Actions10
- Audio Actions
- Document Actions
- File Actions
- Image Actions
- Text Actions
- Video Actions
Overview
This node integrates with the Google Gemini API to generate images based on textual prompts. It is designed for scenarios where users want to create AI-generated images dynamically within their workflows, such as generating creative visuals, concept art, or illustrative content from descriptive text.
For example, a marketing team could use this node to automatically generate unique product images from descriptions, or a content creator might generate artwork for blog posts without manual design work.
Properties
| Name | Meaning |
|---|---|
| Server URL | The base URL of the Google Gemini API endpoint (default: https://generativelanguage.googleapis.com). |
| API Key | The API key credential required to authenticate requests to the Google Gemini API. |
| Model | The specific image generation model to use. Can be selected from a list or specified by ID. |
| Prompt | A text description that defines what the generated image should depict. |
| Number of Images | How many images to generate in one request. Note: Not supported by Gemini models, only Imagen models. |
| Put Output in Field | The name of the output field where the binary image data will be stored. |
Output
The node outputs JSON data containing the generated image(s). If configured, the actual image files are provided as binary data under the specified output field name (default "data"). This allows subsequent nodes to access and manipulate the image files directly.
Dependencies
- Requires an active Google Gemini API key for authentication.
- Needs network access to the specified Google Gemini API server URL.
- No additional external dependencies beyond the Google Gemini API.
Troubleshooting
- Invalid API Key or Authentication Errors: Ensure the API key is correct and has permissions for image generation.
- Model Not Supported: Some options like "Number of Images" are not supported by all models; verify model capabilities.
- Network Issues: Confirm the server URL is reachable and no firewall blocks the connection.
- Empty or Invalid Prompt: The prompt must be a meaningful text string describing the desired image; empty prompts may cause errors or no output.