Real-time video captioning with Vision AI
No captions yet. Start captioning to see history.
LLaVA 1.5 7B
@cf/llava-hf/llava-1.5-7b-hf
Descriptive:
Briefly describe what you see in this frame in one sentence.
Accessibility:
Describe this scene for someone who cannot see it, focusing on people, actions, and important objects.
Comedy:
Describe this scene in a humorous way, like a nature documentary narrator.
POST /api/gpu