Add tutorial for text-to-image generation using Microsoft.Extensions.AI

[Copilot]

This PR adds a comprehensive tutorial that demonstrates how to use the Microsoft.Extensions.AI library to generate images from text prompts using the IImageGenerator interface.

Overview

The tutorial covers the complete workflow for integrating text-to-image capabilities into .NET applications, with support for both OpenAI and Azure OpenAI providers.

What's included

Documentation

• New tutorial article (docs/ai/tutorials/text-to-image.md) that covers:
  • Introduction to the IImageGenerator interface and its capabilities
  • Step-by-step instructions for creating a console application
  • Configuration options for customizing image generation (size, count, format)
  • Pipeline composition with middleware for telemetry and logging
  • Error handling and best practices
  • Saving generated images locally
  • Production-ready recommendations

Code Examples

• OpenAI implementation with complete, compilable C# code
• Azure OpenAI implementation with authentication using DefaultAzureCredential
• Both examples demonstrate:
  • Basic image generation from text prompts
  • Configuration with ImageGenerationOptions
  • Building pipelines with ImageGeneratorBuilder
  • Adding OpenTelemetry for observability
  • Error handling for common scenarios
  • Downloading and saving generated images

Features

• Uses zone pivots to seamlessly switch between OpenAI and Azure OpenAI examples
• All code examples compile successfully using .NET 9.0
• Follows Microsoft documentation standards with proper frontmatter
• Includes proper experimental API warning (MEAI001)
• Code snippets organized with region markers for easy reference
• Added to the AI tutorials section in the table of contents

Technical Details

The tutorial demonstrates the experimental IImageGenerator interface from the Microsoft.Extensions.AI library, showing how to:

• Convert OpenAI's ImageClient to IImageGenerator using the AsIImageGenerator() extension method
• Configure image generation with System.Drawing.Size for dimensions
• Use ImageGenerationResponseFormat for controlling output format
• Access generated images through ImageGenerationResponse.Contents collection
• Cast content items to UriContent to retrieve image URLs

Fixes #486214

Warning

Firewall rules blocked me from connecting to one or more addresses (expand for details)

I tried to connect to the following addresses, but was blocked by firewall rules:

• https://api.github.com/repos/jeremylikness/text2imagesample/contents
  • Triggering command: curl -s REDACTED (http block)

If you need me to access, download, or install something from one of these locations, you can either:

• Configure Actions setup steps to set up my environment, which run before the firewall is enabled
• Add the appropriate URLs or hosts to the custom allowlist in this repository's Copilot coding agent settings (admins only)

Original prompt

---

This section details on the original issue you should resolve

<issue_title>[New article]: AI text-to-image feature</issue_title>
<issue_description>Create a tutorial that shows how to use the text to image features of Microsoft.Extensions.AI, including code examples in C#.

Proposed topic or title

AI text-to-image feature

Location in table of contents.

docs/ai/toc.yml

Sources:

• https://devblogs.microsoft.com/dotnet/explore-text-to-image-dotnet/
• https://github.com/jeremylikness/text2imagesample
• ericstj/imageGeneratorSample@8a97699
• Add image support to GenerativeAI.Microsoft gunpal5/Google_GenerativeAI#73

---

Associated WorkItem - 486214</issue_description>

Comments on the Issue (you are @copilot in this section)

Fixes #48169

---

💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.

---

Internal previews

📄 File	🔗 Preview link
docs/ai/index.yml	[linkListType: architecture
docs/ai/overview.md	Develop .NET apps with AI features
docs/ai/quickstarts/build-chat-app.md	CustomerIntent: As a .NET developer new to AI, I want deploy and use sample code to interact to learn from the sample code.
docs/ai/quickstarts/build-vector-search-app.md	Build a .NET AI vector search app
docs/ai/quickstarts/generate-images.md	docs/ai/quickstarts/generate-images
docs/ai/quickstarts/text-to-image.md	Generate images from text using AI
docs/ai/toc.yml	docs/ai/toc
docs/azure/index.yml	Azure for .NET developers

[Copilot]

Pull Request Overview

This PR adds a comprehensive quickstart tutorial demonstrating how to generate images from text prompts using the Microsoft.Extensions.AI library's experimental IImageGenerator interface. The tutorial provides step-by-step instructions with working code examples for Azure OpenAI integration, covering basic image generation, configuration options, error handling, and best practices.

Key changes:

• Adds new quickstart tutorial text-to-image.md with complete Azure OpenAI implementation
• Reorganizes TOC structure with new "Text to image" section and expanded quickstarts
• Includes working C# code example with proper error handling and configuration management
• Updates existing generate-images.md title to clarify it uses DALLe directly

Reviewed Changes

Copilot reviewed 5 out of 6 changed files in this pull request and generated 5 comments.

Show a summary per file

File	Description
docs/ai/toc.yml	Restructures navigation with expanded quickstarts section and new "Text to image" category containing both MEAI and DALLe tutorials
docs/ai/quickstarts/text-to-image.md	Adds new comprehensive tutorial covering IImageGenerator usage with Azure OpenAI, including setup, code examples, options, error handling, and best practices
docs/ai/quickstarts/snippets/text-to-image/azure-openai/TextToImageAzureOpenAI.csproj	Adds project file with required package references for the text-to-image quickstart sample
docs/ai/quickstarts/snippets/text-to-image/azure-openai/Program.cs	Implements complete working example demonstrating basic generation, configuration options, and error handling patterns
docs/ai/quickstarts/generate-images.md	Updates title to clarify distinction from MEAI tutorial by specifying it uses DALLe

[ericstj]

@gewarren - gave first pass of feedback. Let me know what you think based on desired scope of this initial PR.