ModelScopeT2V

Reported on 3 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 Processing3 results

Text-to-Video GenerationonMSR-VTT
FID· 2023-08-12
11.09
best: 8.19 (TF-T2V)
SOTA
ModelScope Text-to-Video Technical Report arXiv:2308.06571
Text-to-Video GenerationonMSR-VTT
CLIPSIM· 2023-08-12
0.293
best: 0.3125 (PixelDance)
ModelScope Text-to-Video Technical Report arXiv:2308.06571
Text-to-Video GenerationonMSR-VTT
FVD· 2023-08-12
550
best: 998 (MagicVideo)
ModelScope Text-to-Video Technical Report arXiv:2308.06571