Qualcomm® AI HubAI Hub

AOT-GAN

High resolution image in-painting on-device.

AOT-GAN is a machine learning model that allows to erase and in-paint part of given input image.

Snapdragon® X Elite
TorchScripttoQualcomm® AI Engine Direct
146ms
Inference Time
4MB
Memory Usage
275NPU
Layers

Technical Details

Model checkpoint:CelebAHQ
Input resolution:512x512
Number of parameters:15.2M
Model size:58.0 MB

Applicable Scenarios

  • Image editing

Licenses

Source Model:MIT
Deployable Model:AI Model Hub License

Supported Compute Chipsets

  • Snapdragon® X Elite