Image-to-Video Generation on VBench (test)
66.23Aesthetic Quality ScoreOrigin
Evaluation results
| Method | Links | |||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| OriginModel=Wan2.2, Config=14B-720P-I2V2026.03 | 66.23 | — | — | — | — | — | — | — | — | — | 74.36 | 97.55 | 97.24 | 1,605 | 1 | — | — | — | — | |
| SVOOModel=Wan2.2, Config=14B-720P-I2V2026.03 | 63.76 | — | — | — | — | — | — | 29.678 | 91.3 | 0.095 | 73.37 | 97.31 | 96.97 | 994 | 1.61 | — | — | — | — | |
| RadialModel=Wan2.2, Config=14B-720P-I2V2026.03 | 63.73 | — | — | — | — | — | — | 25.08 | 79.7 | 0.156 | 71.19 | 95.91 | 96.49 | 1,157 | 1.39 | — | — | — | — | |
| DFD2026.06 | 63.71 | — | 93.03 | — | — | — | — | — | — | — | — | 96.13 | 96.92 | — | — | 97.59 | 99 | 98.59 | 99.3 | |
| Teacher2026.06 | 63.2 | — | 92.85 | — | — | — | — | — | — | — | — | 96.16 | 96.48 | — | — | 97.17 | 99.05 | 98.67 | 99.25 | |
| DMD22026.06 | 63.01 | — | 92.45 | — | — | — | — | — | — | — | — | 94.21 | 96.21 | — | — | 97.34 | 98.86 | 98.5 | 99 | |
| SVG2Model=Wan2.2, Config=14B-720P-I2V2026.03 | 62.36 | — | — | — | — | — | — | 28.384 | 89.3 | 0.106 | 71.28 | 96.79 | 96.65 | 1,057 | 1.52 | — | — | — | — | |
| SpargeAttnModel=Wan2.2, Config=14B-720P-I2V2026.03 | 62.29 | — | — | — | — | — | — | 25.935 | 83.2 | 0.139 | 72.61 | 97.03 | 97.09 | 1,119 | 1.42 | — | — | — | — | |
| OriginModel=Hunyuan, Config=13B-720P-I2V2026.03 | 62.06 | — | — | — | — | — | — | — | — | — | 70.3 | 96.55 | 96.54 | 1,761 | 1 | — | — | — | — | |
| SVG1Model=Wan2.2, Config=14B-720P-I2V2026.03 | 62.05 | — | — | — | — | — | — | 26.882 | 86.6 | 0.131 | 72.88 | 97.17 | 97.08 | 1,034 | 1.55 | — | — | — | — | |
| OriginModel=Wan2.1, Config=14B-720P-I2V2026.03 | 61.86 | — | — | — | — | — | — | — | — | — | 71.52 | 94.98 | 95.37 | 1,658 | 1 | — | — | — | — | |
| SpargeAttnModel=Wan2.1, Config=14B-720P-I2V2026.03 | 61.77 | — | — | — | — | — | — | 21.557 | 69.1 | 0.297 | 70.83 | 95.81 | 95.04 | 1,124 | 1.48 | — | — | — | — | |
| SVOOModel=Wan2.1, Config=14B-720P-I2V2026.03 | 61.67 | — | — | — | — | — | — | 27.545 | 87.8 | 0.121 | 71.71 | 94.8 | 95.39 | 954 | 1.74 | — | — | — | — | |
| RadialModel=Hunyuan, Config=13B-720P-I2V2026.03 | 61.66 | — | — | — | — | — | — | 23.463 | 72 | 0.258 | 69.52 | 95.3 | 95.62 | 912 | 1.93 | — | — | — | — | |
| RadialModel=Wan2.1, Config=14B-720P-I2V2026.03 | 61.62 | — | — | — | — | — | — | 23.673 | 75.9 | 0.189 | 70.91 | 94.52 | 95.36 | 1,046 | 1.58 | — | — | — | — | |
| SVG2Model=Wan2.1, Config=14B-720P-I2V2026.03 | 61.45 | — | — | — | — | — | — | 27.324 | 85.6 | 0.125 | 70.76 | 95.72 | 94.93 | 998 | 1.66 | — | — | — | — | |
| SVG1Model=Wan2.1, Config=14B-720P-I2V2026.03 | 61.02 | — | — | — | — | — | — | 24.262 | 82.5 | 0.174 | 70.93 | 94.42 | 94.51 | 1,047 | 1.58 | — | — | — | — | |
| SpargeAttnModel=Hunyuan, Config=13B-720P-I2V2026.03 | 60.99 | — | — | — | — | — | — | 22.908 | 71.7 | 0.259 | 68.53 | 96.22 | 95.37 | 1,287 | 1.37 | — | — | — | — | |
| SVG2Model=Hunyuan, Config=13B-720P-I2V2026.03 | 59.75 | — | — | — | — | — | — | 24.947 | 76.1 | 0.22 | 68.45 | 95.61 | 95.68 | 889 | 1.98 | — | — | — | — | |
| SVOOModel=Hunyuan, Config=13B-720P-I2V2026.03 | 59.68 | — | — | — | — | — | — | 25.155 | 75.9 | 0.2 | 69.7 | 96.79 | 95.7 | 810 | 2.17 | — | — | — | — | |
| I2VGuardPurification Defense=Crop and Resize, Video Generation Model=CogVideoX2026.07 | 59.51 | — | — | — | — | — | — | — | — | — | 65.6 | 94.15 | 96.46 | — | — | 96.4 | 97.61 | 92.92 | 94.95 | |
| I2VGuardPurification Defense=JPEG Compression, Video Generation Model=CogVideoX2026.07 | 58.78 | — | — | — | — | — | — | — | — | — | 65.38 | 92.92 | 95.66 | — | — | 96.03 | 97.25 | 93.95 | 96.44 | |
| I2VGuardPurification Defense=ADVClean, Video Generation Model=LTX-Video2026.07 | 58.59 | — | — | — | — | — | — | — | — | — | 64.31 | 93.71 | 96.92 | — | — | 98.97 | 99.33 | 96.08 | 96.71 | |
| DP-DMD2026.06 | 58.5 | — | 88.43 | — | — | — | — | — | — | — | — | 84.57 | 90.68 | — | — | 96.03 | 98.32 | 95.7 | 95.2 | |
| Anti-PromptPurification Defense=Crop and Resize, Video Generation Model=CogVideoX2026.07 | 58.26 | — | — | — | — | — | — | — | — | — | 67.53 | 93.46 | 96.3 | — | — | 95.95 | 97.22 | 92.89 | 94.89 | |
| Anti-PromptPurification Defense=JPEG Compression, Video Generation Model=CogVideoX2026.07 | 57.45 | — | — | — | — | — | — | — | — | — | 67.1 | 91.96 | 95.15 | — | — | 95.48 | 96.78 | 93.85 | 96.3 | |
| Anti-PromptPurification Defense=ADVClean, Video Generation Model=LTX-Video2026.07 | 57.31 | — | — | — | — | — | — | — | — | — | 63.35 | 92.94 | 96.67 | — | — | 98.76 | 99.2 | 95.78 | 96.44 | |
| I2VGuardPurification Defense=ADVClean, Video Generation Model=CogVideoX2026.07 | 56.97 | — | — | — | — | — | — | — | — | — | 66.02 | 93.79 | 96.27 | — | — | 96.75 | 97.69 | 94.94 | 97.48 | |
| Anti-PromptPurification Defense=ADVClean, Video Generation Model=CogVideoX2026.07 | 56.97 | — | — | — | — | — | — | — | — | — | 67.04 | 91.84 | 95.71 | — | — | 95.65 | 96.83 | 93.71 | 97.07 | |
| I2VGuardPurification Defense=Crop and Resize, Video Generation Model=LTX-Video2026.07 | 55.68 | — | — | — | — | — | — | — | — | — | 61.82 | 90.36 | 95.11 | — | — | 98.21 | 98.9 | 93.32 | 94.32 | |
| SVG1Model=Hunyuan, Config=13B-720P-I2V2026.03 | 55.57 | — | — | — | — | — | — | 23.437 | 72.9 | 0.236 | 67.04 | 96.51 | 95.47 | 887 | 1.98 | — | — | — | — | |
| Anti-PromptPurification Defense=Crop and Resize, Video Generation Model=LTX-Video2026.07 | 53.92 | — | — | — | — | — | — | — | — | — | 59.96 | 88.59 | 94.71 | — | — | 97.79 | 98.56 | 92.19 | 93.65 | |
| I2VGuardPurification Defense=JPEG Compression, Video Generation Model=LTX-Video2026.07 | 53.03 | — | — | — | — | — | — | — | — | — | 58.69 | 85.71 | 93.48 | — | — | 97.38 | 98.14 | 92.04 | 94.6 | |
| Anti-PromptPurification Defense=JPEG Compression, Video Generation Model=LTX-Video2026.07 | 52.02 | — | — | — | — | — | — | — | — | — | 57.96 | 85.46 | 93.23 | — | — | 97.25 | 98.02 | 91.58 | 93.89 | |
| ALGBackbone=Wan 2.22025.06 | — | 39 | 80.5 | 85.2 | 98.5 | 0.637 | 0.182 | — | — | — | — | — | — | — | — | — | — | — | — | |
| ALGBackbone=Wan 2.12025.06 | — | 39.4 | 80 | 84.5 | 98 | 0.614 | 0.176 | — | — | — | — | — | — | — | — | — | — | — | — | |
| ALGBackbone=LTX-Video2025.06 | — | 21.5 | 78.2 | 85.4 | 98.9 | 0.626 | 0.175 | — | — | — | — | — | — | — | — | — | — | — | — | |
| ALGModel=Wan 2.22025.06 | — | 39 | 80.5 | 85.2 | 98.5 | 0.637 | 0.182 | — | — | — | — | — | — | — | — | — | — | — | — | |
| CFGBackbone=Wan 2.22025.06 | — | 31.7 | 79.6 | 85.4 | 98.5 | 0.635 | 0.183 | — | — | — | — | — | — | — | — | — | — | — | — | |
| CFGBackbone=Wan 2.12025.06 | — | 28.9 | 79.1 | 85.3 | 98.3 | 0.618 | 0.179 | — | — | — | — | — | — | — | — | — | — | — | — | |
| CFGBackbone=LTX-Video2025.06 | — | 15.5 | 77.8 | 85.9 | 99.1 | 0.625 | 0.175 | — | — | — | — | — | — | — | — | — | — | — | — | |
| CFGModel=Wan 2.22025.06 | — | 31.7 | 79.6 | 85.4 | 98.5 | 0.635 | 0.183 | — | — | — | — | — | — | — | — | — | — | — | — |