ObjectAdd: Adding Objects into Image via a Training-Free Diffusion Modification Fashion
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909955377856512 |
|---|---|
| author | Zhang, Ziyue Lin, Mingbao Song, Quanjian Zhang, Yuxin Ji, Rongrong |
| author_facet | Zhang, Ziyue Lin, Mingbao Song, Quanjian Zhang, Yuxin Ji, Rongrong |
| contents | We introduce ObjectAdd, a training-free diffusion modification method to add user-expected objects into user-specified area. The motive of ObjectAdd stems from: first, describing everything in one prompt can be difficult, and second, users often need to add objects into the generated image. To accommodate with real world, our ObjectAdd maintains accurate image consistency after adding objects with technical innovations in: (1) embedding-level concatenation to ensure correct text embedding coalesce; (2) object-driven layout control with latent and attention injection to ensure objects accessing user-specified area; (3) prompted image inpainting in an attention refocusing & object expansion fashion to ensure rest of the image stays the same. With a text-prompted image, our ObjectAdd allows users to specify a box and an object, and achieves: (1) adding object inside the box area; (2) exact content outside the box area; (3) flawless fusion between the two areas |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_17230 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ObjectAdd: Adding Objects into Image via a Training-Free Diffusion Modification Fashion Zhang, Ziyue Lin, Mingbao Song, Quanjian Zhang, Yuxin Ji, Rongrong Computer Vision and Pattern Recognition We introduce ObjectAdd, a training-free diffusion modification method to add user-expected objects into user-specified area. The motive of ObjectAdd stems from: first, describing everything in one prompt can be difficult, and second, users often need to add objects into the generated image. To accommodate with real world, our ObjectAdd maintains accurate image consistency after adding objects with technical innovations in: (1) embedding-level concatenation to ensure correct text embedding coalesce; (2) object-driven layout control with latent and attention injection to ensure objects accessing user-specified area; (3) prompted image inpainting in an attention refocusing & object expansion fashion to ensure rest of the image stays the same. With a text-prompted image, our ObjectAdd allows users to specify a box and an object, and achieves: (1) adding object inside the box area; (2) exact content outside the box area; (3) flawless fusion between the two areas |
| title | ObjectAdd: Adding Objects into Image via a Training-Free Diffusion Modification Fashion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.17230 |