| name | nano-banana-pro |
| description | Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro). Use when you need to: (1) generate images from text descriptions, (2) edit existing images with AI, (3) compose multiple images into one scene. Supports 1K/2K/4K resolutions and up to 14 input images for composition. |
| category | file-generation |
| tags | ["image","ai","gemini","generation","editing"] |
| version | 1.0.0 |
| skillId | skp-ud4d5kijwrf8k18muzmhwv9y |
| workflowId | c-g6emwcpi1wpalsz6j4gyi3d9 |
| installationId | skpi-h9kpmts9ho1kl9l1sohaloeu |
| triggers | ["generate image","edit image","AI image generation","Gemini image","图片生成","AI绘图","编辑图片","文生图","图生图"] |
Nano Banana Pro
Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro). Use when you need to: (1) generate images from text descriptions, (2) edit existing images with AI, (3) compose multiple images into one scene. Supports 1K/2K/4K resolutions and up to 14 input images for composition.
Input
Provide input as JSON:
{
"prompt": "Detailed description for image generation or editing (e.g., 'a cute cat playing in a garden')",
"resolution": "Image resolution: 1K, 2K, or 4K (default: 1K)",
"aspect_ratio": "Image aspect ratio: 16:9, 1:1, 9:16, 5:4, or 4:3 (default: 1:1)",
"input_image": "<file-id>"
}
Note on File Input:
input_image is optional and requires a file ID (format: df-xxxxx)- How to get file ID:
- Upload your image using
refly file upload <file-path>
- Copy the returned file ID from the upload response
- Use this file ID in the input JSON
- Omit
input_image for pure text-to-image generation
- Provide
input_image for image editing or transformation
API Request Structure
This skill uses Gemini 3 Pro Image API with the following structure:
Text-to-Image (Pure Generation)
{
"contents": [{
"parts": [
{"text":
