrelation to orthogonalize frame-level semantics, followed by singular value reweighting to strengthen prompt-specific information and identity-preserving cross-attention to stabilize character identity during diffusion. The method requires no model modification or fine-tuning and can be seamlessly integrated into existing diffusion pipelines. Experiments demonstrate consistent improvements in prompt-image alignment, identity consistency, and visual diversity, achieving state-of-the-art performance among training-free baselines. Code is available at: https://github.com/YuZhenyuLindy/DeCorStory |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_01306 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DeCorStory: Gram-Schmidt Prompt Embedding Decorrelation for Consistent Storytelling Sarkar, Ayushman Yu, Zhenyu Idris, Mohd Yamani Idna Computer Vision and Pattern Recognition Maintaining visual and semantic consistency across frames is a key challenge in text-to-image storytelling. Existing training-free methods, such as One-Prompt-One-Story, concatenate all prompts into a single sequence, which often induces strong embedding correlation and leads to color leakage, background blending, and identity drift. We propose DeCorStory, a training-free inference-time framework that explicitly reduces inter-frame semantic interference. DeCorStory applies Gram-Schmidt prompt embedding decorrelation to orthogonalize frame-level semantics, followed by singular value reweighting to strengthen prompt-specific information and identity-preserving cross-attention to stabilize character identity during diffusion. The method requires no model modification or fine-tuning and can be seamlessly integrated into existing diffusion pipelines. Experiments demonstrate consistent improvements in prompt-image alignment, identity consistency, and visual diversity, achieving state-of-the-art performance among training-free baselines. Code is available at: https://github.com/YuZhenyuLindy/DeCorStory |
| title | DeCorStory: Gram-Schmidt Prompt Embedding Decorrelation for Consistent Storytelling |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.01306 |