Video Generation on VBench v1 (test)
7.39Latency (s)Radial
Evaluation Results
| Method | Links | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| RadialBase Model=Self-Forcing 1.3B, fps=162026.02 | 7.39 | 1.3 | 45.8 | 66.1 | 96 | 88.6 | 90.2 | 93.6 | 78.7 | 53.7 | 73.7 | |
| LIGHT FORCINGBase Model=Self-Forcing 1.3B, fps=162026.02 | 7.39 | 1.3 | 67.2 | 71 | 98.3 | 66.7 | 96.2 | 96.5 | 85.4 | 80.9 | 84.5 | |
| VMoBABase Model=Self-Forcing 1.3B, fps=162026.02 | 7.42 | 1.29 | 65.2 | 69.9 | 97.3 | 84.2 | 92.8 | 95.5 | 84.5 | 80.3 | 83.6 | |
| SLABase Model=Self-Forcing 1.3B, fps=162026.02 | 7.71 | 1.25 | 66.7 | 69.8 | 98.3 | 44.2 | 95.6 | 96.7 | 83.4 | 82.5 | 83.2 | |
| STABase Model=Self-Forcing 1.3B, fps=162026.02 | 8.27 | 1.16 | 64.5 | 71.7 | 98.5 | 48.9 | 96.3 | 96.9 | 84 | 82.1 | 83.6 | |
| LIGHT FORCINGBase Model=LongLive 1.3B, fps=162026.02 | 8.81 | 1.19 | 67.2 | 70.6 | 98.2 | 59.4 | 96.9 | 96.7 | 84.8 | 80.2 | 83.9 | |
| VMoBABase Model=LongLive 1.3B, fps=162026.02 | 8.88 | 1.18 | 59.9 | 68.2 | 97.5 | 50.6 | 58.3 | 80.9 | 71.5 | 70.7 | 71.3 | |
| RadialBase Model=LongLive 1.3B, fps=162026.02 | 8.89 | 1.18 | 55.1 | 72 | 98 | 25 | 77.6 | 88.9 | 75 | 66.6 | 73.3 | |
| STABase Model=LongLive 1.3B, fps=162026.02 | 9.56 | 1.1 | 65.6 | 71.2 | 99 | 22.8 | 97.4 | 97.8 | 82.8 | 81.6 | 82.6 | |
| FlashAttention2Base Model=Self-Forcing 1.3B, fps=162026.02 | 9.61 | 1 | 67.4 | 70 | 98.3 | 63.1 | 95.3 | 96.5 | 84.8 | 81.2 | 84.1 | |
| FlashAttention2Base Model=LongLive 1.3B, fps=162026.02 | 10.47 | 1 | 68.7 | 69.3 | 98.8 | 39.2 | 97 | 97.2 | 83.8 | 80.7 | 83.2 | |
| SVG2Base Model=Self-Forcing 1.3B, fps=162026.02 | 21.38 | 0.45 | 66 | 68.2 | 97.8 | 72.8 | 93.6 | 95.6 | 83.9 | 78.5 | 82.8 | |
| SVG2Base Model=LongLive 1.3B, fps=162026.02 | 22.12 | 0.47 | 66.7 | 67 | 98.5 | 44.4 | 95.3 | 96.1 | 82.7 | 78.7 | 81.9 |