--- library_name: pytorch license: apache-2.0 tags: - android pipeline_tag: image-to-image --- ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/web-assets/model_demo.png) # 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](https://github.com/piddnad/DDColor/). This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.61.0/src/qai_hub_models/models/ddcolor) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary). Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) 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 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/releases/v0.61.0/ddcolor-onnx-float.zip) | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/releases/v0.61.0/ddcolor-qnn_dlc-float.zip) | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddcolor/releases/v0.61.0/ddcolor-tflite-float.zip) For more device-specific assets and performance metrics, visit **[DDColor on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/ddcolor)**. ### Option 2: Export with Custom Configurations Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.61.0/src/qai_hub_models/models/ddcolor) 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](https://github.com/qualcomm/ai-hub-models/blob/v0.61.0/src/qai_hub_models/models/ddcolor) 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® X2 Elite | 28.138 ms | 2 - 2 MB | NPU | DDColor | ONNX | float | Snapdragon® X Elite | 72.436 ms | 113 - 113 MB | NPU | DDColor | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 45.917 ms | 0 - 1502 MB | NPU | DDColor | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 83.913 ms | 0 - 634 MB | NPU | DDColor | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 63.095 ms | 1 - 5 MB | NPU | DDColor | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 72.798 ms | 0 - 130 MB | NPU | DDColor | ONNX | float | Qualcomm® QCS8450 | 83.913 ms | 0 - 634 MB | NPU | DDColor | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 104.762 ms | 1 - 4 MB | NPU | DDColor | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 72.436 ms | 113 - 113 MB | NPU | DDColor | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 35.16 ms | 2 - 800 MB | NPU | DDColor | ONNX | float | Snapdragon® 8 Elite Mobile | 35.16 ms | 2 - 800 MB | NPU | DDColor | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 27.381 ms | 0 - 735 MB | NPU | DDColor | QNN_DLC | float | Snapdragon® X2 Elite | 29.421 ms | 1 - 1 MB | NPU | DDColor | QNN_DLC | float | Snapdragon® X Elite | 62.593 ms | 1 - 1 MB | NPU | DDColor | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 41.544 ms | 1 - 562 MB | NPU | DDColor | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 73.072 ms | 0 - 462 MB | NPU | DDColor | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 59.309 ms | 1 - 4 MB | NPU | DDColor | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 129.547 ms | 1 - 453 MB | NPU | DDColor | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 62.434 ms | 1 - 3 MB | NPU | DDColor | QNN_DLC | float | Qualcomm® SA8775P | 65.755 ms | 1 - 453 MB | NPU | DDColor | QNN_DLC | float | Qualcomm® SA8650P | 65.755 ms | 1 - 453 MB | NPU | DDColor | QNN_DLC | float | Qualcomm® SA8255P | 65.755 ms | 1 - 453 MB | NPU | DDColor | QNN_DLC | float | Qualcomm® QCS8450 | 73.072 ms | 0 - 462 MB | NPU | DDColor | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 75.832 ms | 1 - 4 MB | NPU | DDColor | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 62.593 ms | 1 - 1 MB | NPU | DDColor | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 31.552 ms | 1 - 615 MB | NPU | DDColor | QNN_DLC | float | Qualcomm® SA7255P | 129.547 ms | 1 - 453 MB | NPU | DDColor | QNN_DLC | float | Qualcomm® SA8295P | 69.512 ms | 0 - 330 MB | NPU | DDColor | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 31.552 ms | 1 - 615 MB | NPU | DDColor | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 27.395 ms | 0 - 644 MB | NPU | DDColor | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 43.068 ms | 1 - 1423 MB | NPU | DDColor | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 78.852 ms | 1 - 551 MB | NPU | DDColor | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 58.201 ms | 1 - 117 MB | NPU | DDColor | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 124.581 ms | 1 - 798 MB | NPU | DDColor | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 67.703 ms | 0 - 4 MB | NPU | DDColor | TFLITE | float | Qualcomm® SA8775P | 72.352 ms | 1 - 850 MB | NPU | DDColor | TFLITE | float | Qualcomm® SA8650P | 72.352 ms | 1 - 850 MB | NPU | DDColor | TFLITE | float | Qualcomm® SA8255P | 72.352 ms | 1 - 850 MB | NPU | DDColor | TFLITE | float | Qualcomm® QCS8450 | 78.852 ms | 1 - 551 MB | NPU | DDColor | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 72.407 ms | 1 - 116 MB | NPU | DDColor | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 33.881 ms | 1 - 981 MB | NPU | DDColor | TFLITE | float | Qualcomm® SA7255P | 124.581 ms | 1 - 798 MB | NPU | DDColor | TFLITE | float | Qualcomm® SA8295P | 73.535 ms | 1 - 378 MB | NPU | DDColor | TFLITE | float | Snapdragon® 8 Elite Mobile | 33.881 ms | 1 - 981 MB | NPU | DDColor | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 27.519 ms | 1 - 1042 MB | NPU ## License * The license for the original implementation of DDColor can be found [here](https://github.com/piddnad/DDColor/blob/master/LICENSE). ## References * [DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders](https://arxiv.org/abs/2201.03545) * [Source Model Implementation](https://github.com/piddnad/DDColor/) ## Community * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI. * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).