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 2.50, ONNX Runtime 1.30.0	Download
QNN_DLC	float	Universal	QAIRT 2.50	Download
TFLITE	float	Universal	QAIRT 2.50	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:

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

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
DDColor	ONNX	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	28.521 ms	2 - 726 MB	NPU
DDColor	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	38.44 ms	2 - 509 MB	NPU
DDColor	ONNX	float	Snapdragon® X2 Elite	28.581 ms	2 - 2 MB	NPU
DDColor	ONNX	float	Snapdragon® X Elite	75.141 ms	112 - 112 MB	NPU
DDColor	ONNX	float	Snapdragon® 8 Gen 3 Mobile	48.677 ms	2 - 1256 MB	NPU
DDColor	ONNX	float	Snapdragon® 8 Gen 1 Mobile	82.678 ms	3 - 514 MB	NPU
DDColor	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	69.211 ms	1 - 6 MB	NPU
DDColor	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	75.295 ms	0 - 115 MB	NPU
DDColor	ONNX	float	Qualcomm® QCS8450	82.678 ms	3 - 514 MB	NPU
DDColor	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	78.095 ms	1 - 5 MB	NPU
DDColor	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	75.141 ms	112 - 112 MB	NPU
DDColor	ONNX	float	Qualcomm® Dragonwing™ Q-8750	38.44 ms	2 - 509 MB	NPU
DDColor	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	25.361 ms	0 - 620 MB	NPU
DDColor	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	31.885 ms	1 - 561 MB	NPU
DDColor	QNN_DLC	float	Snapdragon® X2 Elite	27.176 ms	1 - 1 MB	NPU
DDColor	QNN_DLC	float	Snapdragon® X Elite	59.28 ms	1 - 1 MB	NPU
DDColor	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	39.338 ms	0 - 1151 MB	NPU
DDColor	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	68.909 ms	0 - 416 MB	NPU
DDColor	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	55.457 ms	1 - 5 MB	NPU
DDColor	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	59.419 ms	1 - 3 MB	NPU
DDColor	QNN_DLC	float	Qualcomm® SA8650P	65.734 ms	1 - 452 MB	NPU
DDColor	QNN_DLC	float	Qualcomm® SA8255P	65.734 ms	1 - 452 MB	NPU
DDColor	QNN_DLC	float	Qualcomm® QCS8450	68.909 ms	0 - 416 MB	NPU
DDColor	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	64.29 ms	3 - 6 MB	NPU
DDColor	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	59.28 ms	1 - 1 MB	NPU
DDColor	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	31.885 ms	1 - 561 MB	NPU
DDColor	QNN_DLC	float	Qualcomm® SA8295P	69.453 ms	1 - 307 MB	NPU
DDColor	TFLITE	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	23.846 ms	0 - 643 MB	NPU
DDColor	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	34.567 ms	0 - 481 MB	NPU
DDColor	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	41.281 ms	1 - 662 MB	NPU
DDColor	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	73.222 ms	1 - 501 MB	NPU
DDColor	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	57.789 ms	1 - 118 MB	NPU
DDColor	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	70.927 ms	1 - 4 MB	NPU
DDColor	TFLITE	float	Qualcomm® SA8650P	72.46 ms	1 - 852 MB	NPU
DDColor	TFLITE	float	Qualcomm® SA8255P	72.46 ms	1 - 852 MB	NPU
DDColor	TFLITE	float	Qualcomm® QCS8450	73.222 ms	1 - 501 MB	NPU
DDColor	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	71.667 ms	1 - 117 MB	NPU
DDColor	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	34.567 ms	0 - 481 MB	NPU
DDColor	TFLITE	float	Qualcomm® SA8295P	69.758 ms	1 - 348 MB	NPU

License

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

References

• DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders
• Source Model Implementation

Community

• Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
• For questions or feedback please reach out to us.