PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916458720657408 |
|---|---|
| author | Kim, Dongjun Lai, Chieh-Hsin Liao, Wei-Hsiang Takida, Yuhta Murata, Naoki Uesaka, Toshimitsu Mitsufuji, Yuki Ermon, Stefano |
| author_facet | Kim, Dongjun Lai, Chieh-Hsin Liao, Wei-Hsiang Takida, Yuhta Murata, Naoki Uesaka, Toshimitsu Mitsufuji, Yuki Ermon, Stefano |
| contents | The diffusion model performs remarkable in generating high-dimensional content but is computationally intensive, especially during training. We propose Progressive Growing of Diffusion Autoencoder (PaGoDA), a novel pipeline that reduces the training costs through three stages: training diffusion on downsampled data, distilling the pretrained diffusion, and progressive super-resolution. With the proposed pipeline, PaGoDA achieves a $64\times$ reduced cost in training its diffusion model on 8x downsampled data; while at the inference, with the single-step, it performs state-of-the-art on ImageNet across all resolutions from 64x64 to 512x512, and text-to-image. PaGoDA's pipeline can be applied directly in the latent space, adding compression alongside the pre-trained autoencoder in Latent Diffusion Models (e.g., Stable Diffusion). The code is available at https://github.com/sony/pagoda. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_14822 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher Kim, Dongjun Lai, Chieh-Hsin Liao, Wei-Hsiang Takida, Yuhta Murata, Naoki Uesaka, Toshimitsu Mitsufuji, Yuki Ermon, Stefano Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning The diffusion model performs remarkable in generating high-dimensional content but is computationally intensive, especially during training. We propose Progressive Growing of Diffusion Autoencoder (PaGoDA), a novel pipeline that reduces the training costs through three stages: training diffusion on downsampled data, distilling the pretrained diffusion, and progressive super-resolution. With the proposed pipeline, PaGoDA achieves a $64\times$ reduced cost in training its diffusion model on 8x downsampled data; while at the inference, with the single-step, it performs state-of-the-art on ImageNet across all resolutions from 64x64 to 512x512, and text-to-image. PaGoDA's pipeline can be applied directly in the latent space, adding compression alongside the pre-trained autoencoder in Latent Diffusion Models (e.g., Stable Diffusion). The code is available at https://github.com/sony/pagoda. |
| title | PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2405.14822 |