Overview

This exercise demonstrates how to generate images using AI with Azure AI Foundry and the OpenAI DALL-E model. The goal is to develop an application that interacts with the model to create AI-generated images.

Steps & Configuration Details

1. Create an Azure AI Foundry Project

  • Open Azure AI Foundry portal (https://ai.azure.com) and sign in.
  • Search for dall-e-3 and select Use this model.
  • Configuration Items:
    • Azure AI Foundry Resource: A valid name.
    • Subscription: Your Azure subscription.
    • Resource Group: Select or create a resource group.
    • Region: Choose any AI Services-supported location.
    • Deployment Name: dall-e-3 (default).

2. Test the Model in the Playground

  • Navigate to Playgrounds → Images Playground.
  • Ensure DALL-E model deployment is selected.
  • Submit prompts:
    Create an image of a robot eating spaghetti.
  • Review the generated image and refine prompts.

3. Prepare the Application Configuration

  • Open Azure AI Foundry portal → Models + Endpoints.
  • Click Get Endpoint to retrieve the connection string.
  • Open Azure Portal (https://portal.azure.com).
  • Launch Azure Cloud Shell (PowerShell environment).
  • Clone the repository:
    rm -r mslearn-ai-vision -f
git clone https://github.com/MicrosoftLearning/mslearn-ai-vision
  • Navigate to the correct folder:
    • Python: cd mslearn-ai-vision/Labfiles/dalle-client/python
    • C#: cd mslearn-ai-vision/Labfiles/dalle-client/c-sharp
  • Install dependencies:
    • Python:
      python -m venv labenv
./labenv/bin/Activate.ps1
pip install -r requirements.txt azure-identity azure-ai-projects openai requests
    • C#:
      dotnet add package Azure.Identity
dotnet add package Azure.AI.Projects --version 1.0.0-beta.9
dotnet add package Azure.AI.OpenAI
  • Open the configuration file:
    • Python: .env
    • C#: appsettings.json
  • Update Configuration Values:
    • Project Endpoint
    • Model Deployment Name (dall-e-3)
  • Save the configuration file.

4. Add Code to Use Azure OpenAI

  • Open the code file:
    • Python: dalle-client.py
    • C#: Program.cs
  • Add references:
    • Python:
      from dotenv import load_dotenv
from azure.identity import DefaultAzureCredential
from azure.ai.projects import AIProjectClient
import requests
    • C#:
      using Azure.Identity;
using Azure.AI.Projects;
using Azure.AI.OpenAI;
using OpenAI.Images;
  • Initialize the OpenAI client:
    • Python:
      project_client = AIProjectClient(
    endpoint=project_connection,
    credential=DefaultAzureCredential(
        exclude_environment_credential=True,
        exclude_managed_identity_credential=True
    )
)
openai_client = project_client.inference.get_azure_openai_client(api_version="2024-06-01")
    • C#:
      DefaultAzureCredentialOptions options = new() {
    ExcludeEnvironmentCredential = true,
    ExcludeManagedIdentityCredential = true
};
ImageClient openAIimageClient = new AzureOpenAIClient(
    new Uri(project_connection),
    new DefaultAzureCredential(options)
).GetImageClient(model_deployment);
  • Generate an image:
    • Python:
      result = openai_client.images.generate(
    model=model_deployment,
    prompt=input_text,
    n=1
)
json_response = json.loads(result.model_dump_json())
image_url = json_response["data"][0]["url"]
    • C#:
      GeneratedImage imageGeneration = await openAIimageClient.GenerateImageAsync(
    input_text,
    new ImageGenerationOptions() {
        Size = GeneratedImageSize.W1024xH1024
    }
);
imageUrl = imageGeneration.ImageUri;

5. Run Your Application

  • Open Azure Cloud Shell.
  • Run the application:
    • Python:
      python dalle-client.py
    • C#:
      dotnet run
  • Example prompt:
    Create an image of a robot eating pizza.
  • The response should include a generated image.

6. Clean Up

  • Delete Azure resources to avoid unnecessary costs:

Related Posts