update steps and delete unnecessary screenshots

msakande · msakande · commit 70eae42183a7 · 2025-09-23T17:43:01.000-05:00
diff --git a/articles/ai-foundry/concepts/concept-playgrounds.md b/articles/ai-foundry/concepts/concept-playgrounds.md
@@ -26,9 +26,9 @@ Some highlights of the Azure AI Foundry playgrounds experience include:
 
 - **AgentOps support** for Evaluations and Tracing in the **Agents playground.**
 - **Open in VS Code** for Chat and Agents playground. This feature saves you time by automatically importing your endpoint and key from Azure AI Foundry to VS Code for multilingual code samples.
-- **Images Playground 2.0** for [gpt-image-1](https://ai.azure.com/explore/models/gpt-image-1/version/2025-04-15/registry/azure-openai/?cid=learnDocs), [Stable Diffusion 3.5 Large](https://ai.azure.com/explore/models/Stable-Diffusion-3.5-Large/version/1/registry/azureml-stabilityai/?cid=learnDocs), and [Bria 2.3 Fast](https://ai.azure.com/explore/models/Bria-2.3-Fast/version/1/registry/azureml-bria/?cid=learnDocs) models.
-- **Audio playground** for [gpt-4o-audio](https://ai.azure.com/explore/models/gpt-4o-transcribe/version/2025-03-20/registry/azure-openai/?cid=learnDocs), [gpt-4o-transcribe](https://ai.azure.com/explore/models/gpt-4o-transcribe/version/2025-03-20/registry/azure-openai/?cid=learnDocs), and [gpt-4o-mini-tts](https://ai.azure.com/explore/models/gpt-4o-mini-tts/version/2025-03-20/registry/azure-openai/?cid=learnDocs) models.
-- **Video playground** for Azure OpenAI Sora.
+- **Images Playground 2.0** for models such as [gpt-image-1](https://ai.azure.com/explore/models/gpt-image-1/version/2025-04-15/registry/azure-openai/?cid=learnDocs), [Stable Diffusion 3.5 Large](https://ai.azure.com/explore/models/Stable-Diffusion-3.5-Large/version/1/registry/azureml-stabilityai/?cid=learnDocs), [Bria 2.3 Fast](https://ai.azure.com/explore/models/Bria-2.3-Fast/version/1/registry/azureml-bria/?cid=learnDocs), and [FLUX.1-Kontext-pro](https://ai.azure.com/resource/models/Flux.1-Kontext-pro/version/1/registry/azureml-blackforestlabs/?cid=learnDocs) models.
+- **Audio playground** for models such as [gpt-4o-audio-preview](https://ai.azure.com/resource/models/gpt-4o-audio-preview/version/2024-12-17/registry/azure-openai/?cid=learnDocs), [gpt-4o-transcribe](https://ai.azure.com/explore/models/gpt-4o-transcribe/version/2025-03-20/registry/azure-openai/?cid=learnDocs), and [gpt-4o-mini-tts](https://ai.azure.com/explore/models/gpt-4o-mini-tts/version/2025-03-20/registry/azure-openai/?cid=learnDocs) models.
+- **Video playground** for [Azure OpenAI Sora](https://ai.azure.com/resource/models/sora/version/2025-05-02/registry/azure-openai/?cid=learnDocs).
 
 :::image type="content" source="../media/concept-playgrounds/playground-landing-page.png" alt-text="Screenshot of the Azure AI Foundry playground landing page showcasing features for rapid prototyping and experimentation. The left pane of the portal has been customized to show the Playgrounds tab." lightbox="../media/concept-playgrounds/playground-landing-page.png":::
 
@@ -57,35 +57,35 @@ Available on the multilingual sample code samples, **Open in VS Code** automatic
 To use the **Open in VS Code** functionality from the chat and agents playgrounds, follow these steps:
 
 1. Select **Try the Chat playground** to open it. Alternatively, you can follow these steps in the Agents playground by selecting **Let's go** on the Agents playground card.
+
 1. If you don't have a deployment already, select **Create new deployment** and deploy a model such as `gpt-4o-mini`.
+
 1. Make sure your deployment is selected in the Deployment box.
+
 1. Select **View code** to see the code sample.
-1. Select **Open in VS Code** to open VS Code in a new tab of your browser window.
 
-    :::image type="content" source="../media/concept-playgrounds/open-in-vs-code-foundry.png" alt-text="Screenshot showing the Open in VS Code button in Azure AI Foundry playground for seamless code integration." lightbox="../media/concept-playgrounds/open-in-vs-code-foundry.png":::
+1. Select **Open in VS Code** to open VS Code in a new tab of your browser window.
 
 1. You're redirected to the `/azure` environment of VS Code where your code sample, API endpoint, and key are already imported from the Azure AI Foundry playground.
-    
-    :::image type="content" source="../media/concept-playgrounds/open-in-vs-code-vscode.png" alt-text="Screenshot of the VS Code environment showing imported code sample, API endpoint, and key from the Azure AI Foundry playground." lightbox="../media/concept-playgrounds/open-in-vs-code-vscode.png":::
 
-1. Browse the `README.md` file for instructions to run your model.
+1. Browse the `INSTRUCTIONS.md` file for instructions to run your model.
+
 1. View your code sample in the `run_model.py` file.
+
 1. View relevant dependencies in the `requirements.txt` file.
 
 
 ## Agents playground
 
-The agents playground lets you explore, prototype, and test agents without running any code. From this page, you can quickly iterate and experiment with new ideas. To get started with the Agents playground, see the [Quickstart: Create a new agent](../../ai-services/agents/quickstart.md).
+The agents playground lets you explore, prototype, and test agents without running any code. From this page, you can quickly iterate and experiment with new ideas. To get started with the agents playground, see the [Quickstart: Create a new agent](../../ai-services/agents/quickstart.md).
 
-:::image type="content" source="../media/concept-playgrounds/agents-playground.png" alt-text="Screenshot of the agents playground interface for exploring, prototyping, and testing agents without code." lightbox="../media/concept-playgrounds/agents-playground.png":::
 
 ## Chat playground
 
-The chat playground is the place to test the latest reasoning models from Azure OpenAI, DeepSeek, and Meta. To learn more about the chat playground, see the [Quickstart: Use the chat playground in Azure AI Foundry portal](../quickstarts/get-started-playground.md).
+The chat playground is the place to test the latest reasoning models from Azure OpenAI, DeepSeek, and Meta. To learn more about the chat playground, see the [Quickstart: Get answers in the chat playground](../quickstarts/get-started-playground.md).
 
 For all reasoning models, the chat playground provides a chain-of-thought summary drop-down that lets you see how the model thinks through its response before sharing the output.
 
-:::image type="content" source="../media/concept-playgrounds/chat-playground-cot-summary.png" alt-text="Screenshot of the Chat playground interface for exploring, prototyping, and testing chat models without code." lightbox="../media/concept-playgrounds/chat-playground-cot-summary.png":::
 
 ## Audio playground
 
@@ -94,35 +94,42 @@ The audio playground (preview) lets you use text-to-speech and transcription cap
 To try the text-to-speech capability, follow these steps:
 
 1. Select **Try the Audio playground** to open it.
+
 1. If you don't have a deployment already, select **Create new deployment** and deploy a model such as `gpt-4o-mini-tts`.
+
 1. Make sure your deployment is selected in the Deployment box.
+
 1. Input a text prompt.
+
 1. Adjust model parameters such as voice and response format.
+
 1. Select **Generate** to receive a speech output with playback controls that include play, rewind, forward, adjust speed, and volume.
-1. Download the audio file to your local computer.
 
-    :::image type="content" source="../media/concept-playgrounds/audio-playground-text-to-speech.png" alt-text="Screenshot of the Audio playground interface showcasing text-to-speech capabilities with playback controls." lightbox="../media/concept-playgrounds/audio-playground-text-to-speech.png":::
+1. Download the audio file to your local computer.
 
 To try the transcription capability, follow these steps:
 
 1. If you don't have a deployment already, select **Create new deployment** and deploy a model such as `gpt-4o-transcribe`.
+
+1. Make sure your deployment is selected in the Deployment box. 
+
 1. (Optional) Include a phrase list as a text mechanism to guide your audio input.
+
 1. Input an audio file, by either uploading one or recording the audio from the prompt bar.
-1. Select **Generate transcription** to send the audio input to the model and receive a transcribed output in both text and JSON formats.
 
-    :::image type="content" source="../media/concept-playgrounds/audio-playground-transcribe.png" alt-text="Screenshot of the Audio playground interface demonstrating transcription output from audio input." lightbox="../media/concept-playgrounds/audio-playground-transcribe.png":::
+1. Select **Generate transcription** to send the audio input to the model and receive a transcribed output in both text and JSON formats.
 
 
 ## Video playground
 
 The video playground (preview) is your rapid iteration environment for exploring, refining, and validating generative video workflows. It's designed for developers who need to go from idea to prototype with precision, control, and speed. The playground gives you a low-friction interface to test prompt structures, assess motion fidelity, evaluate model consistency across frames, and compare outputs across models—without writing boilerplate or wasting compute cycles. It's also a great demo interface for your chief product officer and engineering VP.
 
-All model endpoints are integrated with **Azure AI Content Safety**. As a result, harmful and unsafe images are filtered out before they appear in the video playground. If content moderation policies flag your text prompt or video generation, you get a warning notification.
+All model endpoints are integrated with **Azure AI Content Safety**. As a result, the video playground filters out harmful and unsafe images before they appear. If content moderation policies flag your text prompt or video generation, you get a warning notification.
 
 You can use the video playground with the **Azure OpenAI Sora** model.
 
 > [!TIP]  
-> See the [60-second reel of the video playground for Azure OpenAI Sora](https://aka.ms/VideoPlaygroundReel) and the DevBlog for how to transform your [enterprise-ready use case by industry](https://aka.ms/VideoPlaygroundDevBlog).
+> See the DevBlog for [Go from prompt to playback with Sora from Azure OpenAI in the video playground in Azure AI Foundry](https://devblogs.microsoft.com/foundry/sora-in-video-playground/).
 
 Follow these steps to use the video playground:
 
@@ -131,20 +138,18 @@ Follow these steps to use the video playground:
 
 1. Select **Try the Video playground** to open it.
 1. If you don't have a deployment already, select **Deploy now** from the top right side of the homepage and deploy the `sora` model.
-1. On the homepage of the video playground, get inspired by **pre-built prompts** sorted by the **industry** filter. From here, you can view the videos in full display and copy the prompt to build from it.
-
-    :::image type="content" source="../media/concept-playgrounds/video-playground-copy-prompt.png" alt-text="Screenshot of the video playground highlighting the Use prompt button to copy a prompt." lightbox="../media/concept-playgrounds/video-playground-copy-prompt.png":::
+1. On the homepage of the video playground, get inspired by **pre-built prompts** sorted by the **industry** filter. From here, you can view the videos in full display and copy the prompt from the bottom right corner of a video to build from it.
 
-1. Copying the prompt pastes it in the prompt bar. Adjust key controls (for example, aspect ratio or resolution) to deeply understand specific model responsiveness and constraints.
+1. Copy the prompt to paste it in the prompt bar. Adjust key controls (for example, aspect ratio or resolution) to deeply understand specific model responsiveness and constraints.
 1. Select **Generate** to generate a video based on the copied prompt.
-1. Rewrite your text prompt syntax with gpt-4o using **Re-write with AI**. 
+1. Rewrite your text prompt syntax with gpt-4o by using **Re-write with AI**. 
 1. Switch on the **Start with an industry system prompt** capability, choose an industry, and specify the change required for your original prompt.
 1. Select **Update** to update the prompt, and then select **Generate** to create a new video.
 
     :::image type="content" source="../media/concept-playgrounds/video-playground-rewrite-prompt-with-ai.png" alt-text="Screenshot showing the controls used to rewrite a prompt with AI and generate an updated image." lightbox="../media/concept-playgrounds/video-playground-rewrite-prompt-with-ai.png":::
 
-1. Go to the **Generation history** tab to review your generations as a grid or list view. When you select the videos, open them in full screen mode for full immersion. Visually observe outputs across prompt tweaks or parameter changes.
-1. In full screen mode, edit the prompt and submit for regeneration.
+1. Go to the **Generation history** tab to review your generations as a grid or list view. When you select the videos, you open them in full screen mode for full immersion. Visually observe outputs across prompt tweaks or parameter changes.
+1. In full screen mode, edit the prompt and submit it for regeneration.
 1. Either in full screen mode or through the options button that shows up when you hover across the video, download the videos to your local computer, view the video generation information tag, view code, or delete the video.
 
     :::image type="content" source="../media/concept-playgrounds/options-menu-for-generated-video.png" alt-text="Screenshot showing the options button for downloading, viewing details, and deleting a generated image." lightbox="../media/concept-playgrounds/options-menu-for-generated-video.png":::
@@ -189,22 +194,32 @@ When you use the video playground to plan your production workload, explore and
 The images playground is ideal for developers who build image generation flows. This playground is a full-featured, controlled environment for high-fidelity experiments designed for model-specific APIs to generate and edit images.
 
 > [!TIP]  
-> See the [60-second reel of the Images playground for gpt-image-1](https://youtu.be/btA8njJjLXY) and our DevBlog for how to transform your [enterprise-ready use case by industry.](https://devblogs.microsoft.com/foundry/images-playground-may-2025/)
+> See the [60-second reel of the Images playground for gpt-image-1](https://youtu.be/btA8njJjLXY) and our DevBlog for how to transform your [Rapidly prototype with gpt-image-1 from Azure OpenAI Service in the Images Playground in Azure AI Foundry.](https://devblogs.microsoft.com/foundry/images-playground-may-2025/)
 
 You can use the images playground with these models:
 
 - [gpt-image-1](https://ai.azure.com/explore/models/gpt-image-1/version/2025-04-15/registry/azure-openai) from Azure OpenAI.
 - [Stable Diffusion 3.5 Large](https://ai.azure.com/explore/models/Stable-Diffusion-3.5-Large/version/1/registry/azureml-stabilityai), [Stable Image Core](https://ai.azure.com/explore/models/Stable-Image-Core/version/1/registry/azureml-stabilityai), [Stable Image Ultra](https://ai.azure.com/explore/models/Stable-Image-Ultra/version/1/registry/azureml-stabilityai) from Stability AI.
 - [Bria 2.3 Fast](https://ai.azure.com/explore/models/Bria-2.3-Fast/version/1/registry/azureml-bria) from Bria AI.
+- [dall-e-3](https://ai.azure.com/resource/models/dall-e-3/version/3.0/registry/azure-openai/?cid=learnDocs)
+- [FLUX.1-Kontext-pro](https://ai.azure.com/explore/models/FLUX.1-Kontext-pro/version/1/registry/azureml-blackforestlabs/?cid=learnDocs) and [FLUX-1.1-pro](https://ai.azure.com/explore/models/FLUX-1.1-pro/version/1/registry/azureml-blackforestlabs/?cid=learnDocs) from Black Forest Labs.
 
 Follow these steps to use the images playground:
 
 1. Select **Try the Images playground** to open it.
+
 1. If you don't have a deployment already, select **Create new deployment** and deploy a model such as `gpt-image-1`.
-1. **Start with a pre-built text prompt**: Select an option to get started with a prebuilt text prompt that automatically fills the prompt bar.
+
+1. **Start with a sample text prompt**: Select an option to get started with a prebuilt text prompt that automatically fills the prompt bar.
+
 1. **Explore the model API-specific generation controls after model deployment:** Adjust key controls (for example, number of variants, quality, strength) to deeply understand specific model responsiveness and constraints.
+
+1. Select **Generate**.
+
 1. **Side-by-side observations in grid view:** Visually observe outputs across prompt tweaks or parameter changes.
+
 1. **Transform with API tooling:** Inpainting with text transformation is available for gpt-image-1. Alter parts of your original image with inpainting selection. Use text prompts to specify the change.
+
 1. **Port to production with multi-lingual code samples:** Use Python, Java, JavaScript, C# code samples with "View Code". Images playground is your launchpad to development work in VS Code.
 
 ### What to validate when experimenting in images playground
