Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2404.19427 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913336370659328 |
|---|---|
| author | Kim, Chanran Lee, Jeongin Joung, Shichang Kim, Bongmo Baek, Yeul-Min |
| author_facet | Kim, Chanran Lee, Jeongin Joung, Shichang Kim, Bongmo Baek, Yeul-Min |
| contents | In the field of personalized image generation, the ability to create images preserving concepts has significantly improved. Creating an image that naturally integrates multiple concepts in a cohesive and visually appealing composition can indeed be challenging. This paper introduces "InstantFamily," an approach that employs a novel masked cross-attention mechanism and a multimodal embedding stack to achieve zero-shot multi-ID image generation. Our method effectively preserves ID as it utilizes global and local features from a pre-trained face recognition model integrated with text conditions. Additionally, our masked cross-attention mechanism enables the precise control of multi-ID and composition in the generated images. We demonstrate the effectiveness of InstantFamily through experiments showing its dominance in generating images with multi-ID, while resolving well-known multi-ID generation problems. Additionally, our model achieves state-of-the-art performance in both single-ID and multi-ID preservation. Furthermore, our model exhibits remarkable scalability with a greater number of ID preservation than it was originally trained with. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_19427 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | InstantFamily: Masked Attention for Zero-shot Multi-ID Image Generation Kim, Chanran Lee, Jeongin Joung, Shichang Kim, Bongmo Baek, Yeul-Min Computer Vision and Pattern Recognition In the field of personalized image generation, the ability to create images preserving concepts has significantly improved. Creating an image that naturally integrates multiple concepts in a cohesive and visually appealing composition can indeed be challenging. This paper introduces "InstantFamily," an approach that employs a novel masked cross-attention mechanism and a multimodal embedding stack to achieve zero-shot multi-ID image generation. Our method effectively preserves ID as it utilizes global and local features from a pre-trained face recognition model integrated with text conditions. Additionally, our masked cross-attention mechanism enables the precise control of multi-ID and composition in the generated images. We demonstrate the effectiveness of InstantFamily through experiments showing its dominance in generating images with multi-ID, while resolving well-known multi-ID generation problems. Additionally, our model achieves state-of-the-art performance in both single-ID and multi-ID preservation. Furthermore, our model exhibits remarkable scalability with a greater number of ID preservation than it was originally trained with. |
| title | InstantFamily: Masked Attention for Zero-shot Multi-ID Image Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.19427 |