LetzAI ACTION
Create Image Edit
Creates an image edit task that modifies an existing image using inpainting or outpainting in LetzAI. See the documentation
- Action
- Writes data
- Destructive
- API key
- SDK
- MCP
IMPLEMENTATION
Call this tool
Connect a user's LetzAI account once, then configure and run Create Image Edit from your backend or agent.
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: "letzai-create-image-edit",
externalUserId: "{external_user_id}", // any stable ID for this user in your system
configuredProps: {
letzai: { authProvisionId: "apn_xxxxxxx" },
mode: "Mode",
originalImageCompletionId: "Original Image Completion ID",
},
})
console.log(result)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": "letzai-create-image-edit",
"configured_props": {
"letzai": { "authProvisionId": "apn_xxxxxxx" },
"mode": "Mode",
"originalImageCompletionId": "Original Image Completion ID"
}
}'// accessToken: mint a short-lived token with the Connect SDK — see the MCP guide
const transport = new StreamableHTTPClientTransport(
new URL("https://remote.mcp.pipedream.net/v3"),
{
requestInit: {
headers: {
Authorization: `Bearer ${accessToken}`,
"x-pd-project-id": "{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": "letzai",
},
},
},
)
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: "letzai-create-image-edit",
arguments: {
mode: "Mode",
originalImageCompletionId: "Original Image Completion ID",
},
})SCHEMA
Inputs
Pipedream supplies the connected account. Your application provides the operation-specific values below. Dynamic inputs are resolved against that user's account.
| Property | Type | Description |
|---|---|---|
mode Mode | string | The Editing Mode. Can be 'in' for Inpainting (modify within image) or 'out' for Outpainting (extend image) Required |
originalImageCompletionId Original Image Completion ID | string | The ID of the original image completion used for editing Optional |
imageUrl Image URL | string | The URL to the image you want to edit Optional |
prompt Prompt | string | Text description of the desired modifications Optional |
mask Mask | string | Base64 encoded image mask (required for inpainting) Optional |
width Width | integer | The width of the image Optional |
height Height | integer | The height of the image Optional |
imageCompletionsCount Image Completions Count | integer | Number of variations to generate Optional |
settings Settings | object | Required for Outpainting. Format: {'panControls': {'up': false, 'right': false, 'down': false, 'left': false}, 'zoomSize': 1.5} Optional |
webhookUrl Webhook URL | string | Optional URL to receive a POST notification when upscale is complete Optional |
REFERENCE
Tool details
Behavior hints are published with the component in the Pipedream registry and surface as MCP tool annotations, so an agent can reason about a tool before it calls it.
- Registry key
- letzai-create-image-edit
- Version
- 0.0.2
- App
- LetzAI
- Authentication
- API key
- Read-only
- No
- Destructive
- Yes
- Open world
- Yes
- Source
- View on GitHub ↗