In Admin > Settings > Images, configure AI image generation.
Enable Image Generation
| Setting | Description | Default |
|---|
| Image generation enabled | Image generation feature ON/OFF | Disabled |
Image generation is only exposed to users when enabled as an agent capability.
Supported Engines
Add and manage image generation connections. Multiple engines can be configured simultaneously.
| Engine | Strengths |
|---|
| DALL-E (OpenAI) | OpenAI image generation API |
| Azure OpenAI | Azure gpt-image-1, quality/format/background options supported |
| Gemini | Google Gemini image generation (API Key auth) |
| Vertex AI | Google Vertex AI image generation (OAuth2 token caching) |
Per-Engine Settings
OpenAI / DALL-E
Azure OpenAI
Gemini
Vertex AI
| Setting | Description |
|---|
| API Base URL | OpenAI API Endpoint |
| API Key | API authentication key |
| Model | e.g., dall-e-3 |
| Image size | Default size (e.g., 1024x1024) |
| Setting | Description | Options |
|---|
| API Base URL | Azure OpenAI Endpoint | - |
| API Key | Azure auth key | - |
| Quality | Image quality | auto, low, medium, high |
| Output Format | Output format | png, jpeg, webp |
| Background | Background handling | auto, transparent, opaque |
| Setting | Description |
|---|
| API Key | Google AI Studio API key |
| Model | Gemini image generation model |
| Setting | Description |
|---|
| Project ID | Google Cloud project ID |
| Location | Region |
| Model | Gemini image generation model |
Agent Integration
For image generation to work, all 3 conditions must be met:
- Image generation enabled + engine connected in this tab
- Image generation capability set to Default On or Default Off in agent settings
- User manually toggles image generation in chat (when Default Off)
Image generation operates as an agent Tool. When the AI decides “an image is needed”, it auto-invokes the image generation tool.
