Merge pull request #50342 from GraemeMalcolm/main

JamesJBarnett · web-flow · commit 4d269c4c49df · 2025-05-08T13:27:56.000-07:00
There's more to image generation than DALL-E
diff --git a/learn-pr/wwl-data-ai/generate-images-azure-openai/1-introduction.yml b/learn-pr/wwl-data-ai/generate-images-azure-openai/1-introduction.yml
@@ -3,10 +3,10 @@ uid: learn.wwl.generate-images-azure-openai.introduction
 title: Introduction
 metadata:
   title: Introduction
-  description: Overview of DALL-E image generation models
+  description: Overview of image generation models
   author: ivorb
   ms.author: berryivor
-  ms.date: 04/29/2025
+  ms.date: 05/08/2025
   ms.topic: unit
   ms.collection:
     - wwl-ai-copilot
diff --git a/learn-pr/wwl-data-ai/generate-images-azure-openai/2-what-is-dall-e.yml b/learn-pr/wwl-data-ai/generate-images-azure-openai/2-what-is-dall-e.yml
@@ -1,12 +1,12 @@
 ### YamlMime:ModuleUnit
 uid: learn.wwl.generate-images-azure-openai.what-is-dall-e
-title: What is DALL-E?
+title: What are image-generation models?
 metadata:
-  title: What is DALL-E?
-  description: Explore DALL-E models
+  title: What are image-generation models?
+  description: Explore what image-generation models are.
   author: ivorb
   ms.author: berryivor
-  ms.date: 04/29/2025
+  ms.date: 05/08/2025
   ms.topic: unit
   ms.collection:
     - wwl-ai-copilot
diff --git a/learn-pr/wwl-data-ai/generate-images-azure-openai/3-dall-e-in-openai-studio.yml b/learn-pr/wwl-data-ai/generate-images-azure-openai/3-dall-e-in-openai-studio.yml
@@ -1,12 +1,12 @@
 ### YamlMime:ModuleUnit
 uid: learn.wwl.generate-images-azure-openai.dall-e-in-openai-studio
-title: Explore DALL-E in Azure AI Foundry portal
+title: Explore image-generation models in Azure AI Foundry portal
 metadata:
-  title: Explore DALL-E in Azure AI Foundry portal
-  description: Use the playground in Azure AI Foundry portal to explore DALL-E image generation
+  title: Explore image-generation models in Azure AI Foundry portal
+  description: Use the Images playground in Azure AI Foundry portal to explore image generation models.
   author: ivorb
   ms.author: berryivor
-  ms.date: 04/29/2025
+  ms.date: 05/08/2025
   ms.topic: unit
   ms.collection:
     - wwl-ai-copilot
diff --git a/learn-pr/wwl-data-ai/generate-images-azure-openai/4-dall-e-rest-api.yml b/learn-pr/wwl-data-ai/generate-images-azure-openai/4-dall-e-rest-api.yml
@@ -1,12 +1,12 @@
 ### YamlMime:ModuleUnit
 uid: learn.wwl.generate-images-azure-openai.dall-e-rest-api
-title: Use the Azure OpenAI REST API to consume DALL-E models
+title: Create a client application that uses an image generation model
 metadata:
-  title: Create a client application to consume DALL-E models
-  description: Use APIs and SDKs to consume DALL-E models and generate images
+  title: Create a client application that uses an image generation model
+  description: Use APIs and SDKs to consume image generation models.
   author: ivorb
   ms.author: berryivor
-  ms.date: 04/29/2025
+  ms.date: 05/08/2025
   ms.topic: unit
   ms.collection:
     - wwl-ai-copilot
diff --git a/learn-pr/wwl-data-ai/generate-images-azure-openai/5-exercise-use-dall-e.yml b/learn-pr/wwl-data-ai/generate-images-azure-openai/5-exercise-use-dall-e.yml
@@ -1,12 +1,12 @@
 ### YamlMime:ModuleUnit
 uid: learn.wwl.generate-images-azure-openai.exercise-use-dall-e
-title: Exercise - Generate images with a DALL-E model
+title: Exercise - Generate images with AI
 metadata:
   title: Exercise - Generate images with AI
-  description: Hands-on exercise to use DALL-E in Azure OpenAI service
+  description: Hands-on exercise to use an image generation model in Azure AI Foundry.
   author: ivorb
   ms.author: berryivor
-  ms.date: 04/29/2025
+  ms.date: 05/08/2025
   ms.topic: unit
   ms.collection:
     - wwl-ai-copilot
diff --git a/learn-pr/wwl-data-ai/generate-images-azure-openai/6-knowledge-check.yml b/learn-pr/wwl-data-ai/generate-images-azure-openai/6-knowledge-check.yml
@@ -3,7 +3,7 @@ uid: learn.wwl.generate-images-azure-openai.knowledge-check
 title: Module assessment
 metadata:
   title: Module assessment
-  description: Check your knowledge of using DALL-E in Azure OpenAI service
+  description: Check your knowledge of image generation models.
   author: ivorb
   ms.author: berryivor
   ms.date: 04/29/2025
@@ -25,14 +25,14 @@ quiz:
     - content: "text-embedding-ada-002"
       isCorrect: false
       explanation: "The text-embedding-ada-002 model is used to generate embeddings (vectors that represent text tokens)."
-  - content: "Which playground in Azure AI Foundry portal should you use to utilize the DALL-E model?"
+  - content: "Which playground in Azure AI Foundry portal should you use to test an image-generation model?"
     choices:
     - content: "Agents"
       isCorrect: false
       explanation: "The Agents playground is used to test AI agents."
     - content: "Chat"
       isCorrect: false
-      explanation: "The Chat playground is used to explore GPT 3 and earlier language generation models."
+      explanation: "The Chat playground is used to explore natural language generation models."
     - content: "Images"
       isCorrect: true
       explanation: "The Images playground is used to explore image generation models."
diff --git a/learn-pr/wwl-data-ai/generate-images-azure-openai/7-summary.yml b/learn-pr/wwl-data-ai/generate-images-azure-openai/7-summary.yml
@@ -3,10 +3,10 @@ uid: learn.wwl.generate-images-azure-openai.summary
 title: Summary
 metadata:
   title: Summary
-  description: Summarize what you've learned about DALL-E models
+  description: Summarize what you've learned about image generation models
   author: ivorb
   ms.author: berryivor
-  ms.date: 04/29/2025
+  ms.date: 05/08/2025
   ms.topic: unit
   ms.collection:
     - wwl-ai-copilot
diff --git a/learn-pr/wwl-data-ai/generate-images-azure-openai/includes/1-introduction.md b/learn-pr/wwl-data-ai/generate-images-azure-openai/includes/1-introduction.md
@@ -1,5 +1,9 @@
-Azure AI Foundry enables you to use language models to generate content based on natural language prompts. One of these models is the OpenAI DALL-E image generation model, which is capable of creating original graphical content based on natural language descriptions of a desired image.
+With Azure AI Foundry, you can use language models to generate content based on natural language prompts. Often the generated content is in the form of natural language text, but increasingly, models can generate other kinds of content.
 
-The ability to use AI to generate graphics has a number of applications; including the creation of illustrations or photorealistic images for articles or marketing collateral, generation of unique product or company logos, or any scenario where a desired image can be described.
+For example, the OpenAI DALL-E image generation model can create original graphical content based on a description of a desired image.
 
-In this module, you'll learn how to develop an application that uses the DALL-E model to generate and retrieve images.
+![Diagram of a prompt requesting a model to create an image.](../media/image-generation.png)
+
+The ability to use AI to generate graphics has many applications; including the creation of illustrations or photorealistic images for articles or marketing collateral, generation of unique product or company logos, or any scenario where a desired image can be described.
+
+In this module, you'll learn how to develop an application that uses generative AI to generate original images.
diff --git a/learn-pr/wwl-data-ai/generate-images-azure-openai/includes/2-what-is-dall-e.md b/learn-pr/wwl-data-ai/generate-images-azure-openai/includes/2-what-is-dall-e.md
@@ -1,11 +1,19 @@
-DALL-E is a generative AI model that can generate graphical data from natural language input. Put more simply, you can provide a DALL-E model with a description and it can generate an appropriate image.
+Azure AI Foundry supports multiple models that are capable of generating images, including (but not limited to):
 
-For example, you might submit the following natural language prompt to DALL-E:
+- DALL-E 3
+- GPT-Image 1
+
+> [!TIP]
+> For the latest information about model availability in Azure AI Foundry, view the model catalog. See **[Model catalog and collections in Azure AI Foundry portal](/azure/ai-foundry/how-to/model-catalog-overview?azure-portal=true)** for details.
+
+Image generation models are generative AI model that can create graphical data from natural language input. Put more simply, you can provide the model with a description and it can generate an appropriate image.
+
+For example, you might submit the following natural language prompt to an image generation model:
 
 *A squirrel on a motorcycle*
 
 This prompt could result in the generation of graphical output such as the following image:
 
 ![A picture of a squirrel on a motorcycle.](../media/squirrel-on-motorcycle.png)
 
-The images generated by DALL-E models are original; they are not retrieved from a curated image catalog. In other words, DALL-E is not a search system for *finding* appropriate images - it is an artificial intelligence (AI) model that *generates* new images based on the data on which it was trained.
+The images generated are original; they aren't retrieved from a curated image catalog. In other words, the model isn't a search system for *finding* appropriate images - it is an artificial intelligence (AI) model that *generates* new images based on the data on which it was trained.
diff --git a/learn-pr/wwl-data-ai/generate-images-azure-openai/includes/3-dall-e-in-openai-studio.md b/learn-pr/wwl-data-ai/generate-images-azure-openai/includes/3-dall-e-in-openai-studio.md
@@ -1,8 +1,8 @@
-To experiment with DALL-E models, you can create an Azure AI Foundry project (or provision an Azure OpenAI Service resource in an Azure subscription) and use the *Images playground* in Azure AI Foundry portal to submit prompts and view the resulting generated images.
+To experiment with image generation models, you can create an Azure AI Foundry project and use the *Images playground* in Azure AI Foundry portal to submit prompts and view the resulting generated images.
 
 ![A screenshot of the Images playground in Azure AI Studio.](../media/images-playground.png)
 
-When using the playground, you can adjust the **settings** to specify:
+When using the playground, you can adjust the **settings** to control the output. For example, when using a DALL-E model you can specify:
 
 - The resolution (size) of the generated images. Available sizes are `1024x1024` (which is the default value), `1792x1024`, or `1024x1792`.
 - The image style to be generated (such as `vivid` or `natural`).
diff --git a/learn-pr/wwl-data-ai/generate-images-azure-openai/includes/4-dall-e-rest-api.md b/learn-pr/wwl-data-ai/generate-images-azure-openai/includes/4-dall-e-rest-api.md
@@ -1,14 +1,14 @@
-You can use the Azure OpenAI service REST API to consume DALL-E models from applications. Alternatively, you can use a language-specific OpenAI SDK (for example, the OpenAI Python SDK or the Azure OpenAI .NET SDK) to abstract the REST methods.
+You can use a REST API to consume DALL-E models from applications. Alternatively, you can use a language-specific SDK (for example, the OpenAI Python SDK or the Azure OpenAI .NET SDK) to abstract the REST methods.
 
-You initiate the image generation process by submitting a request to the service endpoint with the authorization key in the header. The request contains the following parameters:
+You initiate the image generation process by submitting a request to the service endpoint with the authorization key in the header. The request contains parameters describing the image-generation requirements. For example, parameters for a DALL-E model include:
 
 - **prompt**: The description of the image to be generated.
 - **n**: The number of images to be generated. DALL-E 3 only supports n=1.
-- **size**: The resolution of the image(s) to be generated (*1024x1024*, *1792x1024*, or *1024x1792* for DALL-E 3; *256x256*, *512x512*, or *1024x1024* for DALL-E 2).
+- **size**: The resolution of the image(s) to be generated (*1024x1024*, *1792x1024*, or *1024x1792* for DALL-E 3)
 - **quality** *Optional*: The quality of the image (*standard* or *hd*). Defaults to *standard*.
 - **style** *Optional*: The visual style of the image (*natural* or *vivid*). Defaults to *vivid*.
 
-For example, the following JSON could be submitted via the REST API to generate an 1024 x 1024 image of a badger wearing a tuxedo:
+For example, the following JSON could be submitted via the REST API to a DALL-E model, prompting it to generate an 1024 x 1024 image of a badger wearing a tuxedo:
 
 ```json
 {
@@ -20,8 +20,6 @@ For example, the following JSON could be submitted via the REST API to generate
 }
 ```
 
-If you're using an older generation model such as DALL-E 2, the REST request does not immediately return the results of the image generation process. Instead, the response includes an **operation-location** header with a URL for a callback service that your application code can poll until the results of image generation are ready.
-
 With DALL-E 3, the result from the request is processed synchronously with the response containing the URL for the generated image. The response is similar to the following JSON:
 
 ```json
diff --git a/learn-pr/wwl-data-ai/generate-images-azure-openai/includes/5-exercise-use-dall-e.md b/learn-pr/wwl-data-ai/generate-images-azure-openai/includes/5-exercise-use-dall-e.md
@@ -1,4 +1,4 @@
-Now it's your chance to use a DALL-E model to generate images. In this exercise, you'll provision an Azure AI Foundry project and use it to deploy a DALL-E model and explore image generation in the Azure AI Foundry portal. Then you'll use the Python or .NET SDK to consume a DALL-E model from a custom application.
+Now it's your chance to use generative AI to create images. In this exercise, you'll provision an Azure AI Foundry project and deploy a DALL-E model. Then, you'll explore image generation in the Azure AI Foundry portal. Finally, you'll use the Python or .NET SDK to consume the DALL-E model from a custom application.
 
 Launch the exercise and follow the instructions.
 
diff --git a/learn-pr/wwl-data-ai/generate-images-azure-openai/includes/7-summary.md b/learn-pr/wwl-data-ai/generate-images-azure-openai/includes/7-summary.md
@@ -1,4 +1,4 @@
-This module described the DALL-E image generation model, and how you can use it in the Azure OpenAI service to generate images based on natural language prompts. You can explore DALL-E using the playground in Azure AI Studio, and you can use the REST API to build applications that use DALL-E to generate new images.
+This module described image generation models, and how you can use them in Azure AI Foundry to generate images based on natural language prompts. You can explore image generation models using the *Images* playground in Azure AI Foundry portal, and you can use REST APIs or SDKs to build applications that generate new images.
 
 > [!TIP]
-> To learn more about using DALL-E in the Azure OpenAI service, see [Quickstart: Generate images with Azure OpenAI Service](/azure/ai-services/openai/dall-e-quickstart) in the Azure openAI service documentation.
+> To learn more about using DALL-E in the Azure OpenAI service, see [Quickstart: Generate images with Azure OpenAI Service](/azure/ai-services/openai/dall-e-quickstart) in the Azure OpenAI service documentation.
diff --git a/learn-pr/wwl-data-ai/generate-images-azure-openai/index.yml b/learn-pr/wwl-data-ai/generate-images-azure-openai/index.yml
@@ -2,21 +2,21 @@
 uid: learn.wwl.generate-images-azure-openai
 metadata:
   title: Generate images with AI
-  description: Use DALL-E models in Azure AI Foundry to generate images
+  description: Use models in Azure AI Foundry to generate images
   author: ivorb
   ms.author: berryivor
-  ms.date: 04/29/2025
+  ms.date: 05/08/2025
   ms.service: azure-ai-openai
   ms.topic: module-standard-task-based
   ms.collection:
     - wwl-ai-copilot
 title: Generate images with AI
-summary: "In Azure AI Foundry, you can use the OpenAI DALL-E model to generate original images based on natural language prompts."
+summary: "In Azure AI Foundry, you can use image generation models to create original images based on natural language prompts."
 abstract: |
   After completing this module, you'll be able to:
-    - Describe the capabilities of DALL-E models
+    - Describe the capabilities of image generation models
     - Use the Images playground in Azure AI Foundry portal
-    - Integrate DALL-E model image generation into your apps
+    - Integrate image generation models into your apps
 prerequisites: |
   Before starting this module, you should be familiar with Azure AI Foundry. You should also have programming experience with Python or Microsoft C#.
 iconUrl: /learn/achievements/generic-badge.svg
diff --git a/learn-pr/wwl-data-ai/generate-images-azure-openai/media/image-generation.png b/learn-pr/wwl-data-ai/generate-images-azure-openai/media/image-generation.png
