UniVid: Pyramid Diffusion Model for High Quality Video Generation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912966024101888 |
|---|---|
| author | Xiao, Xinyu Yang, Binbin Li, Tingtian Yu, Yipeng Lei, Sen |
| author_facet | Xiao, Xinyu Yang, Binbin Li, Tingtian Yu, Yipeng Lei, Sen |
| contents | Diffusion-based text-to-video generation (T2V) or image-to-video (I2V) generation have emerged as a prominent research focus. However, there exists a challenge in integrating the two generative paradigms into a unified model. In this paper, we present a unified video generation model (UniVid) with hybrid conditions of the text prompt and reference image. Given these two available controls, our model can extract objects' appearance and their motion descriptions from textual prompts, while obtaining texture details and structural information from image clues to guide the video generation process. Specifically, we scale up the pre-trained text-to-image diffusion model for generating temporally coherent frames via introducing our temporal-pyramid cross-frame spatial-temporal attention modules and convolutions. To support bimodal control, we introduce a dual-stream cross-attention mechanism, whose attention scores can be freely re-weighted for interpolation of between single and two modalities controls during inference. Extensive experiments showcase that our UniVid achieves superior temporal coherence on T2V, I2V and (T+I)2V tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_13739 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | UniVid: Pyramid Diffusion Model for High Quality Video Generation Xiao, Xinyu Yang, Binbin Li, Tingtian Yu, Yipeng Lei, Sen Computer Vision and Pattern Recognition Artificial Intelligence Multimedia Diffusion-based text-to-video generation (T2V) or image-to-video (I2V) generation have emerged as a prominent research focus. However, there exists a challenge in integrating the two generative paradigms into a unified model. In this paper, we present a unified video generation model (UniVid) with hybrid conditions of the text prompt and reference image. Given these two available controls, our model can extract objects' appearance and their motion descriptions from textual prompts, while obtaining texture details and structural information from image clues to guide the video generation process. Specifically, we scale up the pre-trained text-to-image diffusion model for generating temporally coherent frames via introducing our temporal-pyramid cross-frame spatial-temporal attention modules and convolutions. To support bimodal control, we introduce a dual-stream cross-attention mechanism, whose attention scores can be freely re-weighted for interpolation of between single and two modalities controls during inference. Extensive experiments showcase that our UniVid achieves superior temporal coherence on T2V, I2V and (T+I)2V tasks. |
| title | UniVid: Pyramid Diffusion Model for High Quality Video Generation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Multimedia |
| url | https://arxiv.org/abs/2603.13739 |