Diffusion-RWKV: Scaling RWKV-Like Architectures for Diffusion Models
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_ | 1866911828907393024 |
|---|---|
| author | Fei, Zhengcong Fan, Mingyuan Yu, Changqian Li, Debang Huang, Junshi |
| author_facet | Fei, Zhengcong Fan, Mingyuan Yu, Changqian Li, Debang Huang, Junshi |
| contents | Transformers have catalyzed advancements in computer vision and natural language processing (NLP) fields. However, substantial computational complexity poses limitations for their application in long-context tasks, such as high-resolution image generation. This paper introduces a series of architectures adapted from the RWKV model used in the NLP, with requisite modifications tailored for diffusion model applied to image generation tasks, referred to as Diffusion-RWKV. Similar to the diffusion with Transformers, our model is designed to efficiently handle patchnified inputs in a sequence with extra conditions, while also scaling up effectively, accommodating both large-scale parameters and extensive datasets. Its distinctive advantage manifests in its reduced spatial aggregation complexity, rendering it exceptionally adept at processing high-resolution images, thereby eliminating the necessity for windowing or group cached operations. Experimental results on both condition and unconditional image generation tasks demonstrate that Diffison-RWKV achieves performance on par with or surpasses existing CNN or Transformer-based diffusion models in FID and IS metrics while significantly reducing total computation FLOP usage. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_04478 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Diffusion-RWKV: Scaling RWKV-Like Architectures for Diffusion Models Fei, Zhengcong Fan, Mingyuan Yu, Changqian Li, Debang Huang, Junshi Computer Vision and Pattern Recognition Transformers have catalyzed advancements in computer vision and natural language processing (NLP) fields. However, substantial computational complexity poses limitations for their application in long-context tasks, such as high-resolution image generation. This paper introduces a series of architectures adapted from the RWKV model used in the NLP, with requisite modifications tailored for diffusion model applied to image generation tasks, referred to as Diffusion-RWKV. Similar to the diffusion with Transformers, our model is designed to efficiently handle patchnified inputs in a sequence with extra conditions, while also scaling up effectively, accommodating both large-scale parameters and extensive datasets. Its distinctive advantage manifests in its reduced spatial aggregation complexity, rendering it exceptionally adept at processing high-resolution images, thereby eliminating the necessity for windowing or group cached operations. Experimental results on both condition and unconditional image generation tasks demonstrate that Diffison-RWKV achieves performance on par with or surpasses existing CNN or Transformer-based diffusion models in FID and IS metrics while significantly reducing total computation FLOP usage. |
| title | Diffusion-RWKV: Scaling RWKV-Like Architectures for Diffusion Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.04478 |