n1jl0091/video-llava-7b-hf_replicate_n1jl0091

Upload an image or video, and Video-LLaVa will give you a text description of what it "sees."

Public
102 runs
  • Prediction

    n1jl0091/video-llava-7b-hf_replicate_n1jl0091:ff284eb7daa7ace568fe353efecc4728c1f1844771462d7ec3b4844741270ddf
    ID
    007twqr00hrj20ck81r8068ffm
    Status
    Succeeded
    Source
    Web
    Hardware
    A100 (80GB)
    Total duration
    Created

    Input

    top_p
    0.9
    videos
    prompts
    [ "What is happening in this video?" ]
    num_frames
    10
    temperature
    0.1
    max_new_tokens
    500

    Output

    [ "In this video, a woman is standing in a kitchen and preparing food.Ъ" ]
    Generated in

Want to make some of these yourself?

Run this model