Image-to-Video Generation on VBench I2V
99.08Background ConsistencyVQQA
Evaluation Results
| Method | Links | ||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VQQAN=5, Optimization Rounds=4, Backbone=Gemini-3-Pro2026.03 | 99.08 | 98.09 | — | 98.44 | — | — | — | — | — | — | — | 97.86 | — | — | |
| Best-of-N & VLM-RatingN=5, Rating Model=Gemini-3-Pro2026.03 | 99.03 | 97.77 | — | 98.32 | — | — | — | — | — | — | — | 97.63 | — | — | |
| Best-of-N & VQAScoreN=5, Scoring Model=VQAScore2026.03 | 98.96 | 97.61 | — | 98.29 | — | — | — | — | — | — | — | 97.48 | — | — | |
| VideoMAR#Params=1.4B + 1.5B, #Videos=0.5M, Gen Rep=Continuous2025.07 | 98.38 | 97.85 | — | — | — | — | 62.34 | — | — | — | — | 84.82 | 94.02 | 75.6 | |
| Lumos-1Resolution=672 × 384 × 25, #Params=3.6B, #Videos=10M, Gen Rep=Discrete2025.07 | 97.4 | 97.42 | — | — | — | — | 69.23 | — | — | — | — | 84.72 | 93.34 | 76.1 | |
| COSMOS#Params=5B + 11B, #Videos=100M, Gen Rep=Continuous2025.07 | 97.36 | 95.99 | — | — | — | — | 59.9 | — | — | — | — | 84.16 | 92.51 | 75.81 | |
| PCMNFE=8, Category=Consistency distillation2026.04 | 97.34 | — | 97.67 | 98.24 | 30.98 | — | 70.42 | — | — | — | — | — | 93.63 | 78.52 | |
| I2VGen-XL#Params=1.4B + 1.0B, #Videos=35M, Gen Rep=Continuous2025.07 | 96.83 | 96.48 | — | — | — | — | 69.14 | — | — | — | — | 85.28 | 92.11 | 78.44 | |
| SEINE#Params=0.9B + 0.1B, #Videos=10M, Gen Rep=Continuous2025.07 | 96.8 | 96.57 | — | — | — | — | 70.97 | — | — | — | — | 84.88 | 92.39 | 77.37 | |
| CogVideoX-5B-I2VGeneration Strategy=Vanilla Generation2026.03 | 96.74 | 97.19 | — | 98.4 | — | — | — | — | — | — | — | 96.62 | — | — | |
| CogVideoX#Params=5.6B + 4.8B, Gen Rep=Continuous2025.07 | 96.74 | 97.19 | — | — | — | — | 70.01 | — | — | — | — | 86.7 | 94.79 | 78.61 | |
| Lumos-1Resolution=672 × 384 × 25, #Params=1.5B, #Videos=10M, Gen Rep=Discrete2025.07 | 96.58 | 96.06 | — | — | — | — | 67.06 | — | — | — | — | 84.16 | 91.8 | 76.53 | |
| SC-DMDNFE=42026.04 | 95.97 | — | 97.41 | 98.37 | 52.85 | — | 72.16 | — | — | — | — | — | 93.9 | 80.86 | |
| ConsistI2V#Params=1.3B + 0.3B, #Videos=10M, Gen Rep=Continuous2025.07 | 95.95 | 95.82 | — | — | — | — | 66.92 | — | — | — | — | 84.07 | 91.91 | 76.22 | |
| LightX2VNFE=4, Category=Distribution matching2026.04 | 95.87 | — | 96.3 | 97.89 | 60.33 | — | 71.67 | — | — | — | — | — | 93.5 | 80.92 | |
| SC-DMD-αNFE=42026.04 | 95.46 | — | 96.48 | 98.3 | 68.13 | — | 72.08 | — | — | — | — | — | 93.88 | 81.71 | |
| DINO-ALF2026.03 | 93.79 | 91.31 | 97.5 | 97.39 | 78.5 | 56.37 | 67.14 | 79.5 | 0.174 | 28.5 | 471.3 | — | — | — | |
| DMDNFE=4, Category=Distribution matching2026.04 | 92.79 | — | 95.21 | 97.99 | 58.46 | — | 70.35 | — | — | — | — | — | 93.09 | 78.89 | |
| VideoCrafter-I2V#Params=2.6B, #Videos=20M, Gen Rep=Continuous2025.07 | 91.31 | 91.17 | — | — | — | — | 71.68 | — | — | — | — | 82.57 | 86.31 | 78.84 | |
| UniAnimate-DiT2026.03 | 91.17 | 87.21 | 95.78 | 92.33 | 74.87 | 56.32 | 66.87 | 75.1 | 0.189 | 27.48 | 527.4 | — | — | — | |
| VACE2026.03 | 91.11 | 88.31 | 95.31 | 94.81 | 75.03 | 57.11 | 67.91 | 77.1 | 0.173 | 27.91 | 498.7 | — | — | — | |
| Hyper-Motion2026.03 | 90.23 | 86.66 | 93.22 | 90.08 | 73.65 | 55.21 | 65.42 | 76.7 | 0.181 | 27.13 | 568.8 | — | — | — | |
| MimicMotion2026.03 | 88.47 | 86.01 | 92.11 | 89.95 | 73.05 | 55.07 | 65.14 | 74.4 | 0.198 | 26.66 | 611.5 | — | — | — | |
| HumanVid2026.03 | 86.91 | 85.33 | 91.01 | 88.21 | 72.72 | 54.61 | 64.19 | 73.7 | 0.213 | 25.54 | 637.1 | — | — | — | |
| †AnyFlow-FAR-Wan2.1-14B#Params=14B, Resolution=480 × 832, NFEs=42026.05 | — | — | — | — | — | — | — | — | — | — | — | 87.87 | 95.35 | 80.39 | |
| †FastVideo-CausalWan2.2-A14B-Preview#Params=14B, Resolution=480 × 832, NFEs=82026.05 | — | — | — | — | — | — | — | — | — | — | — | 86.82 | 94.81 | 78.82 | |
| †Wan2.1-I2V-14B#Params=14B, Resolution=480 × 832, NFEs=50×22026.05 | — | — | — | — | — | — | — | — | — | — | — | 87.71 | 95.12 | 80.3 | |
| CogVideoX-5B-I2V#Params=5B, Resolution=480 × 720, NFEs=50×22026.05 | — | — | — | — | — | — | — | — | — | — | — | 86.7 | 94.79 | 78.61 | |
| HunyuanVideo-I2V#Params=13B, Resolution=720 × 1280, NFEs=50×22026.05 | — | — | — | — | — | — | — | — | — | — | — | 86.82 | 95.1 | 78.54 | |
| MAGI-1#Params=24B, Resolution=720 × 1280, NFEs=32×22026.05 | — | — | — | — | — | — | — | — | — | — | — | 89.28 | 96.12 | 82.44 | |
| Step-Video-TI2V#Params=30B, Resolution=540 × 960, NFEs=50×22026.05 | — | — | — | — | — | — | — | — | — | — | — | 88.36 | 95.5 | 81.22 |