SimInversion: A Simple Framework for Inversion-Based Text-to-Image Editing
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929500904751104 |
|---|---|
| author | Qian, Qi Xu, Haiyang Yan, Ming Hu, Juhua |
| author_facet | Qian, Qi Xu, Haiyang Yan, Ming Hu, Juhua |
| contents | Diffusion models demonstrate impressive image generation performance with text guidance. Inspired by the learning process of diffusion, existing images can be edited according to text by DDIM inversion. However, the vanilla DDIM inversion is not optimized for classifier-free guidance and the accumulated error will result in the undesired performance. While many algorithms are developed to improve the framework of DDIM inversion for editing, in this work, we investigate the approximation error in DDIM inversion and propose to disentangle the guidance scale for the source and target branches to reduce the error while keeping the original framework. Moreover, a better guidance scale (i.e., 0.5) than default settings can be derived theoretically. Experiments on PIE-Bench show that our proposal can improve the performance of DDIM inversion dramatically without sacrificing efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_10476 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SimInversion: A Simple Framework for Inversion-Based Text-to-Image Editing Qian, Qi Xu, Haiyang Yan, Ming Hu, Juhua Computer Vision and Pattern Recognition Diffusion models demonstrate impressive image generation performance with text guidance. Inspired by the learning process of diffusion, existing images can be edited according to text by DDIM inversion. However, the vanilla DDIM inversion is not optimized for classifier-free guidance and the accumulated error will result in the undesired performance. While many algorithms are developed to improve the framework of DDIM inversion for editing, in this work, we investigate the approximation error in DDIM inversion and propose to disentangle the guidance scale for the source and target branches to reduce the error while keeping the original framework. Moreover, a better guidance scale (i.e., 0.5) than default settings can be derived theoretically. Experiments on PIE-Bench show that our proposal can improve the performance of DDIM inversion dramatically without sacrificing efficiency. |
| title | SimInversion: A Simple Framework for Inversion-Based Text-to-Image Editing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.10476 |