# Video super resolution and display with LiteRT Video super resolution (VSR) is supported on Qualcomm AI Hub quantized INT8 models with 128 ×128 input resolution and 512 × 512 output resolution. Select [QuickSRNetSmall-Quantized](https://aihub.qualcomm.com/iot/models/quicksrnetsmall) to download the model file. Run the use case on the target device with file source (128 ×128 input resolution): gst-launch-1.0 -e --gst-debug=2 \ filesrc location=/etc/media/video.mp4 ! qtdemux ! queue ! h264parse ! v4l2h264dec capture-io-mode=4 output-io-mode=4 ! video/x-raw,format=NV12 ! \ queue ! tee name=split split. ! queue ! qtivcomposer name=mixer sink_0::position="<0, 0>" sink_0::dimensions="<960, 1080>" \ sink_1::position="<960, 0>" sink_1::dimensions="<960, 1080>" ! queue ! waylandsink sync=true fullscreen=true split. ! \ qtimlvconverter ! queue ! qtimltflite delegate=external external-delegate-path=libQnnTFLiteDelegate.so \ external-delegate-options="QNNExternalDelegate,backend_type=htp;" model=/etc/models/Quicksrnet_Small_Quantized.tflite ! \ queue ! qtimlpostprocess module=srnet ! video/x-raw,format=RGB ! queue ! mixer. Copy to clipboard The output is displayed on a Wayland display. **Figure : Pipeline for video resolution (Wayland display)** For information about expected output and plugins used in this pipeline, see the [Video super-resolution](https://docs.qualcomm.com/doc/80-80021-50/topic/video-super-resolution.html) sample application. ## Related information [qtimlvsuperresolution](https://docs.qualcomm.com/doc/80-80021-50/topic/qtimlvsuperresolution.html) Last Published: Mar 26, 2026 [Previous Topic Pose estimation and encode with LiteRT](https://docs.qualcomm.com/bundle/publicresource/80-80021-50/topics/single-camera-stream-with-pose-estimation-and-encode.md) [Next Topic Single stream from camera to RTSP with ML detection](https://docs.qualcomm.com/bundle/publicresource/80-80021-50/topics/single-stream-from-camera-to-rtsp-with-ml-detection.md)