zsxkib / memo

MEMO is a state-of-the-art open-weight model for audio-driven talking video generation.

  • Public
  • 872 runs
  • A100 (80GB)
  • GitHub
  • Weights
  • Paper
  • License
Iterate in playground
  • Prediction

    zsxkib/memo:be54f93bc72d562ab2577f57b7eec44707efde55d058ee504c8b65a62d70fdf3
    ID
    tdtwxfnyj9rj00cpyc3vrbk73w
    Status
    Succeeded
    Source
    Web
    Hardware
    A100 (80GB)
    Total duration
    Created

    Input

    fps
    30
    audio
    Video Player is loading.
    Current Time 00:00:000
    Duration 00:00:000
    Loaded: 0%
    Stream Type LIVE
    Remaining Time 00:00:000
     
    1x
    image
    image
    cfg_scale
    3.5
    resolution
    512
    inference_steps
    20
    max_audio_seconds
    8
    num_generated_frames_per_clip
    16

    Output

    Generated in

Want to make some of these yourself?

Run this model