Google Nano Banana 2 Lite Edit API Documentation

Google Nano Banana 2 Lite Edit API Documentation

Playground

Google Nano Banana 2 Lite Edit transforms uploaded images with text instructions, supporting fast prompt-guided image editing, visual refinements, and creative changes with low latency. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Google Nano Banana 2 Lite Edit transforms uploaded images using natural-language instructions with a fast, lightweight image editing model. Upload one or more images, describe the edit you want, choose an aspect ratio and output format, and receive the edited image URL in the standard WaveSpeed prediction response.

Why Choose This?

• Instruction-based image editing
  Edit input images by describing the desired change in natural language.

• Multiple image references
  Provide one or more images to guide the edit workflow.

• Flexible aspect ratios
  Choose common square, portrait, landscape, and wide-format aspect ratio presets.

• Simple editing controls
  The public form focuses on images, prompt, aspect_ratio, and output_format.

• Single-image output
  Each request generates one edited image for predictable cost and behavior.

Parameters

How to Use

1. Upload images — Provide one or more input images for editing.
2. Write your edit prompt — Describe what should change and what should stay the same.
3. Choose aspect ratio — Select a preset, or leave it unset to use the input image’s ratio.
4. Choose output format — Select png or jpeg depending on your workflow.
5. Submit — Generate the edited image and retrieve the output URL.

Pricing

Best Use Cases

• Photo editing — Change backgrounds, style, lighting, mood, or visual details.
• Product visuals — Refine source assets for marketing, ecommerce, and product presentation.
• Creative iteration — Try different edit prompts on the same source images.
• Reference-based edits — Use multiple uploaded images as references for more guided edits.
• Content production — Generate polished edited assets for social media, campaigns, thumbnails, and design workflows.

Pro Tips

• Use clear edit instructions that describe both what should change and what should remain unchanged.
• Upload sharp images with the main subject clearly visible.
• Use multiple images when you need stronger reference guidance.
• Leave aspect_ratio unset to use the input image’s ratio.
• Use png for higher-quality general output.
• Use jpeg for smaller file sizes.

Related Models

• Nano Banana 2 Lite Text-to-Image — Generate images directly from text prompts with Nano Banana 2 Lite.
• Nano Banana 2 Lite Edit — Edit existing images with text instructions using Nano Banana 2 Lite.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "images": [
    "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
  ],
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "aspect_ratio": "1:1",
  "output_format": "png"
}
JSON
)

# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/google/nano-banana-2-lite/edit" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted)
      printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
      printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.

Response Parameters

Result Request Parameters

Result Response Parameters