Metric: FVD16 (higher is better)
| # | Model↕ | FVD16▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | MagicVideo (Zero-shot, 256x256) | 699 | No | MagicVideo: Efficient Video Generation With Late... | 2022-11-20 | - |
| 2 | Video LDM (Zero-shot, 320x512) | 550.61 | No | Align your Latents: High-Resolution Video Synthe... | 2023-04-18 | Code |
| 3 | LAVIE (Zero-shot, 320x512) | 526.3 | No | LAVIE: High-Quality Video Generation with Cascad... | 2023-09-26 | Code |
| 4 | PYoCo (Zero-shot, 64x64) | 355.19 | No | Preserve Your Own Correlation: A Noise Prior for... | 2023-05-17 | - |
| 5 | VideoPoet | 355 | No | VideoPoet: A Large Language Model for Zero-Shot ... | 2023-12-21 | - |
| 6 | Lumiere (Zero-shot, 1024x1024) | 332.49 | No | Lumiere: A Space-Time Diffusion Model for Video ... | 2024-01-23 | Code |
| 7 | Snap Video (Zero-shot, 288×288) | 260.1 | No | Snap Video: Scaled Spatiotemporal Transformers f... | 2024-02-22 | - |
| 8 | W.A.L.T 3B | 258.1 | No | Photorealistic Video Generation with Diffusion M... | 2023-12-11 | - |
| 9 | PixelDance (Zero-shot, 256x256) | 242.82 | No | Make Pixels Dance: High-Dynamic Video Generation | 2023-11-18 | - |
| 10 | Snap Video (Zero-shot, 512x288) | 200.2 | No | Snap Video: Scaled Spatiotemporal Transformers f... | 2024-02-22 | - |