PreciseControl: Enhancing Text-To-Image Diffusion Models with Fine-Grained Attribute Control
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929454274576384 |
|---|---|
| author | Parihar, Rishubh VS, Sachidanand Mani, Sabariswaran Karmali, Tejan Babu, R. Venkatesh |
| author_facet | Parihar, Rishubh VS, Sachidanand Mani, Sabariswaran Karmali, Tejan Babu, R. Venkatesh |
| contents | Recently, we have seen a surge of personalization methods for text-to-image (T2I) diffusion models to learn a concept using a few images. Existing approaches, when used for face personalization, suffer to achieve convincing inversion with identity preservation and rely on semantic text-based editing of the generated face. However, a more fine-grained control is desired for facial attribute editing, which is challenging to achieve solely with text prompts. In contrast, StyleGAN models learn a rich face prior and enable smooth control towards fine-grained attribute editing by latent manipulation. This work uses the disentangled $\mathcal{W+}$ space of StyleGANs to condition the T2I model. This approach allows us to precisely manipulate facial attributes, such as smoothly introducing a smile, while preserving the existing coarse text-based control inherent in T2I models. To enable conditioning of the T2I model on the $\mathcal{W+}$ space, we train a latent mapper to translate latent codes from $\mathcal{W+}$ to the token embedding space of the T2I model. The proposed approach excels in the precise inversion of face images with attribute preservation and facilitates continuous control for fine-grained attribute editing. Furthermore, our approach can be readily extended to generate compositions involving multiple individuals. We perform extensive experiments to validate our method for face personalization and fine-grained attribute editing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_05083 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PreciseControl: Enhancing Text-To-Image Diffusion Models with Fine-Grained Attribute Control Parihar, Rishubh VS, Sachidanand Mani, Sabariswaran Karmali, Tejan Babu, R. Venkatesh Computer Vision and Pattern Recognition Recently, we have seen a surge of personalization methods for text-to-image (T2I) diffusion models to learn a concept using a few images. Existing approaches, when used for face personalization, suffer to achieve convincing inversion with identity preservation and rely on semantic text-based editing of the generated face. However, a more fine-grained control is desired for facial attribute editing, which is challenging to achieve solely with text prompts. In contrast, StyleGAN models learn a rich face prior and enable smooth control towards fine-grained attribute editing by latent manipulation. This work uses the disentangled $\mathcal{W+}$ space of StyleGANs to condition the T2I model. This approach allows us to precisely manipulate facial attributes, such as smoothly introducing a smile, while preserving the existing coarse text-based control inherent in T2I models. To enable conditioning of the T2I model on the $\mathcal{W+}$ space, we train a latent mapper to translate latent codes from $\mathcal{W+}$ to the token embedding space of the T2I model. The proposed approach excels in the precise inversion of face images with attribute preservation and facilitates continuous control for fine-grained attribute editing. Furthermore, our approach can be readily extended to generate compositions involving multiple individuals. We perform extensive experiments to validate our method for face personalization and fine-grained attribute editing. |
| title | PreciseControl: Enhancing Text-To-Image Diffusion Models with Fine-Grained Attribute Control |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.05083 |