Merge pull request #3701 from MicrosoftDocs/main

3/24/2025 PM Publish

Author: Taojunshen

articles/ai-foundry/.openpublishing.redirection.ai-studio.json

@@ -290,6 +290,11 @@
             "redirect_url": "/azure/ai-foundry/how-to/deploy-stability-models",
             "redirect_document_id": true
           },
+          {
+            "source_path_from_root": "/articles/ai-foundry/how-to/deploy-stability-models.md",
+            "redirect_url": "/azure/ai-foundry/concepts/models-featured#stability-ai",
+            "redirect_document_id": false
+          },          
           {
             "source_path_from_root": "/articles/ai-studio/how-to/disable-local-auth.md",
             "redirect_url": "/azure/ai-foundry/how-to/disable-local-auth",

articles/ai-foundry/concepts/models-featured.md

@@ -15,7 +15,7 @@ ms.custom: references_regions, tool_generated
 
 # Featured models of Azure AI Foundry
 
-The Azure AI model catalog offers a large selection of models from a wide range of providers. You have various options for deploying models from the model catalog. This article lists featured models in the model catalog that can be deployed and hosted on Microsoft's servers via serverless APIs. For some of these models, you can also host them on your infrastructure for deployment via managed compute. See [Available models for supported deployment options](../how-to/model-catalog-overview.md#available-models-for-supported-deployment-options) for a list of models in the catalog that are available for deployment via managed compute or serverless API.
+The Azure AI model catalog offers a large selection of models from a wide range of providers. You have various options for deploying models from the model catalog. This article lists featured models in the model catalog that can be deployed and hosted on Microsoft's servers via serverless APIs. For some of these models, you can also host them on your infrastructure for deployment via managed compute. See [Available models for supported deployment options](../how-to/model-catalog-overview.md#available-models-for-supported-deployment-options) to find models in the catalog that are available for deployment via managed compute or serverless API.
 
 [!INCLUDE [models-preview](../includes/models-preview.md)]
 
@@ -333,11 +333,19 @@ The Stability AI collection of image generation models include Stable Image Core
 
 | Model  | Type | Capabilities |
 | ------ | ---- | ------------ |
-| [Stable Diffusion 3.5 Large](https://ai.azure.com/explore/models/Stable-Diffusion-3.5-Large/versions/1) | [Image Generation](../how-to/deploy-stability-models.md?context=/azure/ai-foundry/context/context) | - Input: text and image (1000 tokens and 1 image)  <br /> - Output: 1 Image  <br />  - **Tool calling:** No <br /> - Response formats: Image (PNG and JPG) |
-| [Stable Image Core](https://ai.azure.com/explore/models/Stable-Image-Core/versions/1) | [Image Generation](../how-to/deploy-stability-models.md?context=/azure/ai-foundry/context/context) | - Input: text (1000 tokens)  <br /> - Output: 1 Image  <br />  - **Tool calling:** No <br /> - Response formats: Image (PNG and JPG) |
-| [Stable Image Ultra](https://ai.azure.com/explore/models/Stable-Image-Ultra/versions/1) | [Image Generation](../how-to/deploy-stability-models.md?context=/azure/ai-foundry/context/context) | - Input: text (1000 tokens)  <br /> - Output: 1 Image  <br />  - **Tool calling:** No <br /> - Response formats: Image (PNG and JPG) |
+| [Stable Diffusion 3.5 Large](https://ai.azure.com/explore/models/Stable-Diffusion-3.5-Large/version/1/registry/azureml-stabilityai) | Image generation | - **Input:** text and image (1000 tokens and 1 image)  <br /> - **Output:** 1 Image  <br />  - **Tool calling:** No <br /> - **Response formats**: Image (PNG and JPG) |
+| [Stable Image Core](https://ai.azure.com/explore/models/Stable-Image-Core/version/1/registry/azureml-stabilityai) | Image generation | - **Input:** text (1000 tokens)  <br /> - **Output:** 1 Image  <br />  - **Tool calling:** No <br /> - **Response formats:** Image (PNG and JPG) |
+| [Stable Image Ultra](https://ai.azure.com/explore/models/Stable-Image-Ultra/version/1/registry/azureml-stabilityai) | Image generation | - **Input:** text (1000 tokens)  <br /> - **Output:** 1 Image  <br />  - **Tool calling:** No <br /> - **Response formats:** Image (PNG and JPG) |
 
+#### Inference examples: Stability AI
 
+Stability AI models deployed to serverless APIs implement the Azure AI model inference API on the route `/image/generations`.
+For examples of how to use Stability AI models, see the following examples:
+
+- [Use OpenAI SDK with Stability AI models for text to image requests](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/stabilityai/Text_to_Image_openai_library.ipynb)
+- [Use Requests library with Stability AI models for text to image requests](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/stabilityai/Text_to_Image_requests_library.ipynb)
+- [Use Requests library with Stable Diffusion 3.5 Large for image to image requests](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/stabilityai/Image_to_Image.ipynb)
+- [Example of a fully encoded image generation response](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/stabilityai/Sample_image_generation_response.txt)
 
 
 ## Related content

articles/ai-foundry/how-to/deploy-stability-models.md

@@ -6,7 +6,7 @@ ms.reviewer: scottpolly
 ms.author: scottpolly
 ms.service: azure-ai-foundry
 ms.topic: include
-ms.date: 08/05/2024
+ms.date: 03/24/2024
 ms.custom: include, references_regions
 ---
 
@@ -21,7 +21,7 @@ AI21-Jamba-1.5-Large | [Microsoft Managed Countries/Regions/regions](/partner-ce
 
 |Model  |Offer Availability Region  | Hub/Project Region for Deployment  | Hub/Project Region for Fine tuning  |
 |---------|---------|---------|---------|
-Bria-2.3-Fast   | [Microsoft Managed Countries/Regions](/partner-center/marketplace/tax-details-marketplace#microsoft-managed-countriesregions)  | East US 2   | Not available       |
+Bria-2.3-Fast   | [Microsoft Managed Countries/Regions](/partner-center/marketplace/tax-details-marketplace#microsoft-managed-countriesregions)  | East US <br> East US 2 <br> North Central US <br> South Central US <br> West US <br> West US 3   | Not available       |
 
 ### Cohere models
 

articles/ai-foundry/includes/region-availability-maas.md

@@ -105,7 +105,7 @@ response = client.complete(
         SystemMessage("You are a helpful assistant that can generate responses based on images."),
         UserMessage(content=[
             TextContentItem(text="Which conclusion can be extracted from the following chart?"),
-            ImageContentItem(image=ImageUrl(url=data_url))
+            ImageContentItem(image_url=ImageUrl(url=data_url))
         ]),
     ],
     temperature=1,
@@ -214,4 +214,4 @@ response = client.complete(
 )
 ```
 
-Audio is broken into tokens and submitted to the model for processing. Some models might operate directly over audio tokens while other might use internal modules to perform speech-to-text, resulting in different strategies to compute tokens. Read the model card for details about how each model operates.
+Audio is broken into tokens and submitted to the model for processing. Some models might operate directly over audio tokens while other might use internal modules to perform speech-to-text, resulting in different strategies to compute tokens. Read the model card for details about how each model operates.

articles/ai-foundry/model-inference/includes/use-chat-multi-modal/python.md

@@ -35,15 +35,19 @@ Azure AI model inference is a capability in Azure AI Services resources in Azure
 
 :::image type="content" source="../media/quickstart-get-started-deepseek-r1/resources-architecture.png" alt-text="A diagram showing the high level architecture of the resources created in the tutorial." lightbox="../media/quickstart-get-started-deepseek-r1/resources-architecture.png":::
 
-To create an Azure AI project that supports model inference for DeepSeek-R1, follow these steps:
-
-> [!TIP]
-> You can also create the resources using [Azure CLI](../how-to/quickstart-create-resources.md?pivots=programming-language-cli) or [infrastructure as code with Bicep](../how-to/quickstart-create-resources.md?pivots=programming-language-bicep).
+To create an Azure AI project that supports model inference for DeepSeek-R1, follow these steps. You can also create the resources using [Azure CLI](../how-to/quickstart-create-resources.md?pivots=programming-language-cli) or [infrastructure as code with Bicep](../how-to/quickstart-create-resources.md?pivots=programming-language-bicep).
 
 1. Go to [Azure AI Foundry portal](https://ai.azure.com) and log in with your account.
 
 2. On the landing page, select **Create project**.
 
+    > [!TIP]
+    > **Are you using Azure OpenAI service?** When you are connected to Azure AI Foundry portal using an Azure OpenAI service resource, only Azure OpenAI models show up in the catalog. To view the full list of models, including DeepSeek-R1, use the top **Announcements** section and locate the card with the option **Explore more models**.
+    >
+    > :::image type="content" source="../media/quickstart-get-started-deepseek-r1/explore-more-models.png" alt-text="Screenshot showing the card with the option to explore all the models from the catalog." lightbox="../media/quickstart-get-started-deepseek-r1/explore-more-models.png":::
+    >
+    > A new window shows up with the full list of models. Select **DeepSeek-R1** from the list and select **Deploy**. The wizard asks to create a new project.
+
 3. Give the project a name, for example "my-project".
 
 4. In this tutorial, we create a brand new project under a new AI hub, hence, select **Create new hub**. Hubs are containers for multiple projects and allow you to share resources across all the projects.
@@ -135,7 +139,7 @@ You can use the Azure AI Inference package to consume the model in code:
 
 [!INCLUDE [code-chat-reasoning](../includes/code-create-chat-reasoning.md)]
 
-Reasoning may generate longer responses and consume a larger amount of tokens. You can see the [rate limits](../quotas-limits.md) that apply to DeepSeek-R1 models. Consider having a retry strategy to handle rate limits being applied. You can also [request increases to the default limits](../quotas-limits.md#request-increases-to-the-default-limits).
+Reasoning may generate longer responses and consume a larger number of tokens. You can see the [rate limits](../quotas-limits.md) that apply to DeepSeek-R1 models. Consider having a retry strategy to handle rate limits being applied. You can also [request increases to the default limits](../quotas-limits.md#request-increases-to-the-default-limits).
 
 ### Reasoning content
 
@@ -184,4 +188,4 @@ In general, reasoning models don't support the following parameters you can find
 
 * [Use chat reasoning models](../how-to/use-chat-reasoning.md)
 * [Use image embedding models](../how-to/use-image-embeddings.md)
-* [Azure AI Model Inference API](.././reference/reference-model-inference-api.md)
+* [Azure AI Model Inference API](.././reference/reference-model-inference-api.md)

articles/ai-foundry/model-inference/media/quickstart-get-started-deepseek-r1/explore-more-models.png

@@ -116,8 +116,6 @@ items:
         href: how-to/deploy-models-gretel-navigator.md
       - name: Mistral-7B and Mixtral models
         href: how-to/deploy-models-mistral-open.md
-      - name: Stability AI models
-        href: ./how-to/deploy-stability-models.md
     - name: Work with embedding models
       items:
         - name: Work with text embedding models