Hugging Face's logo

qualcomm
/
ControlNet

Unconditional Image Generation
PyTorch
generative_ai
quantized
android
Model card Files Community
1
ControlNet / README.md
shreyajn's picture
shreyajn
Upload README.md with huggingface_hub
c3a1ccc verified
preview code
|
raw
history blame
12.9 kB
metadata
library_name: pytorch
license: apache-2.0
pipeline_tag: unconditional-image-generation
tags:
  - generative_ai
  - quantized
  - android

ControlNet: 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 Posenet-Mobilenet found here.

This repository provides scripts to run ControlNet on Qualcomm® devices. More details on model performance across various devices, can be found here.

Model Details

  • Model Type: 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 Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Precision Primary Compute Unit Target Model
TextEncoder_Quantized Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 11.394 ms 0 - 74 MB UINT16 NPU ControlNet.bin
TextEncoder_Quantized Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 8.08 ms 0 - 137 MB UINT16 NPU ControlNet.bin
TextEncoder_Quantized QCS8550 (Proxy) QCS8550 Proxy QNN 10.982 ms 0 - 1 MB UINT16 NPU Use Export Script
UNet_Quantized Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 262.52 ms 11 - 17 MB UINT16 NPU ControlNet.bin
UNet_Quantized Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 192.789 ms 3 - 1247 MB UINT16 NPU ControlNet.bin
UNet_Quantized QCS8550 (Proxy) QCS8550 Proxy QNN 260.158 ms 14 - 15 MB UINT16 NPU Use Export Script
VAEDecoder_Quantized Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 390.243 ms 0 - 36 MB UINT16 NPU ControlNet.bin
VAEDecoder_Quantized Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 294.404 ms 0 - 88 MB UINT16 NPU ControlNet.bin
VAEDecoder_Quantized QCS8550 (Proxy) QCS8550 Proxy QNN 379.548 ms 0 - 1 MB UINT16 NPU Use Export Script
ControlNet_Quantized Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 100.33 ms 2 - 68 MB UINT16 NPU ControlNet.bin
ControlNet_Quantized Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 76.94 ms 0 - 533 MB UINT16 NPU ControlNet.bin
ControlNet_Quantized QCS8550 (Proxy) QCS8550 Proxy QNN 103.52 ms 2 - 3 MB UINT16 NPU Use Export Script

Installation

This model can be installed as a Python package via pip.

pip install "qai-hub-models[controlnet_quantized]"

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 on-device

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_quantized.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_quantized.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_quantized.export

Profiling Results
------------------------------------------------------------
TextEncoder_Quantized
Device                          : Samsung Galaxy S23 (13)
Runtime                         : QNN                    
Estimated inference time (ms)   : 11.4                   
Estimated peak memory usage (MB): [0, 74]                
Total # Ops                     : 570                    
Compute Unit(s)                 : NPU (570 ops)          

------------------------------------------------------------
UNet_Quantized
Device                          : Samsung Galaxy S23 (13)
Runtime                         : QNN                    
Estimated inference time (ms)   : 262.5                  
Estimated peak memory usage (MB): [11, 17]               
Total # Ops                     : 5434                   
Compute Unit(s)                 : NPU (5434 ops)         

------------------------------------------------------------
VAEDecoder_Quantized
Device                          : Samsung Galaxy S23 (13)
Runtime                         : QNN                    
Estimated inference time (ms)   : 390.2                  
Estimated peak memory usage (MB): [0, 36]                
Total # Ops                     : 409                    
Compute Unit(s)                 : NPU (409 ops)          

------------------------------------------------------------
ControlNet_Quantized
Device                          : Samsung Galaxy S23 (13)
Runtime                         : QNN                    
Estimated inference time (ms)   : 100.3                  
Estimated peak memory usage (MB): [2, 68]                
Total # Ops                     : 2406                   
Compute Unit(s)                 : NPU (2406 ops)

How does this work?

This export script leverages Qualcomm® AI Hub to optimize, validate, and deploy this model on-device. Lets go through each step below in detail:

Step 1: Upload compiled model

Upload compiled models from qai_hub_models.models.controlnet_quantized on hub.

import torch

import qai_hub as hub
from qai_hub_models.models.controlnet_quantized import Model

# Load the model
model = Model.from_precompiled()

model_textencoder_quantized = hub.upload_model(model.text_encoder.get_target_model_path())
model_unet_quantized = hub.upload_model(model.unet.get_target_model_path())
model_vaedecoder_quantized = hub.upload_model(model.vae_decoder.get_target_model_path())
model_controlnet_quantized = hub.upload_model(model.controlnet.get_target_model_path())

Step 2: Performance profiling on cloud-hosted device

After uploading compiled models from step 1. Models can be profiled model on-device using the target_model. Note that this scripts runs the model on a device automatically provisioned in the cloud. Once the job is submitted, you can navigate to a provided job URL to view a variety of on-device performance metrics.


# Device
device = hub.Device("Samsung Galaxy S23")
profile_job_textencoder_quantized = hub.submit_profile_job(
    model=model_textencoder_quantized,
    device=device,
)
profile_job_unet_quantized = hub.submit_profile_job(
    model=model_unet_quantized,
    device=device,
)
profile_job_vaedecoder_quantized = hub.submit_profile_job(
    model=model_vaedecoder_quantized,
    device=device,
)
profile_job_controlnet_quantized = hub.submit_profile_job(
    model=model_controlnet_quantized,
    device=device,
)

Step 3: Verify on-device accuracy

To verify the accuracy of the model on-device, you can run on-device inference on sample input data on the same cloud hosted device.


input_data_textencoder_quantized = model.text_encoder.sample_inputs()
inference_job_textencoder_quantized = hub.submit_inference_job(
    model=model_textencoder_quantized,
    device=device,
    inputs=input_data_textencoder_quantized,
)
on_device_output_textencoder_quantized = inference_job_textencoder_quantized.download_output_data()

input_data_unet_quantized = model.unet.sample_inputs()
inference_job_unet_quantized = hub.submit_inference_job(
    model=model_unet_quantized,
    device=device,
    inputs=input_data_unet_quantized,
)
on_device_output_unet_quantized = inference_job_unet_quantized.download_output_data()

input_data_vaedecoder_quantized = model.vae_decoder.sample_inputs()
inference_job_vaedecoder_quantized = hub.submit_inference_job(
    model=model_vaedecoder_quantized,
    device=device,
    inputs=input_data_vaedecoder_quantized,
)
on_device_output_vaedecoder_quantized = inference_job_vaedecoder_quantized.download_output_data()

input_data_controlnet_quantized = model.controlnet.sample_inputs()
inference_job_controlnet_quantized = hub.submit_inference_job(
    model=model_controlnet_quantized,
    device=device,
    inputs=input_data_controlnet_quantized,
)
on_device_output_controlnet_quantized = inference_job_controlnet_quantized.download_output_data()

With the output of the model, you can compute like PSNR, relative errors or spot check the output with expected output.

Note: This on-device profiling and inference requires access to Qualcomm® AI Hub. Sign up for access.

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 / .bin export ): This sample app provides instructions on how to use the .so shared library or .bin context binary in an Android application.

View on Qualcomm® AI Hub

Get more details on ControlNet's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

  • The license for the original implementation of ControlNet can be found here.
  • The license for the compiled assets for on-device deployment can be found here

References

Community

Usage and Limitations

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