Text-to-Video Generation on MSR-VTT
Metric: FVD (higher is better)
Metric: FVD (higher is better)
| # | Model↕ | FVD▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | MagicVideo | 998 | No | MagicVideo: Efficient Video Generation With Late... | 2022-11-20 | - |
| 2 | VideoComposer | 580 | No | VideoComposer: Compositional Video Synthesis wit... | 2023-06-03 | Code |
| 3 | ModelScopeT2V | 550 | No | ModelScope Text-to-Video Technical Report | 2023-08-12 | Code |
| 4 | Show-1 | 538 | No | Show-1: Marrying Pixel and Latent Diffusion Mode... | 2023-09-27 | Code |
| 5 | TF-T2V | 441 | No | A Recipe for Scaling up Text-to-Video Generation... | 2023-12-25 | Code |
| 6 | HiGen | 406 | No | Hierarchical Spatio-temporal Decoupling for Text... | 2023-12-07 | Code |
| 7 | PixelDance | 381 | No | Make Pixels Dance: High-Dynamic Video Generation | 2023-11-18 | - |
| 8 | VideoPoet | 213 | No | VideoPoet: A Large Language Model for Zero-Shot ... | 2023-12-21 | - |
| 9 | Video-LaVIT | 188.36 | No | Video-LaVIT: Unified Video-Language Pre-training... | 2024-02-05 | Code |
| 10 | Snap Video (288×288) | 110.4 | No | Snap Video: Scaled Spatiotemporal Transformers f... | 2024-02-22 | - |
| 11 | Snap Video (512x288) | 104 | No | Snap Video: Scaled Spatiotemporal Transformers f... | 2024-02-22 | - |