ControlNet-Canny: Optimized for Qualcomm Devices

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 is based on the implementation of ControlNet-Canny 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
PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X2 Elite QAIRT 2.45, ONNX Runtime 1.25.0 Download
PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X Elite QAIRT 2.45, ONNX Runtime 1.25.0 Download
PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Gen 3 Mobile QAIRT 2.45, ONNX Runtime 1.25.0 Download
PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS8550 (Proxy) QAIRT 2.45, ONNX Runtime 1.25.0 Download
PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite Mobile QAIRT 2.45, ONNX Runtime 1.25.0 Download
PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 7 Gen 4 Mobile QAIRT 2.45, ONNX Runtime 1.25.0 Download
PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile QAIRT 2.45, ONNX Runtime 1.25.0 Download
PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCM6690 QAIRT 2.45, ONNX Runtime 1.25.0 Download
PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS9075 QAIRT 2.45, ONNX Runtime 1.25.0 Download
QNN_CONTEXT_BINARY w8a16 Snapdragon® X2 Elite QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Snapdragon® X Elite QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Gen 3 Mobile QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS8550 (Proxy) QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Qualcomm® SA8775P QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Mobile QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Snapdragon® 7 Gen 4 Mobile QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Gen 5 Mobile QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Qualcomm® SA7255P QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Qualcomm® QCM6690 QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS9075 QAIRT 2.45 Download

For more device-specific assets and performance metrics, visit ControlNet-Canny 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 ControlNet-Canny on GitHub for usage instructions.

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

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
controlnet PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X2 Elite 29.242 ms 34 - 34 MB NPU
controlnet PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X Elite 70.884 ms 352 - 352 MB NPU
controlnet PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 59.885 ms 31 - 44 MB NPU
controlnet PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS8550 (Proxy) 74.079 ms 0 - 384 MB NPU
controlnet PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 119.158 ms 30 - 36 MB NPU
controlnet PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 28.355 ms 31 - 44 MB NPU
controlnet PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCM6690 1078.559 ms 2 - 13 MB NPU
controlnet PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS9075 70.675 ms 33 - 37 MB NPU
controlnet PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite Mobile 43.777 ms 33 - 44 MB NPU
controlnet PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS7790 119.158 ms 30 - 36 MB NPU
controlnet PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS8750 43.777 ms 33 - 44 MB NPU
controlnet PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS7181 70.884 ms 352 - 352 MB NPU
controlnet QNN_CONTEXT_BINARY w8a16 Snapdragon® X2 Elite 29.419 ms 2 - 2 MB NPU
controlnet QNN_CONTEXT_BINARY w8a16 Snapdragon® X Elite 70.922 ms 2 - 2 MB NPU
controlnet QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Gen 3 Mobile 56.153 ms 2 - 10 MB NPU
controlnet QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS8275 138.293 ms 2 - 10 MB NPU
controlnet QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS8550 (Proxy) 75.631 ms 2 - 16 MB NPU
controlnet QNN_CONTEXT_BINARY w8a16 Snapdragon® 7 Gen 4 Mobile 119.233 ms 0 - 6 MB NPU
controlnet QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Gen 5 Mobile 28.308 ms 2 - 10 MB NPU
controlnet QNN_CONTEXT_BINARY w8a16 Qualcomm® SA7255P 138.293 ms 2 - 10 MB NPU
controlnet QNN_CONTEXT_BINARY w8a16 Qualcomm® QCM6690 1089.372 ms 15 - 21 MB NPU
controlnet QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS9075 70.612 ms 0 - 16 MB NPU
controlnet QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Mobile 43.794 ms 2 - 15 MB NPU
controlnet QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS7790 119.233 ms 0 - 6 MB NPU
controlnet QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS8750 43.794 ms 2 - 15 MB NPU
controlnet QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS7181 70.922 ms 2 - 2 MB NPU
text_encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X2 Elite 1.525 ms 1 - 1 MB NPU
text_encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X Elite 3.441 ms 156 - 156 MB NPU
text_encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 2.309 ms 0 - 7 MB NPU
text_encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS8550 (Proxy) 3.244 ms 0 - 161 MB NPU
text_encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 3.682 ms 0 - 7 MB NPU
text_encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 1.548 ms 0 - 7 MB NPU
text_encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCM6690 22.049 ms 0 - 11 MB NPU
text_encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS9075 3.335 ms 0 - 3 MB NPU
text_encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite Mobile 1.755 ms 0 - 7 MB NPU
text_encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS7790 3.682 ms 0 - 7 MB NPU
text_encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS8750 1.755 ms 0 - 7 MB NPU
text_encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS7181 3.441 ms 156 - 156 MB NPU
text_encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® X2 Elite 1.719 ms 0 - 0 MB NPU
text_encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® X Elite 3.61 ms 0 - 0 MB NPU
text_encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Gen 3 Mobile 2.327 ms 0 - 7 MB NPU
text_encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS8275 7.495 ms 0 - 8 MB NPU
text_encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS8550 (Proxy) 3.24 ms 0 - 1 MB NPU
text_encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 7 Gen 4 Mobile 3.685 ms 0 - 7 MB NPU
text_encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Gen 5 Mobile 1.54 ms 0 - 9 MB NPU
text_encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA7255P 7.495 ms 0 - 8 MB NPU
text_encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® QCM6690 21.98 ms 0 - 6 MB NPU
text_encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS9075 3.336 ms 0 - 2 MB NPU
text_encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Mobile 1.749 ms 0 - 9 MB NPU
text_encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS7790 3.685 ms 0 - 7 MB NPU
text_encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS8750 1.749 ms 0 - 9 MB NPU
text_encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS7181 3.61 ms 0 - 0 MB NPU
unet PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X2 Elite 46.456 ms 13 - 13 MB NPU
unet PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X Elite 114.285 ms 829 - 829 MB NPU
unet PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 81.905 ms 13 - 25 MB NPU
unet PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS8550 (Proxy) 113.551 ms 13 - 16 MB NPU
unet PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 180.586 ms 13 - 24 MB NPU
unet PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 48.29 ms 6 - 19 MB NPU
unet PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCM6690 2081.275 ms 13 - 24 MB NPU
unet PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS9075 106.671 ms 13 - 29 MB NPU
unet PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite Mobile 63.286 ms 6 - 18 MB NPU
unet PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS7790 180.586 ms 13 - 24 MB NPU
unet PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS8750 63.286 ms 6 - 18 MB NPU
unet PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS7181 114.285 ms 829 - 829 MB NPU
unet QNN_CONTEXT_BINARY w8a16 Snapdragon® X2 Elite 46.979 ms 13 - 13 MB NPU
unet QNN_CONTEXT_BINARY w8a16 Snapdragon® X Elite 114.186 ms 13 - 13 MB NPU
unet QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Gen 3 Mobile 80.352 ms 13 - 19 MB NPU
unet QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS8275 266.556 ms 8 - 15 MB NPU
unet QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS8550 (Proxy) 112.881 ms 13 - 15 MB NPU
unet QNN_CONTEXT_BINARY w8a16 Snapdragon® 7 Gen 4 Mobile 178.859 ms 11 - 17 MB NPU
unet QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Gen 5 Mobile 46.194 ms 6 - 14 MB NPU
unet QNN_CONTEXT_BINARY w8a16 Qualcomm® SA7255P 266.556 ms 8 - 15 MB NPU
unet QNN_CONTEXT_BINARY w8a16 Qualcomm® QCM6690 2113.897 ms 14 - 24 MB NPU
unet QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS9075 106.622 ms 11 - 25 MB NPU
unet QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Mobile 61.406 ms 6 - 18 MB NPU
unet QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS7790 178.859 ms 11 - 17 MB NPU
unet QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS8750 61.406 ms 6 - 18 MB NPU
unet QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS7181 114.186 ms 13 - 13 MB NPU
vae PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X2 Elite 127.333 ms 4 - 4 MB NPU
vae PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X Elite 258.657 ms 61 - 61 MB NPU
vae PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 197.419 ms 4 - 10 MB NPU
vae PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS8550 (Proxy) 262.72 ms 1 - 66 MB NPU
vae PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 504.535 ms 2 - 9 MB NPU
vae PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 119.259 ms 3 - 11 MB NPU
vae PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCM6690 6285.291 ms 2 - 9 MB NPU
vae PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS9075 241.07 ms 3 - 6 MB NPU
vae PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite Mobile 171.689 ms 3 - 15 MB NPU
vae PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS7790 504.535 ms 2 - 9 MB NPU
vae PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS8750 171.689 ms 3 - 15 MB NPU
vae PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS7181 258.657 ms 61 - 61 MB NPU
vae QNN_CONTEXT_BINARY w8a16 Snapdragon® X2 Elite 127.068 ms 0 - 0 MB NPU
vae QNN_CONTEXT_BINARY w8a16 Snapdragon® X Elite 258.907 ms 0 - 0 MB NPU
vae QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Gen 3 Mobile 196.347 ms 3 - 9 MB NPU
vae QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS8275 712.131 ms 0 - 9 MB NPU
vae QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS8550 (Proxy) 262.881 ms 0 - 2 MB NPU
vae QNN_CONTEXT_BINARY w8a16 Snapdragon® 7 Gen 4 Mobile 503.269 ms 1 - 7 MB NPU
vae QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Gen 5 Mobile 118.996 ms 0 - 13 MB NPU
vae QNN_CONTEXT_BINARY w8a16 Qualcomm® SA7255P 712.131 ms 0 - 9 MB NPU
vae QNN_CONTEXT_BINARY w8a16 Qualcomm® QCM6690 6163.649 ms 10 - 17 MB NPU
vae QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS9075 240.825 ms 0 - 3 MB NPU
vae QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Mobile 171.669 ms 0 - 13 MB NPU
vae QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS7790 503.269 ms 1 - 7 MB NPU
vae QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS8750 171.669 ms 0 - 13 MB NPU
vae QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS7181 258.907 ms 0 - 0 MB NPU

License

  • The license for the original implementation of ControlNet-Canny can be found here.

References

Community

Usage and Limitations

This model may not be used for or in connection with any of the following applications:

  • Accessing essential private and public services and benefits;
  • Administration of justice and democratic processes;
  • Assessing or recognizing the emotional state of a person;
  • Biometric and biometrics-based systems, including categorization of persons based on sensitive characteristics;
  • Education and vocational training;
  • Employment and workers management;
  • Exploitation of the vulnerabilities of persons resulting in harmful behavior;
  • General purpose social scoring;
  • Law enforcement;
  • Management and operation of critical infrastructure;
  • Migration, asylum and border control management;
  • Predictive policing;
  • Real-time remote biometric identification in public spaces;
  • Recommender systems of social media platforms;
  • Scraping of facial images (from the internet or otherwise); and/or
  • Subliminal manipulation
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for qualcomm/ControlNet-Canny