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 | 9.803 ms | 0 - 10 MB | NPU | Use Export Script |
| text_encoder | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_CONTEXT_BINARY | 4.836 ms | 0 - 2 MB | NPU | Use Export Script |
| text_encoder | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_CONTEXT_BINARY | 5.09 ms | 0 - 10 MB | NPU | Use Export Script |
| text_encoder | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_CONTEXT_BINARY | 9.803 ms | 0 - 10 MB | NPU | Use Export Script |
| text_encoder | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_CONTEXT_BINARY | 4.886 ms | 0 - 8 MB | NPU | Use Export Script |
| text_encoder | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_CONTEXT_BINARY | 4.863 ms | 0 - 2 MB | NPU | Use Export Script |
| text_encoder | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_CONTEXT_BINARY | 5.09 ms | 0 - 10 MB | NPU | Use Export Script |
| text_encoder | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_CONTEXT_BINARY | 4.861 ms | 0 - 2 MB | NPU | Use Export Script |
| text_encoder | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | PRECOMPILED_QNN_ONNX | 5.757 ms | 0 - 163 MB | NPU | Use Export Script |
| text_encoder | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_CONTEXT_BINARY | 3.277 ms | 0 - 20 MB | NPU | Use Export Script |
| text_encoder | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 4.073 ms | 0 - 20 MB | NPU | Use Export Script |
| text_encoder | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_CONTEXT_BINARY | 3.147 ms | 0 - 14 MB | NPU | Use Export Script |
| text_encoder | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | PRECOMPILED_QNN_ONNX | 4.466 ms | 0 - 14 MB | NPU | Use Export Script |
| text_encoder | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 5.215 ms | 0 - 0 MB | NPU | Use Export Script |
| text_encoder | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | PRECOMPILED_QNN_ONNX | 5.876 ms | 157 - 157 MB | NPU | Use Export Script |
| unet | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_CONTEXT_BINARY | 269.517 ms | 8 - 15 MB | NPU | Use Export Script |
| unet | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_CONTEXT_BINARY | 115.564 ms | 13 - 16 MB | NPU | Use Export Script |
| unet | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_CONTEXT_BINARY | 109.136 ms | 8 - 16 MB | NPU | Use Export Script |
| unet | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_CONTEXT_BINARY | 269.517 ms | 8 - 15 MB | NPU | Use Export Script |
| unet | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_CONTEXT_BINARY | 115.926 ms | 13 - 15 MB | NPU | Use Export Script |
| unet | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_CONTEXT_BINARY | 116.322 ms | 13 - 16 MB | NPU | Use Export Script |
| unet | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_CONTEXT_BINARY | 109.136 ms | 8 - 16 MB | NPU | Use Export Script |
| unet | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_CONTEXT_BINARY | 116.043 ms | 13 - 15 MB | NPU | Use Export Script |
| unet | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | PRECOMPILED_QNN_ONNX | 186.048 ms | 0 - 883 MB | NPU | Use Export Script |
| unet | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_CONTEXT_BINARY | 82.959 ms | 13 - 30 MB | NPU | Use Export Script |
| unet | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 142.064 ms | 13 - 29 MB | NPU | Use Export Script |
| unet | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_CONTEXT_BINARY | 63.014 ms | 13 - 27 MB | NPU | Use Export Script |
| unet | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | PRECOMPILED_QNN_ONNX | 128.769 ms | 13 - 28 MB | NPU | Use Export Script |
| unet | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 115.763 ms | 13 - 13 MB | NPU | Use Export Script |
| unet | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | PRECOMPILED_QNN_ONNX | 168.682 ms | 831 - 831 MB | NPU | Use Export Script |
| vae | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_CONTEXT_BINARY | 630.869 ms | 0 - 10 MB | NPU | Use Export Script |
| vae | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_CONTEXT_BINARY | 218.948 ms | 0 - 3 MB | NPU | Use Export Script |
| vae | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_CONTEXT_BINARY | 206.531 ms | 0 - 10 MB | NPU | Use Export Script |
| vae | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_CONTEXT_BINARY | 630.869 ms | 0 - 10 MB | NPU | Use Export Script |
| vae | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_CONTEXT_BINARY | 219.47 ms | 0 - 3 MB | NPU | Use Export Script |
| vae | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_CONTEXT_BINARY | 220.945 ms | 0 - 2 MB | NPU | Use Export Script |
| vae | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_CONTEXT_BINARY | 206.531 ms | 0 - 10 MB | NPU | Use Export Script |
| vae | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_CONTEXT_BINARY | 216.56 ms | 0 - 2 MB | NPU | Use Export Script |
| vae | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | PRECOMPILED_QNN_ONNX | 380.517 ms | 0 - 84 MB | NPU | Use Export Script |
| vae | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_CONTEXT_BINARY | 163.446 ms | 0 - 18 MB | NPU | Use Export Script |
| vae | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 287.551 ms | 3 - 22 MB | NPU | Use Export Script |
| vae | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_CONTEXT_BINARY | 161.222 ms | 0 - 14 MB | NPU | Use Export Script |
| vae | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | PRECOMPILED_QNN_ONNX | 279.609 ms | 3 - 17 MB | NPU | Use Export Script |
| vae | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 219.53 ms | 0 - 0 MB | NPU | Use Export Script |
| vae | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | PRECOMPILED_QNN_ONNX | 358.312 ms | 70 - 70 MB | NPU | Use Export Script |
| controlnet | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_CONTEXT_BINARY | 120.001 ms | 2 - 11 MB | NPU | Use Export Script |
| controlnet | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_CONTEXT_BINARY | 59.019 ms | 2 - 4 MB | NPU | Use Export Script |
| controlnet | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_CONTEXT_BINARY | 56.956 ms | 2 - 12 MB | NPU | Use Export Script |
| controlnet | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_CONTEXT_BINARY | 120.001 ms | 2 - 11 MB | NPU | Use Export Script |
| controlnet | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_CONTEXT_BINARY | 59.05 ms | 2 - 4 MB | NPU | Use Export Script |
| controlnet | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_CONTEXT_BINARY | 58.709 ms | 2 - 4 MB | NPU | Use Export Script |
| controlnet | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_CONTEXT_BINARY | 56.956 ms | 2 - 12 MB | NPU | Use Export Script |
| controlnet | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_CONTEXT_BINARY | 59.348 ms | 0 - 2 MB | NPU | Use Export Script |
| controlnet | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | PRECOMPILED_QNN_ONNX | 124.707 ms | 0 - 385 MB | NPU | Use Export Script |
| controlnet | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_CONTEXT_BINARY | 44.351 ms | 2 - 21 MB | NPU | Use Export Script |
| controlnet | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 88.733 ms | 40 - 60 MB | NPU | Use Export Script |
| controlnet | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_CONTEXT_BINARY | 37.254 ms | 1 - 16 MB | NPU | Use Export Script |
| controlnet | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | PRECOMPILED_QNN_ONNX | 94.146 ms | 34 - 47 MB | NPU | Use Export Script |
| controlnet | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 58.994 ms | 2 - 2 MB | NPU | Use Export Script |
| controlnet | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | PRECOMPILED_QNN_ONNX | 121.759 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.
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support