library_name: pytorch
license: other
tags:
- generative_ai
- android
pipeline_tag: unconditional-image-generation
ControlNet-Canny: Optimized for Mobile Deployment
Generating visual arts from text prompt and input guiding image
On-device, high-resolution image synthesis from text and image prompts. ControlNet guides Stable-diffusion with provided input image to generate accurate images from given input prompt.
This model is an implementation of ControlNet-Canny found here.
This repository provides scripts to run ControlNet-Canny on Qualcomm® devices. More details on model performance across various devices, can be found here.
Model Details
- Model Type: Model_use_case.image_generation
- Model Stats:
- Input: Text prompt and input image as a reference
- Conditioning Input: Canny-Edge
- Text Encoder Number of parameters: 340M
- UNet Number of parameters: 865M
- VAE Decoder Number of parameters: 83M
- ControlNet Number of parameters: 361M
- Model size: 1.4GB
| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model |
|---|---|---|---|---|---|---|---|---|
| text_encoder | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_CONTEXT_BINARY | 7.426 ms | 0 - 9 MB | NPU | Use Export Script |
| text_encoder | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_CONTEXT_BINARY | 3.334 ms | 0 - 2 MB | NPU | Use Export Script |
| text_encoder | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | PRECOMPILED_QNN_ONNX | 5.517 ms | 0 - 162 MB | NPU | Use Export Script |
| text_encoder | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_CONTEXT_BINARY | 3.574 ms | 0 - 10 MB | NPU | Use Export Script |
| text_encoder | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_CONTEXT_BINARY | 7.426 ms | 0 - 9 MB | NPU | Use Export Script |
| text_encoder | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_CONTEXT_BINARY | 3.328 ms | 0 - 2 MB | NPU | Use Export Script |
| text_encoder | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_CONTEXT_BINARY | 3.344 ms | 0 - 3 MB | NPU | Use Export Script |
| text_encoder | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_CONTEXT_BINARY | 3.574 ms | 0 - 10 MB | NPU | Use Export Script |
| text_encoder | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_CONTEXT_BINARY | 2.32 ms | 0 - 18 MB | NPU | Use Export Script |
| text_encoder | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 3.993 ms | 0 - 19 MB | NPU | Use Export Script |
| text_encoder | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_CONTEXT_BINARY | 1.804 ms | 0 - 14 MB | NPU | Use Export Script |
| text_encoder | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | PRECOMPILED_QNN_ONNX | 3.116 ms | 0 - 16 MB | NPU | Use Export Script |
| text_encoder | w8a16 | Snapdragon 7 Gen 5 QRD | Snapdragon® 7 Gen 5 Mobile | QNN_CONTEXT_BINARY | 3.694 ms | 0 - 14 MB | NPU | Use Export Script |
| text_encoder | w8a16 | Snapdragon 7 Gen 5 QRD | Snapdragon® 7 Gen 5 Mobile | PRECOMPILED_QNN_ONNX | 5.772 ms | 0 - 15 MB | NPU | Use Export Script |
| text_encoder | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_CONTEXT_BINARY | 1.614 ms | 0 - 11 MB | NPU | Use Export Script |
| text_encoder | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | PRECOMPILED_QNN_ONNX | 2.594 ms | 0 - 11 MB | NPU | Use Export Script |
| text_encoder | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 3.683 ms | 0 - 0 MB | NPU | Use Export Script |
| text_encoder | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | PRECOMPILED_QNN_ONNX | 5.661 ms | 158 - 158 MB | NPU | Use Export Script |
| unet | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_CONTEXT_BINARY | 270.349 ms | 9 - 17 MB | NPU | Use Export Script |
| unet | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_CONTEXT_BINARY | 116.967 ms | 13 - 15 MB | NPU | Use Export Script |
| unet | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | PRECOMPILED_QNN_ONNX | 116.708 ms | 0 - 883 MB | NPU | Use Export Script |
| unet | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_CONTEXT_BINARY | 109.169 ms | 11 - 19 MB | NPU | Use Export Script |
| unet | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_CONTEXT_BINARY | 270.349 ms | 9 - 17 MB | NPU | Use Export Script |
| unet | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_CONTEXT_BINARY | 117.032 ms | 13 - 15 MB | NPU | Use Export Script |
| unet | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_CONTEXT_BINARY | 117.854 ms | 13 - 15 MB | NPU | Use Export Script |
| unet | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_CONTEXT_BINARY | 109.169 ms | 11 - 19 MB | NPU | Use Export Script |
| unet | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_CONTEXT_BINARY | 84.395 ms | 13 - 31 MB | NPU | Use Export Script |
| unet | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 85.293 ms | 13 - 30 MB | NPU | Use Export Script |
| unet | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_CONTEXT_BINARY | 64.04 ms | 5 - 19 MB | NPU | Use Export Script |
| unet | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | PRECOMPILED_QNN_ONNX | 67.019 ms | 6 - 23 MB | NPU | Use Export Script |
| unet | w8a16 | Snapdragon 7 Gen 5 QRD | Snapdragon® 7 Gen 5 Mobile | QNN_CONTEXT_BINARY | 178.57 ms | 13 - 27 MB | NPU | Use Export Script |
| unet | w8a16 | Snapdragon 7 Gen 5 QRD | Snapdragon® 7 Gen 5 Mobile | PRECOMPILED_QNN_ONNX | 177.634 ms | 13 - 28 MB | NPU | Use Export Script |
| unet | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_CONTEXT_BINARY | 49.393 ms | 15 - 23 MB | NPU | Use Export Script |
| unet | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | PRECOMPILED_QNN_ONNX | 50.323 ms | 13 - 28 MB | NPU | Use Export Script |
| unet | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 116.395 ms | 13 - 13 MB | NPU | Use Export Script |
| unet | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | PRECOMPILED_QNN_ONNX | 115.658 ms | 829 - 829 MB | NPU | Use Export Script |
| vae | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_CONTEXT_BINARY | 632.528 ms | 0 - 9 MB | NPU | Use Export Script |
| vae | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_CONTEXT_BINARY | 219.521 ms | 0 - 3 MB | NPU | Use Export Script |
| vae | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | PRECOMPILED_QNN_ONNX | 220.407 ms | 0 - 72 MB | NPU | Use Export Script |
| vae | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_CONTEXT_BINARY | 207.374 ms | 0 - 10 MB | NPU | Use Export Script |
| vae | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_CONTEXT_BINARY | 632.528 ms | 0 - 9 MB | NPU | Use Export Script |
| vae | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_CONTEXT_BINARY | 217.597 ms | 0 - 2 MB | NPU | Use Export Script |
| vae | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_CONTEXT_BINARY | 221.362 ms | 0 - 3 MB | NPU | Use Export Script |
| vae | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_CONTEXT_BINARY | 207.374 ms | 0 - 10 MB | NPU | Use Export Script |
| vae | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_CONTEXT_BINARY | 163.175 ms | 0 - 18 MB | NPU | Use Export Script |
| vae | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 162.456 ms | 3 - 22 MB | NPU | Use Export Script |
| vae | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_CONTEXT_BINARY | 138.761 ms | 0 - 14 MB | NPU | Use Export Script |
| vae | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | PRECOMPILED_QNN_ONNX | 147.451 ms | 3 - 19 MB | NPU | Use Export Script |
| vae | w8a16 | Snapdragon 7 Gen 5 QRD | Snapdragon® 7 Gen 5 Mobile | QNN_CONTEXT_BINARY | 449.996 ms | 0 - 15 MB | NPU | Use Export Script |
| vae | w8a16 | Snapdragon 7 Gen 5 QRD | Snapdragon® 7 Gen 5 Mobile | PRECOMPILED_QNN_ONNX | 446.334 ms | 3 - 18 MB | NPU | Use Export Script |
| vae | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_CONTEXT_BINARY | 92.194 ms | 0 - 8 MB | NPU | Use Export Script |
| vae | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | PRECOMPILED_QNN_ONNX | 98.568 ms | 3 - 14 MB | NPU | Use Export Script |
| vae | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 220.662 ms | 0 - 0 MB | NPU | Use Export Script |
| vae | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | PRECOMPILED_QNN_ONNX | 219.56 ms | 59 - 59 MB | NPU | Use Export Script |
| controlnet | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_CONTEXT_BINARY | 130.567 ms | 2 - 11 MB | NPU | Use Export Script |
| controlnet | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_CONTEXT_BINARY | 58.953 ms | 2 - 4 MB | NPU | Use Export Script |
| controlnet | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | PRECOMPILED_QNN_ONNX | 59.227 ms | 0 - 389 MB | NPU | Use Export Script |
| controlnet | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_CONTEXT_BINARY | 57.342 ms | 2 - 12 MB | NPU | Use Export Script |
| controlnet | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_CONTEXT_BINARY | 130.567 ms | 2 - 11 MB | NPU | Use Export Script |
| controlnet | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_CONTEXT_BINARY | 59.056 ms | 2 - 4 MB | NPU | Use Export Script |
| controlnet | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_CONTEXT_BINARY | 59.074 ms | 2 - 4 MB | NPU | Use Export Script |
| controlnet | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_CONTEXT_BINARY | 57.342 ms | 2 - 12 MB | NPU | Use Export Script |
| controlnet | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_CONTEXT_BINARY | 41.744 ms | 2 - 20 MB | NPU | Use Export Script |
| controlnet | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 44.785 ms | 31 - 51 MB | NPU | Use Export Script |
| controlnet | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_CONTEXT_BINARY | 32.892 ms | 1 - 18 MB | NPU | Use Export Script |
| controlnet | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | PRECOMPILED_QNN_ONNX | 33.213 ms | 31 - 44 MB | NPU | Use Export Script |
| controlnet | w8a16 | Snapdragon 7 Gen 5 QRD | Snapdragon® 7 Gen 5 Mobile | QNN_CONTEXT_BINARY | 109.949 ms | 2 - 16 MB | NPU | Use Export Script |
| controlnet | w8a16 | Snapdragon 7 Gen 5 QRD | Snapdragon® 7 Gen 5 Mobile | PRECOMPILED_QNN_ONNX | 111.554 ms | 21 - 35 MB | NPU | Use Export Script |
| controlnet | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_CONTEXT_BINARY | 26.387 ms | 2 - 13 MB | NPU | Use Export Script |
| controlnet | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | PRECOMPILED_QNN_ONNX | 29.979 ms | 31 - 39 MB | NPU | Use Export Script |
| controlnet | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 59.236 ms | 2 - 2 MB | NPU | Use Export Script |
| controlnet | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | PRECOMPILED_QNN_ONNX | 58.983 ms | 351 - 351 MB | NPU | Use Export Script |
Installation
Install the package via pip:
pip install "qai-hub-models[controlnet-canny]"
Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
Sign-in to Qualcomm® AI Hub with your
Qualcomm® ID. Once signed in navigate to Account -> Settings -> API Token.
With this API token, you can configure your client to run models on the cloud hosted devices.
qai-hub configure --api_token API_TOKEN
Navigate to docs for more information.
Demo off target
The package contains a simple end-to-end demo that downloads pre-trained weights and runs this model on a sample input.
python -m qai_hub_models.models.controlnet_canny.demo
The above demo runs a reference implementation of pre-processing, model inference, and post processing.
NOTE: If you want running in a Jupyter Notebook or Google Colab like environment, please add the following to your cell (instead of the above).
%run -m qai_hub_models.models.controlnet_canny.demo
Run model on a cloud-hosted device
In addition to the demo, you can also run the model on a cloud-hosted Qualcomm® device. This script does the following:
- Performance check on-device on a cloud-hosted device
- Downloads compiled assets that can be deployed on-device for Android.
- Accuracy check between PyTorch and on-device outputs.
python -m qai_hub_models.models.controlnet_canny.export
Deploying compiled model to Android
The models can be deployed using multiple runtimes:
TensorFlow Lite (
.tfliteexport): This tutorial provides a guide to deploy the .tflite model in an Android application.QNN (
.soexport ): This sample app provides instructions on how to use the.soshared library in an Android application.
View on Qualcomm® AI Hub
Get more details on ControlNet-Canny's performance across various devices here. Explore all available models on Qualcomm® AI Hub
License
- The license for the original implementation of ControlNet-Canny can be found here.
- The license for the compiled assets for on-device deployment can be found here
References
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.
