Merge remote-tracking branch 'origin/main'

# Conflicts:
#	MyApp/_pages/ai-server/index.md

Author: Layoric

MyApp/_pages/ai-server/chat.md

@@ -4,6 +4,17 @@ title: AI Server API Usage
 
 AI Server provides a unified API to process requests for AI services to access LLMs, Image Generation, Transcription, and more. The API is designed to be simple to use and easy to integrate into your applications providing many supported languages and frameworks.
 
+## Chat UI
+
+AI Server's Chat UI lets upi send Open AI Chat requests with custom system prompts to any of its active LLMs:
+
+<div class="not-prose">
+<h3 class="text-4xl text-center text-indigo-800 pb-3"><span class="text-gray-300">https://localhost:5006</span>/Chat
+</h3>
+</div>
+
+![](/img/pages/ai-server/uis/Chat.webp)
+
 ## Making a Chat Request
 
 To make a chat request to AI Server, you can use the `/api/OpenAiChatCompletion` endpoint. This endpoint requires a `OpenAiChatCompletion` request DTO that contains a property matching the `OpenAI` API.

MyApp/_pages/ai-server/image-to-image.md

@@ -2,6 +2,18 @@
 title: Image to Image
 ---
 
+## Image to Image UI
+
+AI Server's Image to Image UI lets you create custom Images from a blueprint image from its active Comfy UI Agents:
+
+<div class="not-prose">
+    <h3 class="text-4xl text-center text-indigo-800 pb-3">
+        <span class="text-gray-300">https://localhost:5006</span>/ImageToImage
+    </h3>
+</div>
+
+![](/img/pages/ai-server/uis/ImageToImage.webp)
+
 ## Using Image to Image Endpoints
 
 ::include ai-server/endpoint-usage.md::

MyApp/_pages/ai-server/image-to-text.md

@@ -2,6 +2,18 @@
 title: Image to Text
 ---
 
+## Image to Text UI
+
+AI Server's Image to Text UI lets you request image classifications from its active Comfy UI Agents:
+
+<div class="not-prose">
+    <h3 class="text-4xl text-center text-indigo-800 pb-3">
+        <span class="text-gray-300">https://localhost:5006</span>/ImageToText
+    </h3>
+</div>
+
+![](/img/pages/ai-server/uis/ImageToText.webp)
+
 ## Using Image to Text Endpoints
 
 ::include ai-server/endpoint-usage.md::

MyApp/_pages/ai-server/image-upscale.md

@@ -2,6 +2,18 @@
 title: Image Upscale
 ---
 
+## Image Upscale UI
+
+AI Server's Image Upscale UI lets you use AI to 2x upscale and image from its active Comfy UI Agents:
+
+<div class="not-prose">
+    <h3 class="text-4xl text-center text-indigo-800 pb-3">
+        <span class="text-gray-300">https://localhost:5006</span>/ImageUpscale
+    </h3>
+</div>
+
+![](/img/pages/ai-server/uis/ImageUpscale.webp)
+
 ## Using Image Upscale Endpoints
 
 ::include ai-server/endpoint-usage.md::

MyApp/_pages/ai-server/index.md

@@ -3,28 +3,27 @@ title: Quick Start
 description: Get AI Server up and running quickly
 ---
 
-To get started with AI Server, we need can use the following steps:
+Install AI Server by running [install.sh](https://github.com/ServiceStack/ai-server/blob/main/install.sh):
 
-- **Clone the Repository**: Clone the AI Server repository from GitHub.
-- **Run the Installer**: Run the `install.sh` to set up the AI Server and ComfyUI Agent.
+### 1. Clone the Repository
 
-### Supported OS
+Clone the AI Server repository from GitHub:
 
-The AI Server installer is supported on Linux, macOS, and Windows with WSL2, and all require Docker and Docker Compose to be installed at a minimum.
+```sh
+git clone https://github.com/ServiceStack/ai-server
+```
 
-### Quick Start Commands
+### 2. Run the Installer
 
 ```sh
-git clone https://github.com/ServiceStack/ai-server
 cd ai-server
 cat install.sh | bash
 ```
-### Running the Installer
 
 The installer will detect common environment variables for the supported AI Providers like OpenAI, Google, Anthropic, and others, and prompt ask you if you want to add them to your AI Server configuration.
 
 <div data-asciicinema="/pages/ai-server/ai-server-install.cast" 
-     data-options="{loop:true,poster:'npt:00:08',theme:'dracula',rows:13}"></div>
+     data-options="{loop:true,poster:'npt:00:21',theme:'dracula',rows:13}"></div>
 
 Alternatively, you can specify which providers you want and provide the APIs before continuing with the installation.
 
@@ -40,13 +39,29 @@ You can reset the process by deleting your local `App_Data` directory and rerunn
 
 You will then be able to make requests to the AI Server API endpoints, and access the Admin Portal user interface like the [Chat interface](http://localhost:5005/admin/Chat) to use your AI Provider models.
 
-### Optional ComfyUI Agent
+### Optional - Install ComfyUI Agent
+
+If your server also has a GPU you can ask the installer to also install the [ComfyUI Agent](/ai-server/comfy-extension) locally:
 
-The installer will also ask if you want to install the ComfyUI Agent locally if you run AI server from the installer.
+<div data-asciicinema="https://docs.servicestack.net/pages/ai-server/agent-comfy-install.cast" 
+     data-options="{loop:true,poster:'npt:00:09',theme:'dracula',rows:16}"></div>
 
-If you choose to run AI Server, it will prompt you to install the ComfyUI Agent as well, and assume you want to run it locally.
+The ComfyUI Agent is a separate Docker agent for running [ComfyUI](https://www.comfy.org), 
+[Whisper](https://github.com/openai/whisper) and [FFmpeg](https://www.ffmpeg.org) on servers with GPUs to handle 
+AI Server's [Image](/ai-server/transform/image) and 
+[Video transformations](/ai-server/transform/video) and Media Requests, including:
 
-If you want to run the ComfyUI Agent separately, you can follow these steps:
+- [Text to Image](/ai-server/text-to-image)
+- [Image to Text](/ai-server/image-to-text)
+- [Image to Image](/ai-server/image-to-image)
+- [Image with Mask](/ai-server/image-with-mask)
+- [Image Upscale](/ai-server/image-upscale)
+- [Speech to Text](/ai-server/speech-to-text)
+- [Text to Speech](/ai-server/text-to-speech)
+
+#### Comfy UI Agent Installer
+
+To install the ComfyUI Agent on a separate server (with a GPU), you can clone and run the ComfyUI Agent installer from there instead:
 
 ```sh
 git clone https://github.com/ServiceStack/agent-comfy.git
@@ -62,6 +77,11 @@ These should be the accessible URLs for your AI Server and ComfyUI Agent. When r
 If you want to reset the ComfyUI Agent settings, remember to remove the provider from the AI Server Admin Portal.
 :::
 
+### Supported OS
+
+The AI Server installer is supported on Linux, macOS, and Windows with WSL2, and all require Docker and Docker Compose to be installed at a minimum.
+
+
 ### Prerequisites AI Server - Windows with WSL2
 
 Windows with WSL2 requires the following prerequisites:

MyApp/_pages/ai-server/speech-to-text.md

@@ -4,6 +4,18 @@ title: Speech to Text
 
 AI Server can transcribe audio files to text using the Speech-to-Text provider. This is powered by the Whisper model and is hosted on your own ComfyUI Agent.
 
+## Speech to Text UI
+
+AI Server's Speech to Text UI lets you transcribe audio files from its active Comfy UI Agents:
+
+<div class="not-prose">
+    <h3 class="text-4xl text-center text-indigo-800 pb-3">
+        <span class="text-gray-300">https://localhost:5006</span>/SpeechToText
+    </h3>
+</div>
+
+![](/img/pages/ai-server/uis/SpeechToText.webp)
+
 ## Using Speech to Text Endpoints
 
 ::include ai-server/endpoint-usage.md::

MyApp/_pages/ai-server/text-to-image.md

@@ -2,6 +2,19 @@
 title: Text to Image
 ---
 
+## Text to Image UI
+
+AI Server's Text to Image UI lets send Text to Image requests to any of its active Comfy UI Agents Models, Diffusion
+or DALL·E 3 API Providers:
+
+<div class="not-prose">
+    <h3 class="text-4xl text-center text-indigo-800 pb-3">
+        <span class="text-gray-300">https://localhost:5006</span>/TextToImage
+    </h3>
+</div>
+
+![](/img/pages/ai-server/uis/TextToImage.webp)
+
 ## Using Text to Image Endpoints
 
 ::include ai-server/endpoint-usage.md::

MyApp/_pages/ai-server/text-to-speech.md

@@ -2,8 +2,19 @@
 title: Text to Speech
 ---
 
-## Using Text to Speech Endpoints
+## Text to Speech UI
+
+AI Server's Text to Speech UI lets you create audio files from its active Comfy UI Agents or Open AI Text to Speech models:
+
+<div class="not-prose">
+    <h3 class="text-4xl text-center text-indigo-800 pb-3">
+        <span class="text-gray-300">https://localhost:5006</span>/TextToSpeech
+    </h3>
+</div>
 
+![](/img/pages/ai-server/uis/TextToSpeech.webp)
+
+## Using Text to Speech Endpoints
 
 ::include ai-server/endpoint-usage.md::
 

MyApp/_pages/ai-server/transform/image.md

@@ -5,10 +5,10 @@ description: Processing images with AI Server
 
 AI Server incorporates various image processing capabilities. It wraps some common operations into easier-to-use endpoints, such as:
 
-- **Crop Image**: Crop an image to a specific size.
-- **Convert Image**: Convert an image to a different format.
-- **Scale Image**: Scale an image to a different resolution.
-- **Watermark Image**: Add a watermark to an image.
+- **Crop Image** - Crop an image to a specific size
+- **Convert Image** - Convert an image to a different format
+- **Scale Image** - Scale an image to a different resolution
+- **Watermark Image** - Add a watermark to an image
 
 :::info
 These operations are processed on the AI Server itself, rather than an external API or agent.

MyApp/_pages/ai-server/transform/video.md

@@ -5,11 +5,11 @@ description: Processing videos with AI Server
 
 Also incorporated into the ComfyUI Agent is FFmpeg, which can be used to process videos. AI Server wraps some common operations into easier-to-use endpoints, such as:
 
-- **Crop Video**: Crop a video to a specific size.
-- **Convert Video**: Convert a video to a different format.
-- **Scale Video**: Scale a video to a different resolution.
-- **Watermark Video**: Add a watermark to a video.
-- **Trim Video**: Trim a video to a specific length.
+- **Crop Video** - Crop a video to a specific size
+- **Convert Video** - Convert a video to a different format
+- **Scale Video** - Scale a video to a different resolution
+- **Watermark Video** - Add a watermark to a video
+- **Trim Video** - Trim a video to a specific length
 
 ## Using Video Endpoints