VideoCrafter1

Reported on 5 benchmarks across 1 task · 1 paper · 1 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· 2023-10-30
60.85
best: 63.98 (VideoCrafter2)
SOTA
VideoCrafter1: Open Diffusion Models for High-Quality Video Generation arXiv:2310.19512
Text-to-Video GenerationonEvalCrafter Text-to-Video (ECTV) Dataset
Temporal Consistency· uses extra data· 2023-10-30
55.89
best: 61.46 (VideoCrafter2)
VideoCrafter1: Open Diffusion Models for High-Quality Video Generation arXiv:2310.19512
Text-to-Video GenerationonEvalCrafter Text-to-Video (ECTV) Dataset
Text-to-Video Alignment· uses extra data· 2023-10-30
61.95
best: 68.49 (Lavie)
VideoCrafter1: Open Diffusion Models for High-Quality Video Generation arXiv:2310.19512
Text-to-Video GenerationonEvalCrafter Text-to-Video (ECTV) Dataset
Total Score· uses extra data· 2023-10-30
232
best: 243 (VideoCrafter2)
VideoCrafter1: Open Diffusion Models for High-Quality Video Generation arXiv:2310.19512
Text-to-Video GenerationonEvalCrafter Text-to-Video (ECTV) Dataset
Visual Quality· uses extra data· 2023-10-30
53.08
best: 54.82 (VideoCrafter2)
VideoCrafter1: Open Diffusion Models for High-Quality Video Generation arXiv:2310.19512