Griffin: Generative Reference and Layout Guided Image Composition
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914066662948864 |
|---|---|
| author | Mikaeili, Aryan Alimohammadi, Amirhossein Hassanpour, Negar Mahdavi-Amiri, Ali Tagliasacchi, Andrea |
| author_facet | Mikaeili, Aryan Alimohammadi, Amirhossein Hassanpour, Negar Mahdavi-Amiri, Ali Tagliasacchi, Andrea |
| contents | Text-to-image models have achieved a level of realism that enables the generation of highly convincing images. However, text-based control can be a limiting factor when more explicit guidance is needed. Defining both the content and its precise placement within an image is crucial for achieving finer control. In this work, we address the challenge of multi-image layout control, where the desired content is specified through images rather than text, and the model is guided on where to place each element. Our approach is training-free, requires a single image per reference, and provides explicit and simple control for object and part-level composition. We demonstrate its effectiveness across various image composition tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_23643 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Griffin: Generative Reference and Layout Guided Image Composition Mikaeili, Aryan Alimohammadi, Amirhossein Hassanpour, Negar Mahdavi-Amiri, Ali Tagliasacchi, Andrea Computer Vision and Pattern Recognition Text-to-image models have achieved a level of realism that enables the generation of highly convincing images. However, text-based control can be a limiting factor when more explicit guidance is needed. Defining both the content and its precise placement within an image is crucial for achieving finer control. In this work, we address the challenge of multi-image layout control, where the desired content is specified through images rather than text, and the model is guided on where to place each element. Our approach is training-free, requires a single image per reference, and provides explicit and simple control for object and part-level composition. We demonstrate its effectiveness across various image composition tasks. |
| title | Griffin: Generative Reference and Layout Guided Image Composition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.23643 |