metadata

library_name: pytorch
license: creativeml-openrail-m
pipeline_tag: unconditional-image-generation
tags:
  - generative_ai
  - quantized
  - android

Stable-Diffusion-v2.1: Optimized for Mobile Deployment

State-of-the-art generative AI model used to generate detailed images conditioned on text descriptions

Generates high resolution images from text prompts using a latent diffusion model. This model uses CLIP ViT-L/14 as text encoder, U-Net based latent denoising, and VAE based decoder to generate the final image.

This model is an implementation of Stable-Diffusion-v2.1 found here. This repository provides scripts to run Stable-Diffusion-v2.1 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 to generate image
- QNN-SDK: 2.20
- Text Encoder Number of parameters: 340M
- UNet Number of parameters: 865M
- VAE Decoder Number of parameters: 83M
- Model size: 1GB

Device	Chipset	Target Runtime	Inference Time (ms)	Peak Memory Range (MB)	Precision	Primary Compute Unit	Target Model
Samsung Galaxy S23 Ultra (Android 13)	Snapdragon® 8 Gen 2	QNN Binary	21.604 ms	0 - 93 MB	INT8	NPU	TextEncoder_Quantized.bin
Samsung Galaxy S23 Ultra (Android 13)	Snapdragon® 8 Gen 2	QNN Binary	379.128 ms	0 - 18 MB	INT8	NPU	VAEDecoder_Quantized.bin
Samsung Galaxy S23 Ultra (Android 13)	Snapdragon® 8 Gen 2	QNN Binary	220.629 ms	0 - 3 MB	INT8	NPU	UNet_Quantized.bin

Installation

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

pip install "qai-hub-models[stable_diffusion_v2_1_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.stable_diffusion_v2_1_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.stable_diffusion_v2_1_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.stable_diffusion_v2_1_quantized.export

Profile Job summary of TextEncoder_Quantized
--------------------------------------------------
Device: Snapdragon X Elite CRD (11)
Estimated Inference Time: 21.33 ms
Estimated Peak Memory Range: 0.01-0.01 MB
Compute Units: NPU (1040) | Total (1040)

Profile Job summary of VAEDecoder_Quantized
--------------------------------------------------
Device: Snapdragon X Elite CRD (11)
Estimated Inference Time: 347.52 ms
Estimated Peak Memory Range: 0.03-0.03 MB
Compute Units: NPU (172) | Total (172)

Profile Job summary of UNet_Quantized
--------------------------------------------------
Device: Snapdragon X Elite CRD (11)
Estimated Inference Time: 205.75 ms
Estimated Peak Memory Range: 0.18-0.18 MB
Compute Units: NPU (6753) | Total (6753)

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.stable_diffusion_v2_1_quantized on hub.

import torch

import qai_hub as hub
from qai_hub_models.models.stable_diffusion_v2_1_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())

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,
)

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()

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 Stable-Diffusion-v2.1's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

The license for the original implementation of Stable-Diffusion-v2.1 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.

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