Text-to-image generation using advanced AI models offers a unique way to bring textual descriptions to life as images. Stable Diffusion is a powerful model capable of generating high-quality images from text inputs, and Runpod is a serverless computing platform that can manage resource-intensive tasks effectively. This tutorial will guide you through setting up a serverless application that utilizes Stable Diffusion for generating images from text prompts on Runpod. By the end of this guide, you will have a fully functional text-to-image generation system deployed on a Runpod serverless environment.

​
Prerequisites

Before diving into the setup, ensure you have the following:
  • Access to a Runpod account
  • A GPU instance configured on Runpod
  • Basic knowledge of Python programming

​
Import required libraries

To start, we need to import several essential libraries. These will provide the functionalities required for serverless operation and image generation.
stable_diffusion.py
import runpod
import torch
from diffusers import StableDiffusionPipeline
from io import BytesIO
import base64
Here’s a breakdown of the imports:
  • runpod: The SDK used to interact with Runpod’s serverless environment.
  • torch: PyTorch library, necessary for running deep learning models and ensuring they utilize the GPU.
  • diffusers: Provides methods to work with diffusion models like Stable Diffusion.
  • BytesIO and base64: Used to handle image data conversions.
Next, confirm that CUDA is available, as the model requires a GPU to function efficiently.
stable_diffusion.py
assert (
    torch.cuda.is_available()
), "CUDA is not available. Make sure you have a GPU instance."
This assertion checks whether a compatible NVIDIA GPU is available for PyTorch to use.

​
Load the Stable Diffusion Model

We’ll load the Stable Diffusion model in a separate function. This ensures that the model is only loaded once when the worker process starts, which is more efficient.
stable_diffusion.py
def load_model():
    model_id = "runwayml/stable-diffusion-v1-5"
    pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
    pipe = pipe.to("cuda")
    return pipe
Here’s what this function does:
  • model_id specifies the model identifier for Stable Diffusion version 1.5.
  • StableDiffusionPipeline.from_pretrained loads the model weights into memory with a specified tensor type.
  • pipe.to("cuda") moves the model to the GPU for faster computation.

​
Define Helper Functions

We need a helper function to convert the generated image into a base64 string. This encoding allows the image to be easily transmitted over the web in textual form.
stable_diffusion.py
def image_to_base64(image):
    buffered = BytesIO()
    image.save(buffered, format="PNG")
    return base64.b64encode(buffered.getvalue()).decode("utf-8")
Explanation:
  • BytesIO: Creates an in-memory binary stream to which the image is saved.
  • base64.b64encode: Encodes the binary data to a base64 format, which is then decoded to a UTF-8 string.

​
Define the Handler Function

The handler function will be responsible for managing image generation requests. It includes loading the model (if not already loaded), validating inputs, generating images, and converting them to base64 strings.
stable_diffusion.py
def stable_diffusion_handler(event):
    global model

    # Ensure the model is loaded
    if "model" not in globals():
        model = load_model()

    # Get the input prompt from the event
    prompt = event["input"].get("prompt")

    # Validate input
    if not prompt:
        return {"error": "No prompt provided for image generation."}

    try:
        # Generate the image
        image = model(prompt).images[0]

        # Convert the image to base64
        image_base64 = image_to_base64(image)

        return {"image": image_base64, "prompt": prompt}

    except Exception as e:
        return {"error": str(e)}
Key steps in the function:
  • Checks if the model is loaded globally, and loads it if not.
  • Extracts the prompt from the input event.
  • Validates that a prompt has been provided.
  • Uses the model to generate an image.
  • Converts the image to base64 and prepares the response.

​
Start the Serverless Worker

Now, we’ll start the serverless worker using the Runpod SDK.
stable_diffusion.py
runpod.serverless.start({"handler": stable_diffusion_handler})
This command starts the serverless worker and specifies the stable_diffusion_handler function to handle incoming requests.

​
Complete Code

For your convenience, here is the entire code consolidated:
stable_diffusion.py
import runpod
import torch
from diffusers import StableDiffusionPipeline
from io import BytesIO
import base64

assert (
    torch.cuda.is_available()
), "CUDA is not available. Make sure you have a GPU instance."


def load_model():
    model_id = "runwayml/stable-diffusion-v1-5"
    pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
    # to run on cpu change `cuda` to `cpu`
    pipe = pipe.to("cuda")
    return pipe


def image_to_base64(image):
    buffered = BytesIO()
    image.save(buffered, format="PNG")
    return base64.b64encode(buffered.getvalue()).decode("utf-8")


def stable_diffusion_handler(event):
    global model

    if "model" not in globals():
        model = load_model()

    prompt = event["input"].get("prompt")

    if not prompt:
        return {"error": "No prompt provided for image generation."}

    try:
        image = model(prompt).images[0]
        image_base64 = image_to_base64(image)

        return {"image": image_base64, "prompt": prompt}

    except Exception as e:
        return {"error": str(e)}


runpod.serverless.start({"handler": stable_diffusion_handler})

​
Testing Locally

Before deploying on Runpod, you might want to test the script locally. Create a test_input.json file with the following content:
test_input.json
{
  "input": {
    "prompt": "A serene landscape with mountains and a lake at sunset"
  }
}
Run the script with the following command: 
python stable_diffusion.py --rp_server_api
Note: Local testing may not work optimally without a suitable GPU. If issues arise, proceed to deploy and test on Runpod.

​
Important Notes:

  1. This example requires significant computational resources, particularly GPU memory. Ensure your Runpod configuration has sufficient GPU capabilities.
  2. The model is loaded only once when the worker starts, optimizing performance.
  3. We’ve used Stable Diffusion v1.5; you can replace it with other versions or models as required.
  4. The handler includes error handling for missing input and exceptions during processing.
  5. Ensure necessary dependencies (like torch, diffusers) are included in your environment or requirements file when deploying.
  6. The generated image is returned as a base64-encoded string. For practical applications, consider saving it to a file or cloud storage.

​
Conclusion

In this tutorial, you learned how to use the Runpod serverless platform with Stable Diffusion to create a text-to-image generation system. This project showcases the potential for deploying resource-intensive AI models in a serverless architecture using the Runpod Python SDK. You now have the skills to create and deploy sophisticated AI applications on Runpod. What will you create next?