pschaldenbrand / text2video

Method for generating bizarre looking videos from a series of language descriptions of the video. From the Bot Intelligence Group at CMU: Peter Schaldenbrand, Zhixuan Liu, & Jean Oh

  • Public
  • 8.4K runs
  • T4
  • GitHub
  • Paper
  • License
  • Prediction

    pschaldenbrand/text2video:ed5518ac
    ID
    5cdcmxg5ovbyfdl633uriwmxii
    Status
    Succeeded
    Source
    Web
    Hardware
    T4
    Total duration
    Created

    Input

    fast
    width
    640
    height
    360
    prompts
    The dog is walking through a beautiful forest&A dog flying into the night sky
    frame_rate
    8
    temperature
    30
    frames_per_promt
    40

    Output

    Generated in
  • Prediction

    pschaldenbrand/text2video:ed5518ac
    ID
    qazx4dkferhvhjg6f53an2y6sm
    Status
    Succeeded
    Source
    Web
    Hardware
    T4
    Total duration
    Created
    by @pschaldenbrand

    Input

    fast
    width
    640
    height
    360
    prompts
    Once upon a midnight dreary, while I pondered, weak and weary&Over many a quaint and curious volume of forgotten lore&While I nodded, nearly napping, suddenly there came a tapping&As of some one gently rapping, rapping at my chamber door&“’Tis some visitor,” I muttered, “tapping at my chamber door&Only this and nothing more.”
    frame_rate
    8
    temperature
    30
    frames_per_promt
    40

    Output

    Generated in
  • Prediction

    pschaldenbrand/text2video:ed5518ac
    ID
    7u7tpxas6vcv7fo77lywr7ttkq
    Status
    Succeeded
    Source
    Web
    Hardware
    T4
    Total duration
    Created

    Input

    fast
    width
    640
    height
    360
    prompts
    A unicorn walks through a beautiful forest at dawn&The unicorn dances through the forest as the sun sets
    frame_rate
    8
    temperature
    30
    frames_per_promt
    80

    Output

    Generated in

Want to make some of these yourself?

Run this model