Merge pull request #6263 from MicrosoftDocs/main

Auto Publish – main to live - 2025-07-28 22:03 UTC

Author: learn-build-service-prod[bot]

articles/ai-foundry/how-to/create-azure-ai-project-template.md

@@ -61,7 +61,7 @@ Deploy the Bicep file using either the Azure CLI or Azure PowerShell.
 
 ```azurecli
 az group create --name exampleRG --location eastus
-az deployment group create --resource-group exampleRG --template-file main.bicep --parameters aiServicesName=myai aiProjectName=myai-proj 
+az deployment group create --resource-group exampleRG --template-file main.bicep --parameters aiFoundryName=myai aiProjectName=myai-proj 
 ```
 
 # [Azure PowerShell](#tab/powershell)

articles/ai-foundry/openai/how-to/dall-e.md

@@ -218,6 +218,10 @@ Use the *output_format* parameter to specify the format of the generated image.
 
 Use the *output_compression* parameter to specify the compression level for the generated image. Input an integer between `0` and `100`, where `0` is no compression and `100` is maximum compression. The default is `100`.
 
+#### Streaming 
+
+Use the *stream* parameter to enable streaming responses. When set to `true`, the API returns partial images as they are generated. This provides faster visual feedback for users and improves perceived latency. Set the *partial_images* parameter to control how many partial images are generated (1-3).
+
 
 #### [DALL-E 3](#tab/dalle-3)
 
@@ -263,11 +267,12 @@ The format in which DALL-E 3 generated images are returned. Must be one of `url`
 
 The Image Edit API allows you to modify existing images based on text prompts you provide. The API call is similar to the image generation API call, but you also need to provide an input image.
 
-> [!IMPORTANT]
-> The input image must be less than 20 MB in size and must be a PNG or JPG file.
 
 #### [GPT-image-1](#tab/gpt-image-1)
 
+> [!IMPORTANT]
+> The input image must be less than 50 MB in size and must be a PNG or JPG file.
+
 Send a POST request to:
 
 ```
@@ -326,11 +331,20 @@ The following API body parameters are available for image editing models, in add
 
 The *image* value indicates the image file you want to edit.
 
+#### Input fidelity 
+
+The *input_fidelity* parameter controls how much effort the model will exert to match the style and features, especially facial features, of input images 
+
+This allows you to make subtle edits to an image without altering unrelated areas. When you use high input fidelity, faces are preserved more accurately than in standard mode. 
+
 
 #### Mask
 
 The *mask* parameter is the same type as the main *image* input parameter. It defines the area of the image that you want the model to edit, using fully transparent pixels (alpha of zero) in those areas. The mask must be a PNG file and have the same dimensions as the input image.
 
+#### Streaming 
+
+Use the *stream* parameter to enable streaming responses. When set to `true`, the API returns partial images as they are generated. This provides faster visual feedback for users and improves perceived latency. Set the *partial_images* parameter to control how many partial images are generated (1-3).
 
 #### [DALL-E 3](#tab/dalle-3)
 

articles/ai-foundry/openai/includes/api-versions/latest-inference-preview.md

@@ -664,11 +664,14 @@ Edits an image from a text caption on a given gpt-image-1 model deployment
 
 | Name | Type | Description | Required | Default |
 |------|------|-------------|----------|---------|
-| image | string or array | The image(s) to edit. Must be a supported image file or an array of images. Each image should be a png, or jpg file less than 25MB. | Yes |  |
+| image | string or array | The image(s) to edit. Must be a supported image file or an array of images. Each image should be a png, or jpg file less than 50MB. | Yes |  |
+| input_fidelity| string | Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1. Supports `high` and `low`. | no | `low`. | 
 | mask | string | An additional image whose fully transparent areas (e.g., where alpha is zero) indicate where the image should be edited. If there are multiple images provided, the mask will be applied to the first image. Must be a valid PNG file, less than 4MB, and have the same dimensions as the image. | No |  |
 | n | integer | The number of images to generate. | No | 1 |
 | prompt | string | A text description of the desired image(s). The maximum length is 32000 characters. | Yes |  |
 | quality | enum | The quality of the image that will be generated. `high`, `medium` and `low` are only supported for `gpt-image-1`. `dall-e-2` only supports `standard` quality. Defaults to `auto`.<br>Possible values: `standard`, `low`, `medium`, `high`, `auto` | No |  |
+|partial_images| integer | The number of partial images to generate. This parameter is used for streaming responses that return partial images. Value must be between 0 and 3. When set to 0, the response will be a single image sent in one streaming event. Note that the final image may be sent before the full number of partial images are generated if the full image is generated more quickly. | 0 |
+| stream | boolean | Edit the image in streaming mode. | no | `false` |
 | response_format | enum | The format in which the generated images are returned. Must be one of `url` or `b64_json`. URLs are only valid for 60 minutes after the image has been generated. This parameter is only supported for `dall-e-2`, as `gpt-image-1` will always return base64-encoded images.<br>Possible values: `url`, `b64_json` | No |  |
 | size | enum | The size of the generated images. Must be one of `1024x1024`, `1536x1024` (landscape), `1024x1536` (portrait), or `auto` (default value) for `gpt-image-1`, and one of `256x256`, `512x512`, or `1024x1024` for `dall-e-2`.<br>Possible values: `256x256`, `512x512`, `1024x1024`, `1536x1024`, `1024x1536`, `auto` | No |  |
 | user | string | A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.  | No |  |
@@ -693,7 +696,7 @@ Edits an image from a text caption on a given gpt-image-1 model deployment
 |application/json | [azureerrorresponse](#azureerrorresponse) | |
 
 
-## Create image
+## Image generations - Create
 
 ```HTTP
 POST {endpoint}/openai/v1/images/generations?api-version=preview
@@ -729,6 +732,8 @@ POST {endpoint}/openai/v1/images/generations?api-version=preview
 | output_compression | integer | The compression level (0-100%) for the generated images. This parameter is only supported for `gpt-image-1` with the `webp` or `jpeg` output formats, and defaults to 100. | No | 100 |
 | output_format | enum | The format in which the generated images are returned. This parameter is only supported for `gpt-image-1`. Must be one of `png`, `jpeg`, or `webp`.<br>Possible values: `png`, `jpeg`, `webp` | No |  |
 | prompt | string | A text description of the desired image(s). The maximum length is 32000 characters for `gpt-image-1`, 1000 characters for `dall-e-2` and 4000 characters for `dall-e-3`. | Yes |  |
+|partial_images| integer | The number of partial images to generate. This parameter is used for streaming responses that return partial images. Value must be between 0 and 3. When set to 0, the response will be a single image sent in one streaming event. Note that the final image may be sent before the full number of partial images are generated if the full image is generated more quickly. | 0 |
+| stream | boolean | Edit the image in streaming mode. | no | `false` |
 | quality | enum | The quality of the image that will be generated. <br><br>- `auto` (default value) will automatically select the best quality for the given model.<br>- `high`, `medium` and `low` are supported for `gpt-image-1`.<br>- `hd` and `standard` are supported for `dall-e-3`.<br>- `standard` is the only option for `dall-e-2`.<br>Possible values: `standard`, `hd`, `low`, `medium`, `high`, `auto` | No |  |
 | response_format | enum | The format in which generated images with `dall-e-2` and `dall-e-3` are returned. Must be one of `url` or `b64_json`. URLs are only valid for 60 minutes after the image has been generated. This parameter isn't supported for `gpt-image-1` which will always return base64-encoded images.<br>Possible values: `url`, `b64_json` | No |  |
 | size | enum | The size of the generated images. Must be one of `1024x1024`, `1536x1024` (landscape), `1024x1536` (portrait), or `auto` (default value) for `gpt-image-1`, one of `256x256`, `512x512`, or `1024x1024` for `dall-e-2`, and one of `1024x1024`, `1792x1024`, or `1024x1792` for `dall-e-3`.<br>Possible values: `auto`, `1024x1024`, `1536x1024`, `1024x1536`, `256x256`, `512x512`, `1792x1024`, `1024x1792` | No |  |
@@ -2024,13 +2029,13 @@ Represents a completion response from the API. Note: both the streamed and non-s
 | Name | Type | Description | Required | Default |
 |------|------|-------------|----------|---------|
 | background | enum | Allows to set transparency for the background of the generated image(s). <br>This parameter is only supported for `gpt-image-1`. Must be one of `transparent`, `opaque` or `auto` (default value). When `auto` is used, the model will automatically determine the best background for the image.<br><br>If `transparent`, the output format needs to support transparency, so it should be set to either `png` (default value) or `webp`.<br>Possible values: `transparent`, `opaque`, `auto` | No |  |
-| image | string or array |  | Yes |  |
+| image | string or array | The image(s) to edit. Must be a supported image file or an array of images. Each image should be a png, or jpg file less than 50MB. | Yes |  |
 | mask | string |  | No |  |
 | model | string | The model deployment to use for the image edit operation. | Yes |  |
 | n | integer | The number of images to generate. Must be between 1 and 10. | No | 1 |
 | prompt | string | A text description of the desired image(s). The maximum length is 1000 characters for `dall-e-2`, and 32000 characters for `gpt-image-1`. | Yes |  |
 | quality | enum | The quality of the image that will be generated. `high`, `medium` and `low` are only supported for `gpt-image-1`. `dall-e-2` only supports `standard` quality. Defaults to `auto`.<br>Possible values: `standard`, `low`, `medium`, `high`, `auto` | No |  |
-| response_format | enum | The format in which the generated images are returned. Must be one of `url` or `b64_json`. URLs are only valid for 60 minutes after the image has been generated. This parameter is only supported for `dall-e-2`, as `gpt-image-1` will always return base64-encoded images.<br>Possible values: `url`, `b64_json` | No |  |
+| response_format | enum | The format in which the generated images are returned. Must be one of `url` or `b64_json`. <br>Possible values: `url`, `b64_json` | No |  |
 | size | enum | The size of the generated images. Must be one of `1024x1024`, `1536x1024` (landscape), `1024x1536` (portrait), or `auto` (default value) for `gpt-image-1`, and one of `256x256`, `512x512`, or `1024x1024` for `dall-e-2`.<br>Possible values: `256x256`, `512x512`, `1024x1024`, `1536x1024`, `1024x1536`, `auto` | No |  |
 | user | string | A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.  | No |  |
 

articles/ai-foundry/openai/includes/api-versions/new-inference-preview.md

@@ -18,6 +18,17 @@ ms.custom:
 
 This article provides a summary of the latest releases and major documentation updates for Azure OpenAI.
 
+## July 2025 
+
+### GPT-image-1 update (preview)
+
+- Input fidelity parameter: The `input_fidelity` parameter in the image edits API lets you control how closely the model conveys the style and features of the subjects in the original (input) image. This is useful for:
+    - Editing photos while preserving facial features; creating avatars that look like original person across different styles; combining faces from multiple people into one image.
+    - Maintaining brand identity in generated images for marketing assets, mockups, product photography.
+    - E-commerce and fashion, where you need to edit images of outfits or product details without compromising realism.
+
+- Partial image streaming: The image generation and image edits APIs support partial image streaming, where they return images with partially rendered content throughout the image generation process. Display these images to the user to provide earlier visual feedback and show the progress of the image generation operation. 
+
 ## June 2025
 
 

articles/ai-foundry/openai/whats-new.md

@@ -34,7 +34,7 @@ Azure OpenAI processes the following types of data:
 
 - **Prompts and generated content**. Prompts are submitted by the user, and content is generated by the service, via the completions, chat completions, images, and embeddings operations.
 - **Uploaded data**. You can provide your own data for use with certain service features (e.g., [fine-tuning](/azure/ai-services/openai/how-to/fine-tuning?pivots=programming-language-studio), [assistants API](/azure/ai-services/openai/how-to/batch?tabs=standard-input&pivots=programming-language-ai-studio), [batch processing](/azure/ai-services/openai/how-to/batch?tabs=standard-input&pivots=programming-language-ai-studio)) using the Files API or vector store.
-- **Data for stateful entities**. When you use certain optional features of Azure OpenAI service, such as the Threads feature of the [Assistants API](/azure/ai-services/openai/how-to/assistant) and Stored completions, the service creates a data store to persist message history and other content, in accordance with how you configure the feature.
+- **Data for stateful entities**. When you use certain optional features of Azure OpenAI, such as the [Responses API](/azure/ai-services/openai/how-to/responses), the Threads feature of the [Assistants API](/azure/ai-services/openai/how-to/assistant), and Stored completions, the service creates a data store to persist message history and other content, in accordance with how you configure the feature.
 - **Augmented data included with or via prompts**. When you use data associated with stateful entities, the service retrieves relevant data from a configured data store and augments the prompt to produce generations that are grounded with your data. Prompts may also be augmented with data retrieved from a source included in the prompt itself, such as a URL.   
 - **Training & validation data**. You can provide your own training data consisting of prompt-completion pairs for the purposes of [fine-tuning an OpenAI model](/azure/ai-services/openai/how-to/fine-tuning?pivots=programming-language-studio).
 
@@ -44,11 +44,12 @@ The diagram below illustrates how your data is processed. This diagram covers se
 
 1. How the Azure OpenAI Service processes your prompts via inferencing to generate content (including when additional data from a designated data source is added to a prompt using Azure OpenAI on your data, Assistants, or batch processing). 
 1. How the Assistants feature stores data in connection with Messages, Threads, and Runs.  
+1. How the Responses API feature stores data to persist message history.  
 1. How the Batch feature processes your uploaded data. 
 1. How the Azure OpenAI Service creates a fine-tuned (custom) model with your uploaded data. 
 1. How the Azure OpenAI Service and Microsoft personnel analyze prompts and completions (text and image) for harmful content and for patterns suggesting the use of the service in a manner that violates the Code of Conduct or other applicable product terms. 
 
-:::image type="content" source="media\flow.jpg" alt-text="Data flow diagram for the service." lightbox="media\flow.jpg":::
+:::image type="content" source="media\flow-2.jpg" alt-text="Data flow diagram for the service." lightbox="media\flow-2.jpg":::
 
 As depicted in the diagram above, managed customers may [apply to modify abuse monitoring](https://customervoice.microsoft.com/Pages/ResponsePage.aspx?id=v4j5cvGGr0GRqy180BHbR7en2Ais5pxKtso_Pz4b1_xUOE9MUTFMUlpBNk5IQlZWWkcyUEpWWEhGOCQlQCN0PWcu). 
 
@@ -70,9 +71,9 @@ The Azure OpenAI "on your data" feature lets you connect data sources to ground
 
 ### Data storage for Azure OpenAI Service features 
 
-Some Azure OpenAI Service features store data in the service. This data is either uploaded by the customer, using the Files API or vector store, or is automatically stored in connection with certain stateful entities such as the Threads feature of the Assistants API and Stored completions. Data stored for Azure OpenAI Service features: 
+Some Azure OpenAI Service features store data in the service. This data is either uploaded by the customer, using the Files API or vector store, or is automatically stored in connection with certain stateful entities such as the Responses API, the Threads feature of the Assistants API, and Stored completions. Data stored for Azure OpenAI Service features: 
 - Is stored at rest in the Azure OpenAI resource in the customer's Azure tenant, within the same [geography](https://azure.microsoft.com/explore/global-infrastructure/geographies/) as the Azure OpenAI resource; 
-- Is always encrypted at rest with Microsoft’s AES-256-encryption by default, with the option of using a customer managed key (certain preview features may not support customer managed keys).
+- Is always encrypted at rest with Microsoft’s AES-256-encryption by default, with the option of using a customer managed key (certain preview features may not support customer-managed keys). Microsoft-managed keys are always used to ensure baseline encryption for all stored data.
 - Can be deleted by the customer at any time. 
 
 > [!NOTE]
@@ -82,6 +83,7 @@ Stored data may be used with the following service features/capabilities:
 - **Creating a customized (fine-tuned) model**. Learn more about [how fine-tuning works](/azure/ai-services/openai/how-to/fine-tuning?tabs=turbo%2Cpython-new&pivots=programming-language-studio). Fine-tuned models are exclusively available to the customer whose data was used to create the fine-tuned model, are encrypted at rest (when not deployed for inferencing), and can be deleted by the customer at any time. Training data uploaded for fine-tuning is not used to train, retrain, or improve any Microsoft or third party base models. 
 - **Batch processing**. Learn more about [how batch processing works](https://aka.ms/aoai-batch-how-to). Batch processing is a Global deployment type; data stored at rest remains in the designated Azure geography until processing capacity becomes available; processing may occur in any geography where the relevant Azure OpenAI model is deployed (learn more about [region availability of models](/azure/ai-services/openai/concepts/models#model-summary-table-and-region-availability)).   
 - **Assistants API (preview)**. Learn more about [how the Assistants API works](/azure/ai-services/openai/concepts/assistants). Some features of Assistants, such as Threads, store message history and other content.
+- **Responses API (preview)**. Learn more about [how the Responses API works](/azure/ai-services/openai/how-to/responses?tabs=python-secure). This API stores message history and other content related to message history. This is required for multi-turn conversations and workflows. 
 - **Stored completions (preview)**. <!--Learn more about Stored completions. (link)--> Stored completions stores input-output pairs from the customer’s deployed Azure OpenAI models such as GPT-4o through the chat completions API and displays the pairs in the [Azure AI Foundry portal](https://ai.azure.com/). This allows customers to build datasets with their production data, which can then be used for evaluating or fine-tuning models (as permitted in applicable Product Terms).