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	QCS8550 (Proxy)	Qualcomm® QCS8550 (Proxy)	PRECOMPILED_QNN_ONNX	5.515 ms	0 - 163 MB	NPU	Use Export Script
text_encoder	w8a16	Samsung Galaxy S24	Snapdragon® 8 Gen 3 Mobile	PRECOMPILED_QNN_ONNX	3.957 ms	0 - 19 MB	NPU	Use Export Script
text_encoder	w8a16	Samsung Galaxy S25	Snapdragon® 8 Elite For Galaxy Mobile	PRECOMPILED_QNN_ONNX	3.109 ms	0 - 15 MB	NPU	Use Export Script
text_encoder	w8a16	Snapdragon 8 Elite Gen 5 QRD	Snapdragon® 8 Elite Gen5 Mobile	PRECOMPILED_QNN_ONNX	2.66 ms	0 - 10 MB	NPU	Use Export Script
text_encoder	w8a16	Snapdragon X Elite CRD	Snapdragon® X Elite	PRECOMPILED_QNN_ONNX	5.654 ms	157 - 157 MB	NPU	Use Export Script
unet	w8a16	QCS8550 (Proxy)	Qualcomm® QCS8550 (Proxy)	PRECOMPILED_QNN_ONNX	117.602 ms	13 - 15 MB	NPU	Use Export Script
unet	w8a16	Samsung Galaxy S24	Snapdragon® 8 Gen 3 Mobile	PRECOMPILED_QNN_ONNX	84.132 ms	13 - 29 MB	NPU	Use Export Script
unet	w8a16	Samsung Galaxy S25	Snapdragon® 8 Elite For Galaxy Mobile	PRECOMPILED_QNN_ONNX	66.65 ms	6 - 21 MB	NPU	Use Export Script
unet	w8a16	Snapdragon 8 Elite Gen 5 QRD	Snapdragon® 8 Elite Gen5 Mobile	PRECOMPILED_QNN_ONNX	48.08 ms	13 - 28 MB	NPU	Use Export Script
unet	w8a16	Snapdragon X Elite CRD	Snapdragon® X Elite	PRECOMPILED_QNN_ONNX	115.771 ms	829 - 829 MB	NPU	Use Export Script
vae	w8a16	QCS8550 (Proxy)	Qualcomm® QCS8550 (Proxy)	PRECOMPILED_QNN_ONNX	220.181 ms	0 - 67 MB	NPU	Use Export Script
vae	w8a16	Samsung Galaxy S24	Snapdragon® 8 Gen 3 Mobile	PRECOMPILED_QNN_ONNX	163.042 ms	3 - 22 MB	NPU	Use Export Script
vae	w8a16	Samsung Galaxy S25	Snapdragon® 8 Elite For Galaxy Mobile	PRECOMPILED_QNN_ONNX	147.198 ms	3 - 17 MB	NPU	Use Export Script
vae	w8a16	Snapdragon 8 Elite Gen 5 QRD	Snapdragon® 8 Elite Gen5 Mobile	PRECOMPILED_QNN_ONNX	92.382 ms	3 - 13 MB	NPU	Use Export Script
vae	w8a16	Snapdragon X Elite CRD	Snapdragon® X Elite	PRECOMPILED_QNN_ONNX	219.592 ms	59 - 59 MB	NPU	Use Export Script
controlnet	w8a16	QCS8550 (Proxy)	Qualcomm® QCS8550 (Proxy)	PRECOMPILED_QNN_ONNX	59.707 ms	0 - 384 MB	NPU	Use Export Script
controlnet	w8a16	Samsung Galaxy S24	Snapdragon® 8 Gen 3 Mobile	PRECOMPILED_QNN_ONNX	45.254 ms	32 - 46 MB	NPU	Use Export Script
controlnet	w8a16	Samsung Galaxy S25	Snapdragon® 8 Elite For Galaxy Mobile	PRECOMPILED_QNN_ONNX	33.208 ms	31 - 47 MB	NPU	Use Export Script
controlnet	w8a16	Snapdragon 8 Elite Gen 5 QRD	Snapdragon® 8 Elite Gen5 Mobile	PRECOMPILED_QNN_ONNX	29.973 ms	15 - 25 MB	NPU	Use Export Script
controlnet	w8a16	Snapdragon X Elite CRD	Snapdragon® X Elite	PRECOMPILED_QNN_ONNX	59.173 ms	352 - 352 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 (.tflite export): This tutorial provides a guide to deploy the .tflite model in an Android application.

• QNN (.so export ): This sample app provides instructions on how to use the .so shared 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

• Adding Conditional Control to Text-to-Image Diffusion Models
• 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.