Text-to-Video Generation on WebVid10M
7.64FIDTF-T2V-Semi
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| TF-T2V-Semitraining_setting=semi-supervised, dataset=labeled WebVid10M + text-free Internal10M2023.12 | 7.64 | 366 | 30.32 | |
| TF-T2V2023.12 | 8.19 | 441 | 29.91 | |
| ModelScopeT2Vtraining_data=labeled WebVid10M2023.12 | 11.09 | 550 | 29.3 |