image.generate_thumbnail

Operation: image.generate_thumbnail
Category: ai
Tags: ai, youtube, thumbnail, image

Generate a cinematic YouTube thumbnail image using an AI image provider

Runtime

Type: AI Provider (routed via provider registry)
Timeout: 300s
Retries: 3 (ExponentialWithJitter)

Inputs

Name	Type	Required	Default	Description
title	String	Yes	—	Video title to base the thumbnail on
topic	String	No	—	Video topic or niche for visual context
style_prompt	String	No	—	Additional style/visual direction for the thumbnail

Outputs

Name	Type	Description
url	String	URL of the generated thumbnail image
path	String	Local file path if downloaded

Default Configuration

{
  "aspect_ratio": "16:9",
  "height": 720,
  "modality": "image",
  "provider": "fal",
  "width": 1280
}

Usage

TypeScript

import { WorkflowBuilder } from "@fabric-platform/sdk";

const workflow = new WorkflowBuilder("my-workflow")
  .node("image-generate-thumbnail", "ai_invoke", (n) =>
    n.config({
      operation: "image.generate_thumbnail",
      // ... node-specific config
    })
  )
  .build();

Python

from fabric_platform import FabricClient

fabric = FabricClient(api_key="fab_xxx")

wf_id = fabric.upsert_workflow("my-workflow", nodes=[
    {
        "key": "image-generate-thumbnail",
        "kind": "ai_invoke",
    },
])

Rust

use fabric_sdk::FabricClient;

let client = FabricClient::new("http://localhost:3001", api_key)?;

let wf_id = client.upsert_workflow("my-workflow", serde_json::json!({
    "nodes": [{
        "key": "image-generate-thumbnail",
        "kind": "ai_invoke"
    }]
})).await?;

curl

curl -X POST http://localhost:3001/v1/workflow-definitions \
  -H "Authorization: Bearer $FABRIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "my-workflow",
    "nodes": [{
      "key": "image-generate-thumbnail",
      "kind": "ai_invoke"
    }]
  }'