Text-to-Video Generation on VBench (test)
84.26Total ScoreWan2.1
Evaluation Results
| Method | Links | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Wan2.1#Params=1.3B, Resolution=832 × 480, NFE=50, First-Frame Enhancement (FFE)=false2026.05 | 84.26 | — | — | — | — | — | — | — | — | — | — | — | — | 85.3 | 80.09 | — | |
| One-Forcing (framewise)#Params=1.3B, Resolution=832 × 480, NFE=1*, First-Frame Enhancement (FFE)=true2026.05 | 83.76 | — | — | — | — | — | — | — | — | — | — | — | — | 85.22 | 77.91 | — | |
| Self Forcing#Params=1.3B, Resolution=832 × 480, NFE=4, First-Frame Enhancement (FFE)=false2026.05 | 83.46 | — | — | — | — | — | — | — | — | — | — | — | — | 84.77 | 78.24 | — | |
| SkyReels-V2#Params=1.3B, Resolution=960 × 540, NFE=30, First-Frame Enhancement (FFE)=false2026.05 | 82.67 | — | — | — | — | — | — | — | — | — | — | — | — | 84.7 | 74.53 | — | |
| Pyramid Flow#Params=2B, Resolution=640 × 384, NFE=20, First-Frame Enhancement (FFE)=false2026.05 | 81.72 | — | — | — | — | — | — | — | — | — | — | — | — | 84.74 | 69.62 | — | |
| One-Forcing (chunkwise)#Params=1.3B, Resolution=832 × 480, NFE=1*, First-Frame Enhancement (FFE)=true2026.05 | 81.6 | — | — | — | — | — | — | — | — | — | — | — | — | 83.65 | 73.41 | — | |
| Full-ComputeModel=HunyuanVideo, NFC=50, FLOPs (T)=75202026.02 | 81.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CausVid#Params=1.3B, Resolution=832 × 480, NFE=4, First-Frame Enhancement (FFE)=false2026.05 | 81.18 | — | — | — | — | — | — | — | — | — | — | — | — | 84.41 | 68.3 | — | |
| 50 stepsLatency(s)=332.92, Speed=1.00×, FLOPs(T)=14050.37, Ratio=1.00×, Mem(GB)=60.222026.02 | 80.93 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| RFCModel=HunyuanVideo, m=1, NFC=8.96, FLOPs (T)=1354.652026.02 | 80.83 | — | — | — | — | — | — | — | 18.5408 | 0.6352 | 0.1329 | — | — | — | — | — | |
| TaylorSeerModel=HunyuanVideo, N=5, m=1, NFC=10, FLOPs (T)=1510.212026.02 | 80.77 | — | — | — | — | — | — | — | 16.3606 | 0.5126 | 0.1985 | — | — | — | — | — | |
| RFCModel=HunyuanVideo, m=1, NFC=7.09, FLOPs (T)=1072.652026.02 | 80.49 | — | — | — | — | — | — | — | 18.2521 | 0.6155 | 0.1436 | — | — | — | — | — | |
| DPCache (K = 11)Latency(s)=83.22, Speed=4.05×, FLOPs(T)=3100.33, Ratio=4.53×, Mem(GB)=60.582026.02 | 80.35 | — | — | — | — | — | — | — | 23.11 | 0.7462 | 0.189 | — | — | — | — | — | |
| TaylorSeer¹Latency(s)=86.11, Speed=3.87×, FLOPs(T)=2821.20, Ratio=4.98×, Mem(GB)=84.472026.02 | 80.33 | — | — | — | — | — | — | — | 18.53 | 0.6025 | 0.3722 | — | — | — | — | — | |
| SpeCa¹Latency(s)=82.15, Speed=4.05×, FLOPs(T)=2731.61, Ratio=5.14×, Mem(GB)=84.472026.02 | 80.26 | — | — | — | — | — | — | — | 20.09 | 0.637 | 0.3554 | — | — | — | — | — | |
| DPCache (K = 9)Latency(s)=70.09, Speed=4.75×, FLOPs(T)=2538.79, Ratio=5.53×, Mem(GB)=60.582026.02 | 80.23 | — | — | — | — | — | — | — | 21.04 | 0.6852 | 0.2504 | — | — | — | — | — | |
| NOVA#Params=0.6B, Resolution=768 × 480, NFE=25, First-Frame Enhancement (FFE)=false2026.05 | 80.12 | — | — | — | — | — | — | — | — | — | — | — | — | 80.39 | 79.05 | — | |
| LTX-Video#Params=1.9B, Resolution=768 × 512, NFE=20, First-Frame Enhancement (FFE)=false2026.05 | 80 | — | — | — | — | — | — | — | — | — | — | — | — | 82.3 | 70.79 | — | |
| TaylorSeer²Latency(s)=79.84, Speed=4.17×, FLOPs(T)=2540.46, Ratio=5.53×, Mem(GB)=84.472026.02 | 79.99 | — | — | — | — | — | — | — | 18.23 | 0.5899 | 0.3967 | — | — | — | — | — | |
| TaylorSeerModel=HunyuanVideo, N=8, m=1, NFC=7, FLOPs (T)=1058.452026.02 | 79.59 | — | — | — | — | — | — | — | 15.1999 | 0.4408 | 0.2624 | — | — | — | — | — | |
| TaylorSeerModel=HunyuanVideo, N=6, m=1, NFC=9, FLOPs (T)=1359.192026.02 | 79.52 | — | — | — | — | — | — | — | 15.5321 | 0.4606 | 0.2448 | — | — | — | — | — | |
| TeaCache¹Latency(s)=79.56, Speed=4.18×, FLOPs(T)=2972.71, Ratio=4.73×, Mem(GB)=60.582026.02 | 79.25 | — | — | — | — | — | — | — | 17.55 | 0.5801 | 0.4081 | — | — | — | — | — | |
| MAGI-1#Params=4.5B, Resolution=832 × 480, NFE=64, First-Frame Enhancement (FFE)=false2026.05 | 79.18 | — | — | — | — | — | — | — | — | — | — | — | — | 82.04 | 67.74 | — | |
| ASD#Params=1.3B, Resolution=832 × 480, NFE=1*, First-Frame Enhancement (FFE)=true2026.05 | 79.12 | — | — | — | — | — | — | — | — | — | — | — | — | 81.35 | 70.19 | — | |
| 22% stepsLatency(s)=82.47, Speed=4.04×, FLOPs(T)=3095.22, Ratio=4.54×, Mem(GB)=60.222026.02 | 78.89 | — | — | — | — | — | — | — | 16.97 | 0.5753 | 0.4654 | — | — | — | — | — | |
| FORAModel=HunyuanVideo, N=6, NFC=9, FLOPs (T)=1359.192026.02 | 78.51 | — | — | — | — | — | — | — | 15.5221 | 0.4349 | 0.2743 | — | — | — | — | — | |
| SpeCa²Latency(s)=72.09, Speed=4.62×, FLOPs(T)=2254.75, Ratio=6.23×, Mem(GB)=84.472026.02 | 78.5 | — | — | — | — | — | — | — | 17.83 | 0.5867 | 0.4085 | — | — | — | — | — | |
| Causal-Forcing#Params=1.3B, Resolution=832 × 480, NFE=1, First-Frame Enhancement (FFE)=false2026.05 | 78.39 | — | — | — | — | — | — | — | — | — | — | — | — | 80.67 | 69.25 | — | |
| TeaCache²Latency(s)=70.05, Speed=4.75×, FLOPs(T)=2538.79, Ratio=5.53×, Mem(GB)=60.582026.02 | 78.17 | — | — | — | — | — | — | — | 17.75 | 0.5861 | 0.4137 | — | — | — | — | — | |
| FORAModel=HunyuanVideo, N=8, NFC=7, FLOPs (T)=1058.452026.02 | 77.5 | — | — | — | — | — | — | — | 14.8878 | 0.4114 | 0.2959 | — | — | — | — | — | |
| Self Forcing#Params=1.3B, Resolution=832 × 480, NFE=1, First-Frame Enhancement (FFE)=false2026.05 | 77.18 | — | — | — | — | — | — | — | — | — | — | — | — | 79.4 | 68.34 | — | |
| CausVidModel size=1.3B, Guidance strategy=Modulation guidance2026.02 | 65.43 | 98.45 | 86.59 | 57.65 | 19.02 | — | — | — | — | — | — | — | — | — | — | — | |
| CausVidModel size=1.3B, Guidance strategy=Normalized attention guidance2026.02 | 63.58 | 98.39 | 74.22 | 62.08 | 19.61 | — | — | — | — | — | — | — | — | — | — | — | |
| CausVidModel size=1.3B, Guidance strategy=Original + CLIP2026.02 | 62.82 | 98.63 | 76.38 | 57.77 | 18.49 | — | — | — | — | — | — | — | — | — | — | — | |
| CausVidModel size=1.3B, Guidance strategy=Original2026.02 | 62.72 | 98.76 | 75.25 | 57.85 | 19.01 | — | — | — | — | — | — | — | — | — | — | — | |
| HunyuanModel size=13B, Guidance strategy=Modulation guidance2026.02 | 57.56 | 99.03 | 53.61 | 56.5 | 21.09 | — | — | — | — | — | — | — | — | — | — | — | |
| Baseline vs NABLAJudge=Both are good2025.07 | 57.1 | 64.8 | — | — | — | — | — | — | — | — | — | — | — | — | 66.7 | 40 | |
| HunyuanModel size=13B, Guidance strategy=Original2026.02 | 56.68 | 99.23 | 50.51 | 55.88 | 21.08 | — | — | — | — | — | — | — | — | — | — | — | |
| BaselineJudge=Baseline is better2025.07 | 20.3 | 10.5 | — | — | — | — | — | — | — | — | — | — | — | — | 19.9 | 31.4 | |
| NABLAJudge=NABLA(0.7) is better, Sparsity=80%2025.07 | 18.4 | 15.2 | — | — | — | — | — | — | — | — | — | — | — | — | 13.3 | 26.7 | |
| Baseline vs NABLAJudge=Both are bad2025.07 | 4.1 | 9.5 | — | — | — | — | — | — | — | — | — | — | — | — | 0.9 | 1.9 | |
| BaseModel=Wan2.2-TI2V-5B2026.01 | — | 97.5 | 42 | 44.4 | — | 94.9 | 96.4 | 65.5 | — | — | — | — | — | — | — | — | |
| Base modelModel=Wan2.2-T2V-A14B, Inference steps=40, Function evaluations=802025.10 | — | 97.67 | — | 63.62 | — | 90.06 | 94.03 | — | — | — | — | — | 95.7 | — | — | — | |
| DMD2Inference steps=4, Function evaluations=42025.10 | — | 98.57 | — | 67.02 | — | 92.93 | 95.29 | — | — | — | — | — | 97.08 | — | — | — | |
| FPModel=CogVideoX-2B, Quantization=Full Precision2025.08 | — | 97.95 | 50 | 55.25 | 25.91 | 94.3 | 96.4 | 58.69 | — | — | — | 33.79 | — | — | — | — | |
| FPModel=CogVideoX-5B, Quantization=Full Precision2025.08 | — | 97.61 | 72.22 | 58.88 | 26.46 | 94.63 | 95.56 | 61.8 | — | — | — | 45.28 | — | — | — | — | |
| Full fine-tuningModel=Wan2.2-TI2V-5B2026.01 | — | 97.5 | 45.3 | 44.8 | — | 95.3 | 96.5 | 66.2 | — | — | — | — | — | — | — | — | |
| MotiveModel=Wan2.2-TI2V-5B, Selection percentage=10%, Aggregation=majority vote2026.01 | — | 97.6 | 48.3 | 45.6 | — | 95.1 | 96.6 | 65.5 | — | — | — | — | — | — | — | — | |
| Motive w/o MMModel=Wan2.2-TI2V-5B, Motion Masking=false2026.01 | — | 97.4 | 43.8 | 45.2 | — | 94.9 | 96.5 | 64.8 | — | — | — | — | — | — | — | — | |
| Phased DMDInference steps=4, Function evaluations=42025.10 | — | 97.74 | — | 65.73 | — | 91.15 | 94.4 | — | — | — | — | — | 95.26 | — | — | — | |
| PTQ4DiTModel=CogVideoX-2B, Quantization=W4A42025.08 | — | 99.3 | 0 | 28.5 | 11.11 | 95.33 | 97.61 | 20.66 | — | — | — | 2.11 | — | — | — | — | |
| PTQ4DiTModel=CogVideoX-5B, Quantization=W4A42025.08 | — | 96.38 | 0 | 28.63 | 7.37 | 95.09 | 97.29 | 41.48 | — | — | — | 0 | — | — | — | — | |
| Q-DiTModel=CogVideoX-2B, Quantization=W4A42025.08 | — | 99.14 | 0 | 27.66 | 8.43 | 96.52 | 98.09 | 26.26 | — | — | — | 1.16 | — | — | — | — | |
| Q-DiTModel=CogVideoX-5B, Quantization=W4A42025.08 | — | 95.71 | 36.11 | 33 | 1.91 | 96.99 | 98.26 | 40.8 | — | — | — | 0.22 | — | — | — | — | |
| QuaRotModel=CogVideoX-2B, Quantization=W4A42025.08 | — | 97.54 | 13.89 | 39.59 | 19.57 | 92.35 | 96.18 | 43.22 | — | — | — | 12.21 | — | — | — | — | |
| QuaRotModel=CogVideoX-5B, Quantization=W4A42025.08 | — | 97.77 | 15.28 | 35.36 | 15.31 | 92.71 | 97.23 | 29.41 | — | — | — | 8.36 | — | — | — | — | |
| Random selectionModel=Wan2.2-TI2V-5B, Selection percentage=10%2026.01 | — | 97.3 | 41.6 | 44.6 | — | 94.7 | 96.2 | 65.2 | — | — | — | — | — | — | — | — | |
| S2Q-VDiTModel=CogVideoX-2B, Quantization=W4A42025.08 | — | 98.09 | 36.11 | 52.31 | 24.9 | 93.99 | 96.15 | 53.71 | — | — | — | 34.23 | — | — | — | — | |
| S2Q-VDiTModel=CogVideoX-5B, Quantization=W4A42025.08 | — | 97.18 | 47.22 | 55.35 | 26.02 | 93.69 | 96.25 | 58.76 | — | — | — | 36.56 | — | — | — | — | |
| SmoothQuantModel=CogVideoX-2B, Quantization=W4A42025.08 | — | 98.95 | 0 | 28.31 | 9.74 | 94.65 | 97.62 | 29.76 | — | — | — | 5.31 | — | — | — | — | |
| SmoothQuantModel=CogVideoX-5B, Quantization=W4A42025.08 | — | 95.76 | 1.39 | 29.99 | 6.51 | 96.02 | 96.54 | 40.3 | — | — | — | 0.44 | — | — | — | — | |
| ViDiT-QModel=CogVideoX-2B, Quantization=W4A42025.08 | — | 97.57 | 12.5 | 42.03 | 19.61 | 92.43 | 96.08 | 45.56 | — | — | — | 11.91 | — | — | — | — | |
| ViDiT-QModel=CogVideoX-5B, Quantization=W4A42025.08 | — | 97.09 | 15.28 | 36.71 | 16.91 | 93.01 | 96.37 | 31.95 | — | — | — | 10.85 | — | — | — | — |