Image-to-Image
PyTorch
android

DDColor: Optimized for Qualcomm Devices

DDColor is a coloring algorithm that produces natural, vivid color results from incoming black and white images.

This is based on the implementation of DDColor found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.

Getting Started

There are two ways to deploy this model on your device:

Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

Runtime Precision Chipset SDK Versions Download
ONNX float Universal QAIRT 2.45, ONNX Runtime 1.25.0 Download
QNN_DLC float Universal QAIRT 2.45 Download
TFLITE float Universal QAIRT 2.45 Download

For more device-specific assets and performance metrics, visit DDColor on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:

  • Custom weights (e.g., fine-tuned checkpoints)
  • Custom input shapes
  • Target device and runtime configurations

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for DDColor on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.image_editing

Model Stats:

  • Model checkpoint: ddcolor_paper_tiny.pth
  • Input resolution: 224x224
  • Number of parameters: 56.3M
  • Model size (float): 215 MB
  • Model size (w8a8): 54.8 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
DDColor ONNX float Snapdragon® X2 Elite 28.244 ms 2 - 2 MB NPU
DDColor ONNX float Snapdragon® X Elite 72.621 ms 113 - 113 MB NPU
DDColor ONNX float Snapdragon® 8 Gen 3 Mobile 44.913 ms 0 - 1474 MB NPU
DDColor ONNX float Snapdragon® 8 Gen 1 Mobile 102.53 ms 0 - 535 MB NPU
DDColor ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 73.153 ms 1 - 133 MB NPU
DDColor ONNX float Qualcomm® QCS8450 102.53 ms 0 - 535 MB NPU
DDColor ONNX float Qualcomm® Dragonwing™ IQ-9075 81.383 ms 1 - 5 MB NPU
DDColor ONNX float Snapdragon® 8 Elite Gen 5 Mobile 27.499 ms 2 - 739 MB NPU
DDColor ONNX float Snapdragon® 8 Elite Mobile 35.348 ms 2 - 800 MB NPU
DDColor ONNX float Qualcomm® Dragonwing™ Q-8750 35.348 ms 2 - 800 MB NPU
DDColor ONNX float Qualcomm® Dragonwing™ IQ-X7181 72.621 ms 113 - 113 MB NPU
DDColor QNN_DLC float Snapdragon® X2 Elite 27.841 ms 1 - 1 MB NPU
DDColor QNN_DLC float Snapdragon® X Elite 62.284 ms 1 - 1 MB NPU
DDColor QNN_DLC float Snapdragon® 8 Gen 3 Mobile 41.529 ms 0 - 559 MB NPU
DDColor QNN_DLC float Snapdragon® 8 Gen 1 Mobile 73.893 ms 0 - 463 MB NPU
DDColor QNN_DLC float Qualcomm® QCS8275 129.665 ms 1 - 453 MB NPU
DDColor QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 61.869 ms 1 - 3 MB NPU
DDColor QNN_DLC float Qualcomm® SA8775P 65.631 ms 1 - 453 MB NPU
DDColor QNN_DLC float Qualcomm® SA8650P 65.631 ms 1 - 453 MB NPU
DDColor QNN_DLC float Qualcomm® SA8255P 65.631 ms 1 - 453 MB NPU
DDColor QNN_DLC float Qualcomm® QCS8450 73.893 ms 0 - 463 MB NPU
DDColor QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 66.492 ms 1 - 4 MB NPU
DDColor QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 27.359 ms 0 - 631 MB NPU
DDColor QNN_DLC float Qualcomm® SA7255P 129.665 ms 1 - 453 MB NPU
DDColor QNN_DLC float Snapdragon® 8 Elite Mobile 31.996 ms 1 - 620 MB NPU
DDColor QNN_DLC float Qualcomm® SA8295P 69.54 ms 0 - 330 MB NPU
DDColor QNN_DLC float Qualcomm® Dragonwing™ Q-8750 31.996 ms 1 - 620 MB NPU
DDColor QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 62.284 ms 1 - 1 MB NPU
DDColor TFLITE float Snapdragon® 8 Gen 3 Mobile 43.191 ms 1 - 1423 MB NPU
DDColor TFLITE float Snapdragon® 8 Gen 1 Mobile 80.702 ms 1 - 552 MB NPU
DDColor TFLITE float Qualcomm® QCS8275 124.76 ms 1 - 800 MB NPU
DDColor TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 68.115 ms 1 - 4 MB NPU
DDColor TFLITE float Qualcomm® SA8775P 72.261 ms 1 - 854 MB NPU
DDColor TFLITE float Qualcomm® SA8650P 72.261 ms 1 - 854 MB NPU
DDColor TFLITE float Qualcomm® SA8255P 72.261 ms 1 - 854 MB NPU
DDColor TFLITE float Qualcomm® QCS8450 80.702 ms 1 - 552 MB NPU
DDColor TFLITE float Qualcomm® Dragonwing™ IQ-9075 72.291 ms 1 - 116 MB NPU
DDColor TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 27.555 ms 1 - 1032 MB NPU
DDColor TFLITE float Qualcomm® SA7255P 124.76 ms 1 - 800 MB NPU
DDColor TFLITE float Snapdragon® 8 Elite Mobile 33.765 ms 1 - 982 MB NPU
DDColor TFLITE float Qualcomm® SA8295P 73.621 ms 1 - 378 MB NPU
DDColor TFLITE float Qualcomm® Dragonwing™ Q-8750 33.765 ms 1 - 982 MB NPU

License

  • The license for the original implementation of DDColor can be found here.

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for qualcomm/DDColor