# Google Gemini

> Generate text and images with Google's Gemini AI models.

App · AI Models · 2 actions. Web page: https://docs.lodol.com/docs/integrations/google-gemini

## Actions

### Generate image

Generate an image from a text prompt.

**Inputs**

- Prompt (`prompt`, text, required): The text prompt describing the image to generate
- Model (`model`, text): Which model to use. Defaults to gemini-3.1-flash-image. One of: `gemini-3.1-flash-image` (Nano Banana 2 (highest quality)), `gemini-3.1-flash-lite-image` (Nano Banana Lite (fastest, cheapest)), `gemini-3-pro-image` (Nano Banana Pro). Default: `gemini-3.1-flash-image`.

**Outputs**

- `image_count` (number): Number of images generated
- `images` (list): Base64-encoded generated images

**Example output**

```json
{
  "image_count": 1,
  "images": [
    "base64encodedimagedata..."
  ]
}
```

### Generate text response

Generate a text response using a Gemini model.

**Inputs**

- Prompt (`prompt`, text, required): The text prompt to send to the model
- Model (`model`, text): Which Gemini model to use. Defaults to gemini-3.5-flash. One of: `gemini-3.5-flash` (Gemini 3.5 Flash), `gemini-3.1-flash-lite` (Gemini 3.1 Flash-Lite (faster, lower cost)). Default: `gemini-3.5-flash`.

**Outputs**

- `response_text` (text): The generated text response

**Example output**

```json
{
  "response_text": "This is a sample generated response."
}
```