# Generate Image — Leonardo AI

> Generates new images using Leonardo AI's image generation API. See the documentation

- Key: `leonardo_ai-generate-image`
- Type: Action (Write)
- Version: 0.0.3
- App: Leonardo AI (`leonardo_ai`) — https://pipedream.com/apps/leonardo-ai.md
- This page (HTML): https://pipedream.com/apps/leonardo-ai/actions/generate-image
- Hints: open-world
- Source: https://github.com/PipedreamHQ/pipedream/blob/master/components/leonardo_ai/actions/generate-image/generate-image.mjs

## Description

Generates new images using Leonardo AI's image generation API.  [See the documentation](https://docs.leonardo.ai/reference/creategeneration)

## Props

| Prop | Type | Required | Description |
|---|---|---|---|
| `prompt` | `string` | Yes | The text prompt describing the image you want to generate. |
| `modelId` | `string` | No | The model to use for generation. Leave empty to use the default model. Options are loaded from the connected account. |
| `width` | `integer` | Yes | Width of the generated image in pixels. |
| `height` | `integer` | Yes | Height of the generated image in pixels. |
| `numImages` | `integer` | Yes | Number of images to generate (1-8). If either width or height is over 768, must be between 1 and 4. |
| `guidanceScale` | `integer` | No | How closely the model should follow the prompt. Must be between 1 and 20. Higher values = more adherence to prompt. |
| `numInferenceSteps` | `integer` | No | Number of denoising steps. More steps = higher quality but slower generation. |
| `seed` | `integer` | No | Random seed for reproducible generation. Leave empty for random generation. |

## Run it

**MCP**

```ts
import { Client } from "@modelcontextprotocol/sdk/client/index.js"
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js"
import { PipedreamClient } from "@pipedream/sdk"

const pd = new PipedreamClient({
  projectId: process.env.PIPEDREAM_PROJECT_ID!,
  clientId: process.env.PIPEDREAM_CLIENT_ID!,
  clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
  projectEnvironment: "production",
})

const accessToken = await pd.rawAccessToken

const transport = new StreamableHTTPClientTransport(
  new URL("https://remote.mcp.pipedream.net/v3"),
  {
    requestInit: {
      headers: {
        Authorization: `Bearer ${accessToken}`,
        "x-pd-project-id": process.env.PIPEDREAM_PROJECT_ID!,
        "x-pd-environment": "production",
        "x-pd-external-user-id": "{external_user_id}", // any stable ID for this user in your system
        "x-pd-app-slug": "leonardo_ai",
      },
    },
  },
)

const mcp = new Client({ name: "my-agent", version: "1.0.0" })
await mcp.connect(transport)

const { tools } = await mcp.listTools()

// listTools() hands your model this tool's input schema, so it can
// fill the arguments itself:
const result = await mcp.callTool({
  name: "leonardo_ai-generate-image",
  arguments: {
    prompt: "Prompt",
    modelId: "Model",
  },
})
```

**TypeScript**

```ts
import { PipedreamClient } from "@pipedream/sdk"

const pd = new PipedreamClient({
  projectId: process.env.PIPEDREAM_PROJECT_ID!,
  clientId: process.env.PIPEDREAM_CLIENT_ID!,
  clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
  projectEnvironment: "production",
})

const result = await pd.actions.run({
  id: "leonardo_ai-generate-image",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    leonardo_ai: { authProvisionId: "apn_xxxxxxx" },
    prompt: "Prompt",
    modelId: "Model",
  },
})

console.log(result)
```

**cURL**

```bash
curl -X POST https://api.pipedream.com/v1/connect/{project_id}/actions/run \
  -H "Content-Type: application/json" \
  -H "X-PD-Environment: production" \
  -H "Authorization: Bearer {access_token}" \
  -d '{
    "external_user_id": "{external_user_id}",
    "id": "leonardo_ai-generate-image",
    "configured_props": {
      "leonardo_ai": { "authProvisionId": "apn_xxxxxxx" },
      "prompt": "Prompt",
      "modelId": "Model"
    }
  }'
```

---

- App: https://pipedream.com/apps/leonardo-ai.md · All apps: https://pipedream.com/apps