imagesarrayrequired
The URLs of the images to use for image-to-image generation or image editing.
Nano Banana 2 Edit
15% OFF
google/nano-banana-2/editNano Banana 2 is Google's new state-of-the-art image generation and editing model
Try the model
Playground
Input
PNG, JPEG, WebP, or GIF · 20 MiB maximum each
The URLs of the images to use for image-to-image generation or image editing.
The text prompt to generate an image from.
Additional Settings More
Customize your input with more control.
The aspect ratio of the generated image. Leave empty to keep the aspect ratio of the input image. Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16, 4:1, 1:4, 8:1, 1:8.
The format of the generated image. Allowed values: jpeg, png.
The resolution of the image to generate. Allowed values: 0.5K, 1K, 2K, 4K.
Enable Google web search grounding to provide background context for image generation.
Enable Google image search to retrieve web images as visual background reference for generation.
ResultExample
What would you like to do next?
Examples
Select an example to load its inputs and result into the playground.
- Open result ↗
Input
{ "aspect_ratio": "3:2", "images": [ "https://static.sandbase.ai/examples/c260ffa3-a68a-4042-83e9-22e3edc8e209/input/1473477b-62f4-4256-98a0-f5ad17c3b13f.jpg" ], "prompt": "Make a 3 panel comic in a gritty, noir art style with high-contrast black and white inks. Put the character in a humorous scene." }
Human preference
Arena
Elo ratings from blind side-by-side votes, compared with other image and video models.
Rankings sourced from Artificial Analysis Arena
- Leaderboard
- Image Editing
- Rank
- #14 of 77
- Elo
- 1123 ±12
- Gap to #1
- −76
Image-editing arena: people pick the better of two edits of the same image and instruction, without seeing the model names.
- #9Seedream 5.0 Pro1131±13
- #10Muse Image1129±12
- #11MAI-Image-2.51127±13
- #12Krea 3 (Fast)1126±14
- #13MAI-Image-2.5-Pro1123±12
- #14Nano Banana 2 (Gemini 3.1 Flash Image)1123±12
- #15FLUX 3 Image1122±14
- #16GPT Image 1.5 (high)1119±13
- #17Grok Imagine Image 2.01117±13
- #18Nano Banana Pro (Gemini 3 Pro Image)1108±12
Nano Banana 2 Edit
Edit or combine images with Nano Banana 2, Google's fast image model. Send images with an instruction to restyle, retouch, swap objects, or merge several inputs into one scene.
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
images | image URL[], required | — | Images to edit or combine, Image 1, Image 2, … |
prompt | string, required | — | Up to 50,000 characters. |
aspect_ratio | 21:9 / 16:9 / 3:2 / 4:3 / 5:4 / 1:1 / 4:5 / 3:4 / 2:3 / 9:16 / 4:1 / 1:4 / 8:1 / 1:8 | — | Omit to follow the first input image. |
output_format | jpeg / png | png | Output file format. |
resolution | 0.5K / 1K / 2K / 4K | 1K | Sets the per-image rate. |
enable_web_search | boolean | false | Ground the edit in Google Search results. |
enable_image_search | boolean | false | Use image search results as visual references. |
Billing
$0.045 at 0.5K, $0.067 at 1K, $0.101 at 2K, and $0.151 at 4K per image, Google's list price. Input images are not metered. Turning on enable_web_search or enable_image_search adds $0.014 per request (charged once even if both are on).
| Request | 0.5K | 1K | 2K | 4K |
|---|---|---|---|---|
| One image | $0.045 | $0.067 | $0.101 | $0.151 |
Failed runs are not charged.
Prompting
- Say which image is the base and what each other image contributes.
- List what must not change.
Limits
- One output image per request.
Also on SandBase
Other Nano Banana endpoints: google/nano-banana-pro, google/nano-banana-pro/edit, google/nano-banana-2, google/nano-banana-2-lite, google/nano-banana-2-lite/edit.
Start building
Send your first request
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "google/nano-banana-2/edit",
"images": [
"https://ai.google.dev/static/gemini-api/docs/images/man_in_white_glasses.jpg"
],
"prompt": "Make a 3 panel comic in a gritty, noir art style with high-contrast black and white inks. Put the character in a humurous scene.",
"resolution": "1K",
"output_format": "png",
"enable_web_search": false,
"enable_image_search": false
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
status=$(printf '%s' "$result" | jq -r .status)
case "$status" in completed|failed|timeout) break ;; esac
sleep 2
result=$(curl --fail-with-body --silent \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
"https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"2. Authentication
Create a SandBase API key and set it in your server environment. All requests use Bearer authentication.
export SANDBASE_API_KEY="YOUR_API_KEY"Keep the key on your server. Do not expose it in browser code or commit it to a repository.
3. Queue
Submit a request
POST to /v1/run with this model ID and its inputs. The request example above includes submission and polling.
Fetch request status and result
Use the returned run ID to poll until the status is completed, failed or timeout. Read output only after completed.
curl "https://api.sandbase.ai/v1/run/$RUN_ID" \
-H "Authorization: Bearer $SANDBASE_API_KEY"4. Files
Hosted files
Pass a publicly accessible file URL in the model’s image, video or audio field. Supported formats and limits are shown beside each Playground input.
Uploading images
Use the upload or replace control on supported image fields in the Playground. Video URL fields accept a hosted driving video; they do not imply video-upload support.
5. Schema
Input
promptstringrequired
The text prompt to generate an image from.
Default: "Make a 3 panel comic in a gritty, noir art style with high-contrast black and white inks. Put the character in a humurous scene."
resolutionstring
The resolution of the image to generate.
Default: "1K"
Possible values: "0.5K", "1K", "2K", "4K"
aspect_ratiostring
The aspect ratio of the generated image. Leave empty to keep the aspect ratio of the input image.
Possible values: "21:9", "16:9", "3:2", "4:3", "5:4", "1:1", "4:5", "3:4", "2:3", "9:16", "4:1", "1:4", "8:1", "1:8"
output_formatstring
The format of the generated image.
Default: "png"
Possible values: "jpeg", "png"
enable_web_searchboolean
Enable Google web search grounding to provide background context for image generation.
Default: false
enable_image_searchboolean
Enable Google image search to retrieve web images as visual background reference for generation.
Default: false
{
"model": "google/nano-banana-2/edit",
"images": [
"https://ai.google.dev/static/gemini-api/docs/images/man_in_white_glasses.jpg"
],
"prompt": "Make a 3 panel comic in a gritty, noir art style with high-contrast black and white inks. Put the character in a humurous scene.",
"resolution": "1K",
"output_format": "png",
"enable_web_search": false,
"enable_image_search": false
}Output
A completed run exposes its result in output. The following is the model’s saved example, not a new generation.
[
{
"source": "Google AI for Developers",
"source_url": "https://ai.google.dev/gemini-api/docs/image-generation",
"url": "https://static.sandbase.ai/examples/c260ffa3-a68a-4042-83e9-22e3edc8e209/output/6ef1e332-af29-43c9-82db-b612324ca650.jpg"
}
]