SNED: Superposition Network Architecture Search for Efficient Video Diffusion Model
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917681731469312 |
|---|---|
| author | Li, Zhengang Kang, Yan Liu, Yuchen Liu, Difan Hinz, Tobias Liu, Feng Wang, Yanzhi |
| author_facet | Li, Zhengang Kang, Yan Liu, Yuchen Liu, Difan Hinz, Tobias Liu, Feng Wang, Yanzhi |
| contents | While AI-generated content has garnered significant attention, achieving photo-realistic video synthesis remains a formidable challenge. Despite the promising advances in diffusion models for video generation quality, the complex model architecture and substantial computational demands for both training and inference create a significant gap between these models and real-world applications. This paper presents SNED, a superposition network architecture search method for efficient video diffusion model. Our method employs a supernet training paradigm that targets various model cost and resolution options using a weight-sharing method. Moreover, we propose the supernet training sampling warm-up for fast training optimization. To showcase the flexibility of our method, we conduct experiments involving both pixel-space and latent-space video diffusion models. The results demonstrate that our framework consistently produces comparable results across different model options with high efficiency. According to the experiment for the pixel-space video diffusion model, we can achieve consistent video generation results simultaneously across 64 x 64 to 256 x 256 resolutions with a large range of model sizes from 640M to 1.6B number of parameters for pixel-space video diffusion models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_00195 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SNED: Superposition Network Architecture Search for Efficient Video Diffusion Model Li, Zhengang Kang, Yan Liu, Yuchen Liu, Difan Hinz, Tobias Liu, Feng Wang, Yanzhi Computer Vision and Pattern Recognition Artificial Intelligence While AI-generated content has garnered significant attention, achieving photo-realistic video synthesis remains a formidable challenge. Despite the promising advances in diffusion models for video generation quality, the complex model architecture and substantial computational demands for both training and inference create a significant gap between these models and real-world applications. This paper presents SNED, a superposition network architecture search method for efficient video diffusion model. Our method employs a supernet training paradigm that targets various model cost and resolution options using a weight-sharing method. Moreover, we propose the supernet training sampling warm-up for fast training optimization. To showcase the flexibility of our method, we conduct experiments involving both pixel-space and latent-space video diffusion models. The results demonstrate that our framework consistently produces comparable results across different model options with high efficiency. According to the experiment for the pixel-space video diffusion model, we can achieve consistent video generation results simultaneously across 64 x 64 to 256 x 256 resolutions with a large range of model sizes from 640M to 1.6B number of parameters for pixel-space video diffusion models. |
| title | SNED: Superposition Network Architecture Search for Efficient Video Diffusion Model |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2406.00195 |