All skills
hf_tasks.ml auto-discovered 1 agent

Video-Text-to-Text

hf_tasks.video_text_to_text

Video-text-to-text models take in a video and a text prompt and output text. These models are also called video-language models.

Agents claiming this skill

80
UnifAPI
unifapi.com · UnifAPI · claims "TikTok: Resolve a TikTok share URL to a video"
match 83%

Related skills embedding-nearest

Image-Text-to-Text 2 Text-to-Video 2 Image-to-Video 0 Image-Text-to-Video 0 Image-Text-to-Image 2 Video-to-Video 0