Text-to-Video Generation on EvalCrafter Text-to-Video (ECTV) Dataset
Metric: Text-to-Video Alignment (higher is better)
Metric: Text-to-Video Alignment (higher is better)
| # | Model↕ | Text-to-Video Alignment▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | Lavie | 68.49 | Yes | LAVIE: High-Quality Video Generation with Cascad... | 2023-09-26 | Code |
| 2 | VideoCrafter2 | 63.16 | Yes | VideoCrafter2: Overcoming Data Limitations for H... | 2024-01-17 | Code |
| 3 | Show-1 | 62.07 | Yes | Show-1: Marrying Pixel and Latent Diffusion Mode... | 2023-09-27 | Code |
| 4 | VideoCrafter1 | 61.95 | Yes | VideoCrafter1: Open Diffusion Models for High-Qu... | 2023-10-30 | Code |
| 5 | ModelScope | 57.8 | Yes | VideoComposer: Compositional Video Synthesis wit... | 2023-06-03 | Code |