Fix the image generation docs telling users things that are not true

Users configure ComfyUI correctly, then look for a "Generate Image" button under messages that was removed in v0.7.0, and conclude the integration is broken. The docs made this worse: the usage page claimed native function calling needs no per-chat toggle, when every mode requires it, and no page said what has to be true before an image can be generated at all.

The usage page now lists the real preconditions (global setting, permission, model capability, per-chat Image toggle) and explains what Native and Legacy each do. The ComfyUI page says the button is gone and points there. The troubleshooting checklist gained the same checks.

While in there, corrected what did not match the UI or the code: engine option strings, Base URL and API Key field labels, the Image Prompt Generation location and its Legacy-only scope, image editing being off by default with its own ComfyUI URL and key, the Gemini endpoint method, and the v0.6.44 button removal date.

Author: Classic298

docs/features/chat-conversations/image-generation-and-editing/automatic1111.md

@@ -27,10 +27,10 @@ docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -e AUTOM
 ### Setting Up Open WebUI with AUTOMATIC1111
 
 1. In Open WebUI, navigate to the **Settings** > **Admin** > **Experience** > **Images** menu.
-2. Set the `Image Generation Engine` field to `Default (Automatic1111)`.
-3. In the API URL field, enter the address where AUTOMATIC1111's API is accessible:
+2. Set the `Image Generation Engine` field to `Automatic1111`.
+3. In the `Base URL` field, enter the address where AUTOMATIC1111's API is accessible:
 
-![Screenshot of the Open WebUI Images settings page with Default (Automatic1111) selected and the API URL field highlighted.](/images/image-generation-and-editing/automatic1111-settings.png)
+![Screenshot of the Open WebUI Images settings page configured for AUTOMATIC1111.](/images/image-generation-and-editing/automatic1111-settings.png)
 
 ```txt
 http://<your_automatic1111_address>:7860/

docs/features/chat-conversations/image-generation-and-editing/comfyui.md

@@ -40,11 +40,11 @@ Once you have ComfyUI installed and running, you can connect it to Open WebUI fr
 
 ## Image Prompt Generation
 
-This feature uses a language model to automatically generate more detailed and creative prompts based on your initial input, which can lead to better image results.
+This feature uses a language model to automatically generate more detailed and creative prompts based on your initial input, which can lead to better image results. It only applies to Legacy function calling; in the default Native mode the model writes the prompt itself when it calls the tool.
 
-The **Image Prompt Generation** toggle is located in **Settings > Admin > Experience > Images** under the "Image Generation" section, **before** selecting the image generation engine.
+The **Image Prompt Generation** toggle is located in the **Create Image** section of **Settings > Admin > Experience > Images**.
 
-To customize the prompt template used for generation, go to **Settings > Admin > Experience > Interface > Tasks**.
+To customize the prompt template used for generation, go to **Settings > Admin > Experience > Interface**, in the **Generation** section.
 
 ![Screenshot showing the Image Prompt Generation toggle location in Images settings](/images/image-generation-and-editing/image-prompt-generation-toggle.png)
 
@@ -58,9 +58,9 @@ To customize the prompt template used for generation, go to **Settings > Admin >
     - **Model**: Select the base model to be used for generating the image.
     - **Image Size**: Defines the resolution of the generated image (e.g., 512x512, 1024x1024).
     - **Steps**: The number of sampling steps; higher values can improve image quality but take longer to process.
-    - In the **ComfyUI Base URL** field, enter the address of your running ComfyUI instance (e.g., `http://host.docker.internal:8188/`).
+    - In the **Base URL** field, enter the address of your running ComfyUI instance (e.g., `http://host.docker.internal:8188/`).
     - Click the **refresh icon** (🔄) next to the URL field to verify the connection. A success message should appear.
-    - If your ComfyUI instance requires an API key, enter it in the **ComfyUI API Key** field.
+    - If your ComfyUI instance requires an API key, enter it in the **API Key** field.
 
     ![Screenshot of the Open WebUI Images settings page with ComfyUI selected for image generation.](/images/image-generation-and-editing/comfyui-generation-settings.png)
 
@@ -112,17 +112,22 @@ To customize the prompt template used for generation, go to **Settings > Admin >
 
 ![Screenshot of an image being generated in the chat using ComfyUI.](/images/image-generation-and-editing/comfyui-create-image-in-chat.png)
 
+:::info
+There is no "Generate Image" button underneath messages any more. Generation happens from the chat itself: switch **Image** on in the **Integrations** menu of the message input, then ask for the image. See [Usage](/features/chat-conversations/image-generation-and-editing/usage) for the conditions that have to be met and for the community action that brings the old button back.
+:::
+
 ## Edit Image
 
 Open WebUI also supports image editing through ComfyUI, allowing you to modify existing images.
 
 1. **Navigate to Image Settings:** In Open WebUI, go to the **Settings** > **Admin** > **Experience** > **Images**.
 
 2. **Configure Image Editing:**
-    - Under the **Edit Image** section, set the **Image Edit Engine** to `ComfyUI`.
+    - Under the **Edit Image** section, switch **Image Edit** on. It is off by default, and without it the edit engine is never used.
+    - Set the **Image Edit Engine** to `ComfyUI`.
     - **Model**: Select the model to be used for the editing task.
     - **Image Size**: Specify the desired resolution for the output image.
-    - **ComfyUI Base URL** and **API Key**: These fields are shared with the image generation settings.
+    - **Base URL** and **API Key**: The **Edit Image** section has its own fields for these. They do not fall back to the generation settings, so fill them in even when the same ComfyUI instance serves both.
     - **ComfyUI Workflow**: Upload a separate workflow file specifically designed for image editing tasks. The process is the same as for image generation.
     - **Map Workflow Nodes**: Image editing has five configurable parameters with different defaults than generation:
 
@@ -370,9 +375,9 @@ This section provides a supplementary guide on setting up the FLUX.1 models for
 
 ## Configuring with SwarmUI
 
-SwarmUI utilizes ComfyUI as its backend. In order to get Open WebUI to work with SwarmUI you will have to append `ComfyBackendDirect` to the `ComfyUI Base URL`. Additionally, you will want to setup SwarmUI with LAN access. After aforementioned adjustments, setting up SwarmUI to work with Open WebUI will be the same as the steps for ComfyUI image generation outlined above.
+SwarmUI utilizes ComfyUI as its backend. In order to get Open WebUI to work with SwarmUI you will have to append `ComfyBackendDirect` to the `Base URL`. Additionally, you will want to setup SwarmUI with LAN access. After aforementioned adjustments, setting up SwarmUI to work with Open WebUI will be the same as the steps for ComfyUI image generation outlined above.
 ![Install SwarmUI with LAN Access](https://github.com/user-attachments/assets/a6567e13-1ced-4743-8d8e-be526207f9f6)
 
 ### SwarmUI API URL
 
-The address you will input as the ComfyUI Base URL will look like: `http://<your_swarmui_address>:7801/ComfyBackendDirect`
+The address you will input as the **Base URL** will look like: `http://<your_swarmui_address>:7801/ComfyBackendDirect`

docs/features/chat-conversations/image-generation-and-editing/gemini.mdx

@@ -26,10 +26,10 @@ Alternatively, if you are using Vertex AI, you can create an API key in Google C
 
 1. In Open WebUI, navigate to the **Settings** > **Admin** > **Experience** > **Images** menu.
 2. Set the `Image Generation Engine` field to `Gemini`.
-3. Set the `API Base URL` to `https://generativelanguage.googleapis.com/v1beta`.
+3. Set the `Base URL` to `https://generativelanguage.googleapis.com/v1beta`.
 4. Enter your Google AI Studio [API key](https://aistudio.google.com/api-keys).
-5. Enter the model you wish to use from these [available models](https://ai.google.dev/gemini-api/docs/imagen#model-versions).
-6. Set the image size to one of the available [image sizes](https://ai.google.dev/gemini-api/docs/image-generation#aspect_ratios).
+5. Enter the model you wish to use, either an [Imagen model](https://ai.google.dev/gemini-api/docs/imagen#model-versions) or a [Gemini model](https://ai.google.dev/gemini-api/docs/image-generation).
+6. Set the `Gemini Endpoint Method` to match that model: `predict` for Imagen, `generateContent` for Gemini.
 
 import Tabs from '@theme/Tabs';
 import TabItem from '@theme/TabItem';
@@ -40,63 +40,62 @@ import TabItem from '@theme/TabItem';
   <TabItem value="gemini-3-pro" label="Gemini 3.0 Pro (aka Nano Banana Pro)" default>
 
 **Create Image**
-- **Create Image Model**: `gemini-3-pro-image-preview`
-- **Image Size**: `2816x1536`
-- **Image Prompt Generation**: on
+- **Model**: `gemini-3-pro-image-preview`
+- **Image Size**: (not sent to Gemini, can be left empty)
+- **Image Prompt Generation**: on (Legacy function calling only)
 - **Image Generation Engine**: `Gemini`
-- **Gemini Base URL**: `https://generativelanguage.googleapis.com/v1beta`
-- **Gemini API Key**: Enter your API Key
+- **Base URL**: `https://generativelanguage.googleapis.com/v1beta`
+- **API Key**: Enter your API Key
 - **Gemini Endpoint Method**: `generateContent`
 
 **Edit Image**
+- **Image Edit**: on
 - **Image Edit Engine**: `Gemini`
 - **Model**: `gemini-3-pro-image-preview`
-- **Image Size**: (can be left empty)
-- **Gemini Base URL**: `https://generativelanguage.googleapis.com/v1beta`
-- **Gemini API Key**: Enter your API Key
+- **Image Size**: (not sent to Gemini, can be left empty)
+- **Base URL**: `https://generativelanguage.googleapis.com/v1beta`
+- **API Key**: Enter your API Key
 
 </TabItem>
   <TabItem value="gemini-2.5-flash" label="Gemini 2.5 Flash (aka Nano Banana)">
 
 **Create Image**
-- **Create Image Model**: `gemini-2.5-flash-image`
-- **Image Size**: `2816x1536`
-- **Image Prompt Generation**: on
+- **Model**: `gemini-2.5-flash-image`
+- **Image Size**: (not sent to Gemini, can be left empty)
+- **Image Prompt Generation**: on (Legacy function calling only)
 - **Image Generation Engine**: `Gemini`
-- **Gemini Base URL**: `https://generativelanguage.googleapis.com/v1beta`
-- **Gemini API Key**: Enter your API Key
+- **Base URL**: `https://generativelanguage.googleapis.com/v1beta`
+- **API Key**: Enter your API Key
 - **Gemini Endpoint Method**: `generateContent`
 
 **Edit Image**
+- **Image Edit**: on
 - **Image Edit Engine**: `Gemini`
 - **Model**: `gemini-2.5-flash-image`
-- **Image Size**: (can be left empty)
-- **Gemini Base URL**: `https://generativelanguage.googleapis.com/v1beta`
-- **Gemini API Key**: Enter your API Key
+- **Image Size**: (not sent to Gemini, can be left empty)
+- **Base URL**: `https://generativelanguage.googleapis.com/v1beta`
+- **API Key**: Enter your API Key
 
 </TabItem>
 </Tabs>
 
-![Screenshot of the Open WebUI Images settings page with Gemini selected and the API key, model, and image size fields highlighted.](/images/image-generation-and-editing/gemini-settings.png)
+![Screenshot of the Open WebUI Images settings page with Gemini selected.](/images/image-generation-and-editing/gemini-settings.png)
 
 :::info
 
-This feature appears to only work for models supported with this endpoint: `https://generativelanguage.googleapis.com/v1beta/models/<MODEL_NAME>:predict`.
-This is the OpenAI **BETA** endpoint, which Google provides for experimental OpenAI compatibility.
-
-Google Imagen models use this endpoint while Gemini models use a different endpoint ending with `:generateContent`
+Imagen and Gemini models are served from different endpoints, so **Gemini Endpoint Method** has to match the model you entered.
 
-Imagen model endpoint example:
+Imagen models use `predict`:
 
 - `https://generativelanguage.googleapis.com/v1beta/models/imagen-4.0-generate-001:predict`.
 - [Documentation for Imagen models](https://ai.google.dev/gemini-api/docs/imagen)
 
-Gemini model endpoint example:
+Gemini models use `generateContent`:
 
 - `https://generativelanguage.googleapis.com/v1beta/models/gemini-3-pro-image-preview:generateContent`.
 - [Documentation for Gemini models](https://ai.google.dev/gemini-api/docs/image-generation)
 
-Trying to call a Gemini model, such as `gemini-3-pro-image-preview` would result in an error due to the difference in supported endpoints for Image Generation.
+Leaving the method empty falls back to `predict`, so a Gemini model such as `gemini-3-pro-image-preview` fails until you switch it to `generateContent`.
 
 `400: [ERROR: models/gemini-3-pro-image-preview is not found for API version v1beta, or is not supported for predict. Call ListModels to see the list of available models and their supported methods.]`
 
@@ -107,8 +106,8 @@ Trying to call a Gemini model, such as `gemini-3-pro-image-preview` would result
 Image generation with a LiteLLM proxy using Gemini or Imagen endpoints is supported with Open WebUI. Configure the Image Generation as follows:
 
 1. In Open WebUI, navigate to the **Settings** > **Admin** > **Experience** > **Images** menu.
-2. Set the `Image Generation Engine` field to `Open AI`.
-3. Change the API endpoint URL to `https://<your-litellm-url>:<port>/v1`.
+2. Set the `Image Generation Engine` field to `Default (Open AI)`.
+3. Change the `API Base URL` to `https://<your-litellm-url>:<port>/v1`.
 4. Enter your LiteLLM API key.
 5. The API version can be left blank.
 6. Enter the image model name as it appears in your LiteLLM configuration.

docs/features/chat-conversations/image-generation-and-editing/image-router.md

@@ -16,9 +16,9 @@ Open WebUI also supports image generation through the **Image Router APIs**. Ima
 ### Configuring Open WebUI
 
 1. In Open WebUI, navigate to the **Settings** > **Admin** > **Experience** > **Images** menu.
-2. Set the `Image Generation Engine` field to `Open AI` (Image Router uses the same syntax as OpenAI).
-3. Change the API endpoint URL to `https://api.imagerouter.io/v1/openai`
+2. Set the `Image Generation Engine` field to `Default (Open AI)` (Image Router uses the same syntax as OpenAI).
+3. Change the `API Base URL` to `https://api.imagerouter.io/v1/openai`
 4. Enter your Image Router API key.
 5. Enter the model you wish to use. Do not use the dropdown to select models, enter the model name instead. For more information, [see all models](https://imagerouter.io/models).
 
-![Screenshot of the Open WebUI Images settings page with Open AI selected and the API endpoint URL, API key, and model fields highlighted for Image Router configuration.](/images/image-generation-and-editing/image-router-settings.png)
+![Screenshot of the Open WebUI Images settings page with Open AI selected and the API Base URL, API key and model fields highlighted for Image Router configuration.](/images/image-generation-and-editing/image-router-settings.png)

docs/features/chat-conversations/image-generation-and-editing/lumenfall.md

@@ -17,8 +17,8 @@ Open WebUI also supports image generation through [Lumenfall](https://lumenfall.
 ### Configuring Image Generation
 
 1. In Open WebUI, navigate to the **Settings** > **Admin** > **Experience** > **Images** menu.
-2. Set the `Image Generation Engine` field to `Open AI` (Lumenfall uses the same syntax as OpenAI).
-3. Change the API endpoint URL to `https://api.lumenfall.ai/openai/v1`.
+2. Set the `Image Generation Engine` field to `Default (Open AI)` (Lumenfall uses the same syntax as OpenAI).
+3. Change the `API Base URL` to `https://api.lumenfall.ai/openai/v1`.
 4. Enter your Lumenfall API key.
 5. The API version can be left blank.
 6. Enter the model you wish to use. For example: `gemini-3-pro-image`, `gpt-image-1.5`, or `flux.2-max`. See all available models at [lumenfall.ai/models](https://lumenfall.ai/models).
@@ -32,8 +32,8 @@ Lumenfall also supports image editing through the same API:
 
 1. On the same **Images** settings page, scroll to the **Edit Image** section.
 2. Toggle **Image Edit** to on.
-3. Set the `Image Edit Engine` to `Open AI`.
-4. Enter the same API endpoint URL: `https://api.lumenfall.ai/openai/v1`.
+3. Set the `Image Edit Engine` to `Default (Open AI)`.
+4. Enter the same `API Base URL`: `https://api.lumenfall.ai/openai/v1`.
 5. Enter your Lumenfall API key.
 6. Choose a model that supports editing (e.g. `gpt-image-1.5`).
 

docs/features/chat-conversations/image-generation-and-editing/openai.md

@@ -16,7 +16,7 @@ Open WebUI also supports image generation through the **OpenAI APIs**. This opti
 ### Configuring Open WebUI
 
 1. In Open WebUI, navigate to the **Settings** > **Admin** > **Experience** > **Images** menu.
-2. Set the `Image Generation Engine` field to `Open AI`.
+2. Set the `Image Generation Engine` field to `Default (Open AI)`.
 3. Enter your OpenAI API key.
 4. Choose the model you wish to use. Note that image size options will depend on the selected model:
    - **DALL·E 2**: Supports `256x256`, `512x512`, or `1024x1024` images.
@@ -30,12 +30,12 @@ Open WebUI also supports image generation through the **OpenAI APIs**. This opti
 Image generation with Azure OpenAI (DALL·E or GPT-Image) is supported. Configure the Image Generation as follows:
 
 1. In Open WebUI, navigate to the **Settings** > **Admin** > **Experience** > **Images** menu.
-2. Set the `Image Generation Engine` field to `Open AI` (Azure OpenAI uses the same syntax as OpenAI).
-3. Change the API endpoint URL to `https://<instance-id>.cognitiveservices.azure.com/openai/deployments/<model>/`. Set the instance and model id as you find it in the settings of the Azure AI Foundry.
+2. Set the `Image Generation Engine` field to `Default (Open AI)` (Azure OpenAI uses the same syntax as OpenAI).
+3. Change the `API Base URL` to `https://<instance-id>.cognitiveservices.azure.com/openai/deployments/<model>/`. Set the instance and model id as you find it in the settings of the Azure AI Foundry.
 4. Configure the API version to the value you find in the settings of the Azure AI Foundry.
 5. Enter your Azure OpenAI API key.
 
-![Screenshot of the Open WebUI Images settings page with Open AI selected and the API endpoint URL, API version, and API key fields highlighted for Azure OpenAI configuration.](/images/image-generation-and-editing/azure-openai-settings.png)
+![Screenshot of the Open WebUI Images settings page with Open AI selected and the API Base URL, API version and API key fields highlighted for Azure OpenAI configuration.](/images/image-generation-and-editing/azure-openai-settings.png)
 
 :::tip Azure GPT-Image-1.5 Configuration
 For Azure OpenAI **gpt-image-1.5**, use the following settings for successful generation:
@@ -48,18 +48,18 @@ If you encounter the error `[ERROR: azure-openai error: Unknown parameter: 'resp
 :::
 
 :::tip
-Alternative API endpoint URL tutorial: `https://<endpoint name>.openai.azure.com/openai/deployments/<model name>/` - you can find your endpoint name on https://ai.azure.com/resource/overview, and model name on https://ai.azure.com/resource/deployments.
+Alternative `API Base URL` tutorial: `https://<endpoint name>.openai.azure.com/openai/deployments/<model name>/` - you can find your endpoint name on https://ai.azure.com/resource/overview, and model name on https://ai.azure.com/resource/deployments.
 You can also copy Target URI from your deployment detailed page, but remember to delete strings after model name.
-For example, if your Target URI is `https://test.openai.azure.com/openai/deployments/gpt-image-1/images/generations?api-version=2025-04-01-preview`, the API endpoint URL in Open WebUI should be `https://test.openai.azure.com/openai/deployments/gpt-image-1/`.
+For example, if your Target URI is `https://test.openai.azure.com/openai/deployments/gpt-image-1/images/generations?api-version=2025-04-01-preview`, the `API Base URL` in Open WebUI should be `https://test.openai.azure.com/openai/deployments/gpt-image-1/`.
 :::
 
 ### LiteLLM Proxy with OpenAI Endpoints
 
 Image generation with a LiteLLM proxy using OpenAI endpoints is supported with Open WebUI. Configure the Image Generation as follows:
 
 1. In Open WebUI, navigate to the **Settings** > **Admin** > **Experience** > **Images** menu.
-2. Set the `Image Generation Engine` field to `Open AI`.
-3. Change the API endpoint URL to `https://<your-litellm-url>:<port>/v1`.
+2. Set the `Image Generation Engine` field to `Default (Open AI)`.
+3. Change the `API Base URL` to `https://<your-litellm-url>:<port>/v1`.
 4. Enter your LiteLLM API key.
 5. The API version can be left blank.
 6. Enter the image model name as it appears in your LiteLLM configuration.