bentoml / BentoSD2Upscaler

how to build an image generation application with upscaling ability using BentoML

Serving Stable Diffusion 2 + Upscaler with BentoML

This is a BentoML example project, demonstrating how to build an image generation inference API server using the SD2 model and the upscaler model. See here for a full list of BentoML example projects.

Prerequisites

• You have installed Python 3.8+ and pip. See the Python downloads page to learn more.
• You have a basic understanding of key concepts in BentoML, such as Services. We recommend you read Quickstart first.
• If you want to test this Service locally, we highly recommend using a Nvidia GPU with more than 32G VRAM.
• (Optional) We recommend you create a virtual environment for dependency isolation for this project. See the Conda documentation or the Python documentation for details.

Install dependencies

git clone https://github.com/bentoml/BentoSD2Upscaler.git
cd BentoSD2Upscaler
pip install -r requirements.txt

Run the BentoML Service

We have defined a BentoML Service in service.py. Run bentoml serve in your project directory to start the Service.

$ bentoml serve .

2024-01-19T06:16:28+0800 [INFO] [cli] Starting production HTTP BentoServer from "service:SD2Service" listening on http://localhost:3000 (Press CTRL+C to quit)
Loading pipeline components...: 100%

The server is now active at http://localhost:3000. You can interact with it using the Swagger UI or in other different ways.

CURL

curl -X 'POST' \
  'http://localhost:3000/txt2img' \
  -H 'accept: image/*' \
  -H 'Content-Type: application/json' \
  -d '{
  "prompt": "photo of a majestic sunrise in the mountains, best quality, 4k",
  "negative_prompt": "low quality, bad quality, sketches",
  "height": 512,
  "width": 512,
  "num_inference_steps": 50,
  "guidance_scale": 7.5,
  "upscale": true
}'

Python client

import bentoml

with bentoml.SyncHTTPClient("http://localhost:3000") as client:
    result = client.txt2img(
        guidance_scale=7.5,
        height=512,
        negative_prompt="low quality, bad quality, sketches",
        num_inference_steps=50,
        prompt="photo a majestic sunrise in the mountains, best quality, 4k",
        upscale=True,
        width=512,
    )

Deploy to BentoCloud

After the Service is ready, you can deploy the application to BentoCloud for better management and scalability. Sign up if you haven't got a BentoCloud account.

Make sure you have logged in to BentoCloud, then run the following command to deploy it.

bentoml deploy .

Once the application is up and running on BentoCloud, you can access it via the exposed URL.

Note: For custom deployment in your own infrastructure, use BentoML to generate an OCI-compliant image.