Qualcomm® AI HubAI Hub
HomeCompute ModelsXLSR-Quantized

XLSR-Quantized

Upscale images in real time.

XLSR is designed for lightweight real-time upscaling of images.

Snapdragon® X Elite
0.75ms
Inference Time
7MB
Memory Usage
21NPU
Layers

Technical Details

Model checkpoint:xlsr_3x_checkpoint
Input resolution:128x128
Number of parameters:22.0K
Model size:39.0 KB

Applicable Scenarios

  • Virtual Real Estate Tours
  • Gaming
  • ARVR

Licenses

Source Model:OTHER
Deployable Model:AI Model Hub License

Tags

  • quantized
    A “quantized” model can run in low or mixed precision, which can substantially reduce inference latency.

Supported Compute Chipsets

  • Snapdragon® X Elite