Hugging Face's logo

qualcomm
/
Stable-Diffusion-v2.1

Unconditional Image Generation
PyTorch
generative_ai
quantized
android
Model card Files Community
1
Stable-Diffusion-v2.1 / README.md
shreyajn's picture
shreyajn
Upload README.md with huggingface_hub
01d1834 verified
preview code
|
raw
history blame contribute delete
10.7 kB
metadata
library_name: pytorch
license: creativeml-openrail-m
tags:
  - generative_ai
  - quantized
  - android
pipeline_tag: unconditional-image-generation

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
    • Text Encoder Number of parameters: 340M
    • UNet Number of parameters: 865M
    • VAE Decoder Number of parameters: 83M
    • Model size: 1GB
Model Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Precision Primary Compute Unit Target Model
TextEncoderQuantizable Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 6.622 ms 0 - 2 MB W8A16 NPU Stable-Diffusion-v2.1.so
TextEncoderQuantizable Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 4.851 ms 0 - 19 MB W8A16 NPU Stable-Diffusion-v2.1.so
TextEncoderQuantizable Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 4.198 ms 0 - 15 MB W8A16 NPU Use Export Script
TextEncoderQuantizable Snapdragon X Elite CRD Snapdragon® X Elite QNN 6.896 ms 0 - 0 MB W8A16 NPU Use Export Script
TextEncoderQuantizable SA7255P ADP SA7255P QNN 88.097 ms 0 - 8 MB W8A16 NPU Use Export Script
TextEncoderQuantizable SA8255 (Proxy) SA8255P Proxy QNN 6.68 ms 0 - 2 MB W8A16 NPU Use Export Script
TextEncoderQuantizable SA8650 (Proxy) SA8650P Proxy QNN 6.651 ms 0 - 5 MB W8A16 NPU Use Export Script
TextEncoderQuantizable SA8775P ADP SA8775P QNN 7.894 ms 0 - 10 MB W8A16 NPU Use Export Script
TextEncoderQuantizable QCS8275 (Proxy) QCS8275 Proxy QNN 88.097 ms 0 - 8 MB W8A16 NPU Use Export Script
TextEncoderQuantizable QCS8550 (Proxy) QCS8550 Proxy QNN 6.643 ms 0 - 3 MB W8A16 NPU Use Export Script
TextEncoderQuantizable QCS9075 (Proxy) QCS9075 Proxy QNN 7.894 ms 0 - 10 MB W8A16 NPU Use Export Script
UnetQuantizable Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 97.767 ms 0 - 3 MB W8A16 NPU Stable-Diffusion-v2.1.so
UnetQuantizable Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 69.335 ms 0 - 19 MB W8A16 NPU Stable-Diffusion-v2.1.so
UnetQuantizable Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 61.27 ms 0 - 14 MB W8A16 NPU Use Export Script
UnetQuantizable Snapdragon X Elite CRD Snapdragon® X Elite QNN 99.423 ms 0 - 0 MB W8A16 NPU Use Export Script
UnetQuantizable SA7255P ADP SA7255P QNN 1468.169 ms 0 - 8 MB W8A16 NPU Use Export Script
UnetQuantizable SA8255 (Proxy) SA8255P Proxy QNN 96.812 ms 0 - 2 MB W8A16 NPU Use Export Script
UnetQuantizable SA8650 (Proxy) SA8650P Proxy QNN 97.233 ms 0 - 3 MB W8A16 NPU Use Export Script
UnetQuantizable SA8775P ADP SA8775P QNN 110.658 ms 0 - 9 MB W8A16 NPU Use Export Script
UnetQuantizable QCS8275 (Proxy) QCS8275 Proxy QNN 1468.169 ms 0 - 8 MB W8A16 NPU Use Export Script
UnetQuantizable QCS8550 (Proxy) QCS8550 Proxy QNN 98.147 ms 0 - 3 MB W8A16 NPU Use Export Script
UnetQuantizable QCS9075 (Proxy) QCS9075 Proxy QNN 110.658 ms 0 - 9 MB W8A16 NPU Use Export Script
VaeDecoderQuantizable Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 274.636 ms 0 - 4 MB W8A16 NPU Stable-Diffusion-v2.1.so
VaeDecoderQuantizable Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 206.701 ms 0 - 18 MB W8A16 NPU Stable-Diffusion-v2.1.so
VaeDecoderQuantizable Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 189.387 ms 0 - 355 MB W8A16 NPU Use Export Script
VaeDecoderQuantizable Snapdragon X Elite CRD Snapdragon® X Elite QNN 266.827 ms 0 - 0 MB W8A16 NPU Use Export Script
VaeDecoderQuantizable SA7255P ADP SA7255P QNN 4462.005 ms 1 - 10 MB W8A16 NPU Use Export Script
VaeDecoderQuantizable SA8255 (Proxy) SA8255P Proxy QNN 274.28 ms 0 - 3 MB W8A16 NPU Use Export Script
VaeDecoderQuantizable SA8650 (Proxy) SA8650P Proxy QNN 272.687 ms 0 - 2 MB W8A16 NPU Use Export Script
VaeDecoderQuantizable SA8775P ADP SA8775P QNN 301.027 ms 0 - 10 MB W8A16 NPU Use Export Script
VaeDecoderQuantizable QCS8275 (Proxy) QCS8275 Proxy QNN 4462.005 ms 1 - 10 MB W8A16 NPU Use Export Script
VaeDecoderQuantizable QCS8550 (Proxy) QCS8550 Proxy QNN 259.311 ms 0 - 3 MB W8A16 NPU Use Export Script
VaeDecoderQuantizable QCS9075 (Proxy) QCS9075 Proxy QNN 301.027 ms 0 - 10 MB W8A16 NPU Use Export Script

Installation

Install the package via pip:

pip install "qai-hub-models[stable-diffusion-v2-1-quantized]" -f https://qaihub-public-python-wheels.s3.us-west-2.amazonaws.com/index.html

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.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

Profiling Results
------------------------------------------------------------
TextEncoderQuantizable
Device                          : Samsung Galaxy S23 (13)
Runtime                         : QNN                    
Estimated inference time (ms)   : 6.6                    
Estimated peak memory usage (MB): [0, 2]                 
Total # Ops                     : 787                    
Compute Unit(s)                 : NPU (787 ops)          

------------------------------------------------------------
UnetQuantizable
Device                          : Samsung Galaxy S23 (13)
Runtime                         : QNN                    
Estimated inference time (ms)   : 97.8                   
Estimated peak memory usage (MB): [0, 3]                 
Total # Ops                     : 5891                   
Compute Unit(s)                 : NPU (5891 ops)         

------------------------------------------------------------
VaeDecoderQuantizable
Device                          : Samsung Galaxy S23 (13)
Runtime                         : QNN                    
Estimated inference time (ms)   : 274.6                  
Estimated peak memory usage (MB): [0, 4]                 
Total # Ops                     : 189                    
Compute Unit(s)                 : NPU (189 ops)

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 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