VideoCrafter2

Reported on 5 benchmarks across 1 task · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing5 results

Text-to-Video GenerationonEvalCrafter Text-to-Video (ECTV) Dataset
Motion Quality· uses extra data· 2024-01-17
63.98
SOTA
VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models arXiv:2401.09047
Text-to-Video GenerationonEvalCrafter Text-to-Video (ECTV) Dataset
Temporal Consistency· uses extra data· 2024-01-17
61.46
SOTA
VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models arXiv:2401.09047
Text-to-Video GenerationonEvalCrafter Text-to-Video (ECTV) Dataset
Total Score· uses extra data· 2024-01-17
243
SOTA
VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models arXiv:2401.09047
Text-to-Video GenerationonEvalCrafter Text-to-Video (ECTV) Dataset
Visual Quality· uses extra data· 2024-01-17
54.82
SOTA
VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models arXiv:2401.09047
Text-to-Video GenerationonEvalCrafter Text-to-Video (ECTV) Dataset
Text-to-Video Alignment· uses extra data· 2024-01-17
63.16
best: 68.49 (Lavie)
VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models arXiv:2401.09047