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 1.27.1	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	25.129 ms	2 - 705 MB	NPU
DDColor	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	30.207 ms	1 - 499 MB	NPU
DDColor	ONNX	float	Snapdragon® X2 Elite	24.825 ms	2 - 2 MB	NPU
DDColor	ONNX	float	Snapdragon® X Elite	67.765 ms	112 - 112 MB	NPU
DDColor	ONNX	float	Snapdragon® 8 Gen 3 Mobile	48.09 ms	0 - 682 MB	NPU
DDColor	ONNX	float	Snapdragon® 8 Gen 1 Mobile	81.625 ms	0 - 533 MB	NPU
DDColor	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	62.037 ms	1 - 6 MB	NPU
DDColor	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	67.643 ms	0 - 130 MB	NPU
DDColor	ONNX	float	Qualcomm® QCS8450	81.625 ms	0 - 533 MB	NPU
DDColor	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	74.628 ms	1 - 5 MB	NPU
DDColor	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	67.765 ms	112 - 112 MB	NPU
DDColor	ONNX	float	Qualcomm® Dragonwing™ Q-8750	30.207 ms	1 - 499 MB	NPU
DDColor	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	24.741 ms	0 - 611 MB	NPU
DDColor	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	31.175 ms	1 - 550 MB	NPU
DDColor	QNN_DLC	float	Snapdragon® X2 Elite	25.607 ms	1 - 1 MB	NPU
DDColor	QNN_DLC	float	Snapdragon® X Elite	58.726 ms	1 - 1 MB	NPU
DDColor	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	38.632 ms	0 - 1149 MB	NPU
DDColor	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	68.069 ms	0 - 409 MB	NPU
DDColor	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	54.395 ms	1 - 5 MB	NPU
DDColor	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	59.01 ms	1 - 4 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	68.069 ms	0 - 409 MB	NPU
DDColor	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	63.446 ms	3 - 6 MB	NPU
DDColor	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	58.726 ms	1 - 1 MB	NPU
DDColor	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	31.175 ms	1 - 550 MB	NPU
DDColor	QNN_DLC	float	Qualcomm® SA8295P	67.289 ms	1 - 312 MB	NPU
DDColor	TFLITE	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	23.863 ms	0 - 653 MB	NPU
DDColor	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	34.628 ms	1 - 483 MB	NPU
DDColor	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	41.688 ms	1 - 667 MB	NPU
DDColor	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	74.25 ms	0 - 499 MB	NPU
DDColor	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	57.87 ms	1 - 117 MB	NPU
DDColor	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	71.204 ms	1 - 8 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	74.25 ms	0 - 499 MB	NPU
DDColor	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	71.76 ms	1 - 117 MB	NPU
DDColor	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	34.628 ms	1 - 483 MB	NPU
DDColor	TFLITE	float	Qualcomm® SA8295P	69.674 ms	1 - 349 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.