Atlas Nanobanana Text-to-Image 🍌

Generates images using the AtlasCloud Nanobanana 2 model (google/nano-banana-2/text-to-image).

Token Setup

Before generating images, you need the user's AtlasCloud API token.

• Check memory for atlascloud_token.
• If not found, ask the user: "Please provide your AtlasCloud API token to get started."
• Save the token to memory as atlascloud_token so it is not needed again.

How to Generate an Image

Step 1: Write the params to {baseDir}/params.json.

Step 2: Run the script:

node {baseDir}/generate.js <TOKEN> {baseDir}/params.json

Step 3: In the script output, find the line that starts with IMAGE_URL: between the two rows of = signs:

============================================================
IMAGE_URL: https://atlas-media.oss-us-west-1.aliyuncs.com/images/xxxx.png
============================================================

> ⚠️ CRITICAL: Use exactly the URL that appears in the IMAGE_URL: line of this execution. Never use a URL from the conversation history, previous executions, or memory. Each execution generates a different URL.

Report this URL to the user.

params.json — Payload Correto

> ⚠️ IMPORTANT: Never include media_resolution in the payload — it causes an HTTP 500 error.

{
  "prompt": "descrição detalhada da imagem",
  "aspect_ratio": "16:9",
  "output_format": "png",
  "resolution": "2k",
  "enable_base64_output": false,
  "enable_sync_mode": false,
  "enable_web_search": false,
  "enable_image_search": false
}

Available fields

> NÃO inclua media_resolution — causa erro 500.

Error Handling

Quando usar esta skill

• "Generate an image of..."
• "Create a picture of..."
• "Draw a scene with..."
• "Generate an image of..."
• "Create a photo of..."
• "Create an image with prompt..."