YouTube Cover

• Nano Banana Pro

Examples

Before

After

Before / AfterNano Banana Pro

Bold: Pyra, fully automated

Gemini 3 Pro Image. Pyra's portrait becomes a billboard-bold YouTube thumbnail: face front and centre, a crisp baked "FULLY AUTOMATED" hook, her violet infinity mark as the symbol. One title in, a click-ready 16:9 cover out.

ReproduceOpen

YouTube Cover API

Call this pipeline from your own code. One request dispatches a run; the model is an input field, not a separate endpoint.

import { createClient } from "@pipe2-ai/sdk";

const client = createClient(process.env.PIPE2_TOKEN!);

const { run_pipeline } = await client.RunPipeline({
  pipeline_slug: "youtube-cover",
  input: {
    title: "I Rebuilt My Studio in a Weekend",
  },
});

import asyncio
import os

from pipe2 import Pipe2Client

client = Pipe2Client(token=os.environ["PIPE2_TOKEN"])

run = asyncio.run(client.run_pipeline(
    pipeline_slug="youtube-cover",
    input={
        "title": "I Rebuilt My Studio in a Weekend",
    },
))

client := pipe2.NewClient(os.Getenv("PIPE2_TOKEN"))

input := json.RawMessage(`{
  "title": "I Rebuilt My Studio in a Weekend"
}`)

run, err := pipe2.RunPipeline(context.Background(), client, "youtube-cover", input)
if err != nil {
    log.Fatal(err)
}

pipe2 pipelines run \
  --pipeline youtube-cover \
  --input-json '{"title": "I Rebuilt My Studio in a Weekend"}' \
  --wait

Get an API token →

Parameters

title required

The video title, drives the composition. Write it like a headline: specific, concrete, emotional.

string

description

Optional extra context to shape the visual (channel genre, mood, key scene).

string

style

Art direction preset. bold = saturated and dramatic, minimal = editorial and spacious, clickbait = extreme reaction face, cinematic = teal-orange film still, vlog = warm lifestyle, gaming = neon and motion blur.

boldminimalclickbaitcinematicvloggaming default bold

Use it from an AI agent

Point any MCP client at pipe2 and your agent gets these tools. It finds this pipeline, reads the same schema above, then runs it.

• list_pipelines
• get_pipeline_schema
• run_pipeline
• get_pipeline_run_status
• request_upload

{
  "mcpServers": {
    "pipe2ai": {
      "url": "https://mcp.pipe2.ai/mcp",
      "headers": { "Authorization": "Bearer YOUR_TOKEN" }
    }
  }
}

Full API reference→ MCP setup→ CLI reference→

Frequently Asked Questions