| Paper | Code | Visual Quality | Motion Quality | Temporal Consistency | Text-to-Video Alignment | Total Score | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|---|---|
| VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models | ✓ Link | 54.82 | 63.98 | 61.46 | 63.16 | 243 | VideoCrafter2 | 2024-01-17 |
| Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation | ✓ Link | 53.74 | 52.19 | 60.83 | 62.07 | 229 | Show-1 | 2023-09-27 |
| VideoCrafter1: Open Diffusion Models for High-Quality Video Generation | ✓ Link | 53.08 | 60.85 | 55.89 | 61.95 | 232 | VideoCrafter1 | 2023-10-30 |
| LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models | ✓ Link | 52.83 | 57.99 | 54.23 | 68.49 | 234 | Lavie | 2023-09-26 |
| VideoComposer: Compositional Video Synthesis with Motion Controllability | ✓ Link | 52.47 | 53.09 | 54.46 | 57.8 | 218 | ModelScope | 2023-06-03 |