Qualcomm® AI HubAI Hub

    HomeAll ModelsStyleGAN2

    StyleGAN2

    Generate realistic, randomized images of real classes.

    StyleGAN2 is a machine learning model that generates realistic images from random input state vectors.

    TorchScriptTFLite
    1.01s
    Inference Time
    911-935MB
    Memory Usage
    402CPU
    78GPU
    Layers
    See more metrics
    Model RepositoryHugging FaceResearch Paper

    Technical Details

    Model checkpoint:StyleGAN2 (afhqcat dataset)
    Input resolution:1x512
    Number of parameters:94.6M
    Model size:361 MB

    Applicable Scenarios

      Supported Form Factors

      • Phone
      • Tablet
      • IoT
      • XR

      Licenses

      Source Model:OTHER
      Deployable Model:AI Model Hub License

      Tags

      • real-time
        A “real-time” model can typically achieve 5-60 predictions per second. This translates to latency ranging up to 200 ms per prediction.

      Supported Devices

      • Google Pixel 3
      • Google Pixel 3a
      • Google Pixel 3a XL
      • Google Pixel 4
      • Google Pixel 4a
      • Google Pixel 5a 5G
      • QCS8550 (Proxy)
      • Samsung Galaxy S21
      • Samsung Galaxy S21 Ultra
      • Samsung Galaxy S21+
      • Samsung Galaxy S22 5G
      • Samsung Galaxy S22 Ultra 5G
      • Samsung Galaxy S22+ 5G
      • Samsung Galaxy S23
      • Samsung Galaxy S23 Ultra
      • Samsung Galaxy S23+
      • Samsung Galaxy S24
      • Samsung Galaxy S24 Ultra
      • Samsung Galaxy S24+
      • Samsung Galaxy Tab S8
      • Xiaomi 12
      • Xiaomi 12 Pro

      Supported Chipsets

      • Qualcomm® QCS8550
      • Snapdragon® 8 Gen 1 Mobile
      • Snapdragon® 8 Gen 2 Mobile
      • Snapdragon® 8 Gen 3 Mobile
      • Snapdragon® 888 Mobile