Text-to-Video Generation on Concerts dataset
5,020.37FADsequential two-step text-to-audio-video generation pipeline
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| sequential two-step text-to-audio-video generation pipelinevideo_generation_component=CogvideoX, audio_generation_component=MM-Audio, procedure=two-step sequential2026.03 | 5,020.37 | 206.49 |