Hugging Face's logo

qualcomm
/
Stable-Diffusion-v2.1

Unconditional Image Generation
PyTorch
generative_ai
android
Model card Files
xet
 Community
1
Stable-Diffusion-v2.1 / README.md
qaihm-bot's picture
qaihm-bot
v0.30.5
b9070a7 verified
preview code
|
raw
history blame
13.3 kB
metadata 
library_name: pytorch
license: other
tags:
  - generative_ai
  - 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: Model_use_case.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 Precision Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit Target Model
text_encoder w8a16 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN 18.456 ms 0 - 9 MB NPU Use Export Script
text_encoder w8a16 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN 8.173 ms 0 - 2 MB NPU Use Export Script
text_encoder w8a16 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN 8.367 ms 0 - 9 MB NPU Use Export Script
text_encoder w8a16 SA7255P ADP Qualcomm® SA7255P QNN 18.456 ms 0 - 9 MB NPU Use Export Script
text_encoder w8a16 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN 8.393 ms 0 - 2 MB NPU Use Export Script
text_encoder w8a16 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN 8.257 ms 0 - 2 MB NPU Use Export Script
text_encoder w8a16 SA8775P ADP Qualcomm® SA8775P QNN 8.367 ms 0 - 9 MB NPU Use Export Script
text_encoder w8a16 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN 8.245 ms 0 - 2 MB NPU Use Export Script
text_encoder w8a16 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 8.133 ms 0 - 386 MB NPU Stable-Diffusion-v2.1.onnx
text_encoder w8a16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN 5.767 ms 0 - 18 MB NPU Use Export Script
text_encoder w8a16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 5.364 ms 0 - 20 MB NPU Stable-Diffusion-v2.1.onnx
text_encoder w8a16 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN 5.13 ms 0 - 14 MB NPU Use Export Script
text_encoder w8a16 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 5.361 ms 0 - 14 MB NPU Stable-Diffusion-v2.1.onnx
text_encoder w8a16 Snapdragon X Elite CRD Snapdragon® X Elite QNN 8.624 ms 0 - 0 MB NPU Use Export Script
text_encoder w8a16 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 8.244 ms 378 - 378 MB NPU Stable-Diffusion-v2.1.onnx
unet w8a16 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN 232.337 ms 2 - 9 MB NPU Use Export Script
unet w8a16 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN 93.471 ms 0 - 2 MB NPU Use Export Script
unet w8a16 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN 87.875 ms 0 - 8 MB NPU Use Export Script
unet w8a16 SA7255P ADP Qualcomm® SA7255P QNN 232.337 ms 2 - 9 MB NPU Use Export Script
unet w8a16 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN 93.998 ms 0 - 3 MB NPU Use Export Script
unet w8a16 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN 94.023 ms 0 - 2 MB NPU Use Export Script
unet w8a16 SA8775P ADP Qualcomm® SA8775P QNN 87.875 ms 0 - 8 MB NPU Use Export Script
unet w8a16 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN 93.779 ms 0 - 3 MB NPU Use Export Script
unet w8a16 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 94.913 ms 0 - 898 MB NPU Stable-Diffusion-v2.1.onnx
unet w8a16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN 65.976 ms 0 - 18 MB NPU Use Export Script
unet w8a16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 68.382 ms 0 - 16 MB NPU Stable-Diffusion-v2.1.onnx
unet w8a16 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN 52.475 ms 0 - 15 MB NPU Use Export Script
unet w8a16 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 58.492 ms 0 - 18 MB NPU Stable-Diffusion-v2.1.onnx
unet w8a16 Snapdragon X Elite CRD Snapdragon® X Elite QNN 95.267 ms 0 - 0 MB NPU Use Export Script
unet w8a16 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 96.199 ms 842 - 842 MB NPU Stable-Diffusion-v2.1.onnx
vae w8a16 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN 719.096 ms 0 - 9 MB NPU Use Export Script
vae w8a16 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN 267.027 ms 0 - 3 MB NPU Use Export Script
vae w8a16 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN 248.931 ms 0 - 10 MB NPU Use Export Script
vae w8a16 SA7255P ADP Qualcomm® SA7255P QNN 719.096 ms 0 - 9 MB NPU Use Export Script
vae w8a16 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN 268.927 ms 0 - 2 MB NPU Use Export Script
vae w8a16 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN 267.889 ms 0 - 2 MB NPU Use Export Script
vae w8a16 SA8775P ADP Qualcomm® SA8775P QNN 248.931 ms 0 - 10 MB NPU Use Export Script
vae w8a16 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN 269.837 ms 0 - 2 MB NPU Use Export Script
vae w8a16 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 272.79 ms 0 - 68 MB NPU Stable-Diffusion-v2.1.onnx
vae w8a16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN 202.859 ms 0 - 21 MB NPU Use Export Script
vae w8a16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 208.42 ms 4 - 22 MB NPU Stable-Diffusion-v2.1.onnx
vae w8a16 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN 175.718 ms 0 - 15 MB NPU Use Export Script
vae w8a16 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 194.087 ms 3 - 17 MB NPU Stable-Diffusion-v2.1.onnx
vae w8a16 Snapdragon X Elite CRD Snapdragon® X Elite QNN 265.086 ms 0 - 0 MB NPU Use Export Script
vae w8a16 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 264.341 ms 63 - 63 MB NPU Stable-Diffusion-v2.1.onnx

Deploy to Snapdragon X Elite NPU

Please follow the Stable Diffusion Windows App tutorial to quantize model with custom weights.

Quantize and Deploy Your Own Fine-Tuned Stable Diffusion

Please follow the Quantize Stable Diffusion tutorial to quantize model with custom weights.

Installation

Install the package via pip:

pip install "qai-hub-models[stable-diffusion-v2-1]"

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.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.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.export

Profiling Results
------------------------------------------------------------
text_encoder
Device                          : cs_8275 (ANDROID 14)                 
Runtime                         : QNN                                  
Estimated inference time (ms)   : 18.5                                 
Estimated peak memory usage (MB): [0, 9]                               
Total # Ops                     : 787                                  
Compute Unit(s)                 : npu (787 ops) gpu (0 ops) cpu (0 ops)

------------------------------------------------------------
unet
Device                          : cs_8275 (ANDROID 14)                  
Runtime                         : QNN                                   
Estimated inference time (ms)   : 232.3                                 
Estimated peak memory usage (MB): [2, 9]                                
Total # Ops                     : 5783                                  
Compute Unit(s)                 : npu (5783 ops) gpu (0 ops) cpu (0 ops)

------------------------------------------------------------
vae
Device                          : cs_8275 (ANDROID 14)                 
Runtime                         : QNN                                  
Estimated inference time (ms)   : 719.1                                
Estimated peak memory usage (MB): [0, 9]                               
Total # Ops                     : 173                                  
Compute Unit(s)                 : npu (173 ops) gpu (0 ops) cpu (0 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