Skip to main content
POST
/
vendors
/
google
/
v1
/
nano-banana-2
/
edit
Image to Image Edit
curl --request POST \
  --url https://api.mulerun.com/vendors/google/v1/nano-banana-2/edit \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data @- <<EOF
{
  "prompt": "Add a small knitted wizard hat on the cat's head, make it look natural",
  "images": [
    "https://example.com/cat_photo.png"
  ],
  "aspect_ratio": "1:1",
  "resolution": "2K"
}
EOF
{
  "task_info": {
    "id": "123e4567-e89b-12d3-a456-426614174000",
    "status": "pending",
    "created_at": "2026-02-27T00:00:00.000Z",
    "updated_at": "2026-02-27T00:00:00.000Z"
  }
}

​
Overview

Nano Banana 2 can restyle or surgically modify a reference image while maintaining global composition. Provide up to 14 reference images (10 object + 4 character) plus a short instruction—Nano Banana 2’s upgraded diffusion backbone keeps lighting, textures, and edge fidelity intact.

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

Image to image edit request body

​
prompt
string
required

Text prompt for image editing. Describe the desired change conversationally.

For adding/removing elements: "Add a wizard hat on the cat's head" For inpainting: "Change only the blue sofa to a brown leather chesterfield" For style transfer: "Transform this photo into Van Gogh's Starry Night style"

​
images
string[]
required

List of reference images for editing. Supports both image URLs and base64-encoded images.

Base64 format: data:image/png;base64,{base64_data}

Supported formats: JPEG, JPG, PNG, BMP, WEBP Max file size per image: 20MB

Nano Banana 2 supports up to 14 reference images:

  • Up to 10 images of objects (high-fidelity preservation)
  • Up to 4 images of characters (character consistency)
Required array length: 1 - 14 elements
​
aspect_ratio
enum<string>
default:1:1

Aspect ratio of the edited image (width:height).

Available options:
1:1,
1:4,
1:8,
2:3,
3:2,
3:4,
4:1,
4:3,
4:5,
5:4,
8:1,
9:16,
16:9,
21:9
​
resolution
enum<string>
default:1K

Output resolution preset.

Note: Must use uppercase K (e.g. 1K, 2K, 4K). Lowercase will be rejected.

Available options:
1K,
2K,
4K
​
web_search
boolean
default:false

Enable Google Search grounding for image editing. When enabled, the model can use Google Search (including Web Search and Image Search) to verify facts and generate imagery based on real-time data such as current weather, stock charts, recent events, or accurate depictions of real-world subjects.

Response

202 - application/json

Accepted - Task created successfully

​
task_info
object