> For the complete documentation index, see [llms.txt](https://notara-1.gitbook.io/notara-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://notara-1.gitbook.io/notara-docs/connectors/replicate.md).

# Replicate

Generate images from text prompts using AI models via Replicate.

## What It Enables

| Tool             | Capability | Description                                             |
| ---------------- | ---------- | ------------------------------------------------------- |
| `generate_image` | `write`    | Generate an image from a text prompt and return its URL |

Supports aspect ratios from 1:1 to 21:9, resolutions up to 4K, and JPG or PNG output. You can also pass reference images to transform or use as input. The tool uses Replicate's async prediction API with automatic polling.

`generate_image` is a `write` capability tool and requires admin approval by default.

## Setup

**Required:** Replicate API token.

**Where to find it:** [replicate.com/account/api-tokens](https://replicate.com/account/api-tokens)

1. In the Notara dashboard, go to **Tools**.
2. Click the **Replicate** tile.
3. In Replicate, go to **Account → API tokens** and create a new token.
4. Paste the token into the credential field and click **Verify & Save**.

Your API token is encrypted at rest with AES-256-GCM.

## Example Prompts

> "Generate a 16:9 hero image of a minimalist office with warm lighting."

> "Create a square logo concept for a fintech startup — clean, dark background."

> "Generate a 4K product mockup using this reference image: \[URL]"