Text-to-Video Generation on VBench (Total, Quality, and Semantic Scores)
84.78Total ScoreSIPO
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| SIPOModel=WanX-1.3B2025.05 | 84.78 | 85.73 | 81.02 | |
| C&MModel=WanX-1.3B2025.05 | 84.54 | 85.51 | 80.67 | |
| Diffusion-DPOModel=WanX-1.3B2025.05 | 84.41 | 85.32 | 80.44 | |
| PretrainedModel=WanX-1.3B2025.05 | 84.26 | 85.3 | 80.09 | |
| SIPOModel=CogVideoX-5B2025.05 | 82.28 | 83.37 | 77.91 | |
| C&MModel=CogVideoX-5B2025.05 | 82.17 | 83.26 | 77.81 | |
| Diffusion-DPOModel=CogVideoX-5B2025.05 | 82.02 | 83.15 | 77.5 | |
| PretrainedModel=CogVideoX-5B2025.05 | 81.91 | 83.05 | 77.33 | |
| SIPOModel=CogVideoX-2B, Training Steps=10002025.05 | 81.68 | 82.92 | 76.76 | |
| SIPOModel=CogVideoX-2B, Training Steps=5002025.05 | 81.53 | 82.74 | 76.71 | |
| C&MModel=CogVideoX-2B, Training Steps=10002025.05 | 81.46 | 82.65 | 76.72 | |
| C&MModel=CogVideoX-2B, Training Steps=5002025.05 | 81.37 | 82.55 | 76.69 | |
| Diffusion-DPOModel=CogVideoX-2B, Training Steps=5002025.05 | 81.16 | 82.32 | 76.49 | |
| PretrainedModel=CogVideoX-2B, Training Steps=5002025.05 | 80.91 | 82.18 | 75.83 | |
| PretrainedModel=CogVideoX-2B, Training Steps=10002025.05 | 80.91 | 82.18 | 75.83 | |
| Diffusion-DPOModel=CogVideoX-2B, Training Steps=10002025.05 | 67.28 | 68.37 | 62.93 |