Stable-Diffusion-v2.1 Example

This document explains how to use the QAI AppBuilder Python API to perform inference with the Stable-Diffusion-v2.1 text-to-image model using the Qualcomm® Hexagon™ Processor (NPU).

Supported devices

Device	SoC
Fogwise® AIRbox Q900	QCS9075

Install QAI AppBuilder

tip

1. Install QAI AppBuilder by following the QAI AppBuilder installation guide.

2. Configure ADSP environment variables as described in Create ADSP environment variables.

Run the sample

Install dependencies

Install sample dependencies in the activated virtual environment:

Device

pip3 install requests tqdm qai-hub py3-wget Pillow torch torchvision opencv-python-headless transformers diffusers

Run the script

• Enter the upstream samples directory

  Device

  cd qai-appbuilder/samples

• Prepare input data (use the sample input if provided, or pass script arguments)

Output image

• Run inference

  Device

  python3 GenerativeAI/Image_Generation/stable_diffusion_v2_1/stable_diffusion_v2_1.py --chipset 9075 --prompt "a cat"

On success an image is written under the sample directory, for example:

GenerativeAI/Image_Generation/stable_diffusion_v2_1/images/<timestamp>_512.jpg

On AIRbox Q900 the first run downloads Text Encoder / UNet / VAE (on the order of ~1.2 GB total). Slow networks may take tens of minutes to hours.

tip

Requires transformers and diffusers. Prefer running the script directly (avoids run_inference.py --args quoting issues with spaces in prompts):

python3 GenerativeAI/Image_Generation/stable_diffusion_v2_1/stable_diffusion_v2_1.py --chipset 9075 --prompt "a cat"