Images in OpenWebUI

Introduction

Open WebUI lets you generate and edit images right from the chat interface, whether you want to create visual content, generate art, quickly prototype an image, or edit existing pictures without leaving your conversation. By connecting an image generation engine (such as Nano Banana, or GPT Image) through the admin settings, you can enable an image option in the chat and simply describe what you want to generate or change.

❗ Note: the model selected as the chat model MUST be a language model, never the image generation model itself. The image model is configured separately in the admin Images settings and should never be chosen as the active chat model. We will elaborate on the matter in this guide.

---

Prerequisites

Before configuring images in OpenWebUI, ensure you have the following:

• OpenWebUI Environment: Admin access to OpenWebUI running within your secure GLBNXT workspace.
• GLBNXT API Key: Create a GLBNXT API Key to track your embeddings.

---

Configuration

Step 1: Create an API Key

1. Go to GLBNXT API Keys and click on + Create Key.
2. Enter a name, risk level, expiration and select models (make sure to at least include the embedding models).
3. Copy the API Key and store it somewhere safe.

Step 2: Configure 'images' in OpenWebUI

1. Open OpenWebUI, make sure that you log in as an admin.
2. Select the Admin Account, go to Admin Panel > Settings > Images.
3. Lower on the page you will find "Images", toggle Image Generation on.

1. The above page will appear, the Image Generation Engine should stay on Default (Open AI).
2. Use the OpenAI API Base URL: OpenAI-compatible endpoint found in GLBNXT API Keys.
3. Enter the API Key from Step 1 in the API Key field in OpenWebUI.
4. Then paste the model ID of your preferred image generating / editing model. In the example below, we have chosen for nano-banana, but you could also choose gpt-image-2, nano-banana-2, etc.

1. Press Save, your OpenWebUI instance is now ready to generate and edit images.

---

Important Note!

As noted in the introduction, it is important to remember the following about generating images in OpenWebUI:

• Go through this guide and make sure that an image generating model is selected in the Admin Settings under Images.
• After finalizing the configuration, go to your OpenWebUI Chat Interface.

❗ Make sure to select a language model (and not an image generating model).

• Only when a language model is selected you will be able to actually generate and edit images.
• Click on "integrations" (the button with the four small diamonds) and toggle "Image" on.

• Now you are fully enabled to generate and edit images in OpenWebUI.

---

Need help? Contact the GLBNXT support team or ask a GLBNXT agent to walk you through the setup.