Layered Diffusion Model for One-Shot High Resolution Text-to-Image Synthesis
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_ | 1866911948529991680 |
|---|---|
| author | Khwaja, Emaad Rashwan, Abdullah Chen, Ting Wang, Oliver Kothawade, Suraj Li, Yeqing |
| author_facet | Khwaja, Emaad Rashwan, Abdullah Chen, Ting Wang, Oliver Kothawade, Suraj Li, Yeqing |
| contents | We present a one-shot text-to-image diffusion model that can generate high-resolution images from natural language descriptions. Our model employs a layered U-Net architecture that simultaneously synthesizes images at multiple resolution scales. We show that this method outperforms the baseline of synthesizing images only at the target resolution, while reducing the computational cost per step. We demonstrate that higher resolution synthesis can be achieved by layering convolutions at additional resolution scales, in contrast to other methods which require additional models for super-resolution synthesis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_06079 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Layered Diffusion Model for One-Shot High Resolution Text-to-Image Synthesis Khwaja, Emaad Rashwan, Abdullah Chen, Ting Wang, Oliver Kothawade, Suraj Li, Yeqing Computer Vision and Pattern Recognition Artificial Intelligence We present a one-shot text-to-image diffusion model that can generate high-resolution images from natural language descriptions. Our model employs a layered U-Net architecture that simultaneously synthesizes images at multiple resolution scales. We show that this method outperforms the baseline of synthesizing images only at the target resolution, while reducing the computational cost per step. We demonstrate that higher resolution synthesis can be achieved by layering convolutions at additional resolution scales, in contrast to other methods which require additional models for super-resolution synthesis. |
| title | Layered Diffusion Model for One-Shot High Resolution Text-to-Image Synthesis |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2407.06079 |