Alibaba Wan 2.7 Image Edit Pro API Documentation

Alibaba Wan 2.7 Image Edit Pro API Documentation

Playground

WAN 2.7 Image Edit Pro performs prompt-driven image editing with multi-image reference support and up to 2K output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Wan 2.7 Image Edit Pro is the professional tier of prompt-driven image editing model, delivering higher-fidelity results for production-grade workflows. Upload one or more reference images, describe the edit in plain language, and get a high-resolution updated image — while preserving the original structure, subject identity, and composition.

Ideal for retouching product shots, high-resolution background swaps, detailed style transfers, and any editing task where maximum output quality matters.

• Looking for a lower-cost option? Try Wan 2.7 Image Edit

Why Choose This?

• Higher resolution output Generate edited images at up to 2048×2048 for print-ready assets, large-format displays, and high-DPI screens.

• Natural-language editing Describe what to change and what to keep — the model follows your intent accurately for common creative workflows.

• Multi-image reference support Upload 1 to 3 input images for style, subject, or background guidance and fusion edits.

• Composition preservation Designed to preserve subject identity, pose, and overall structure while applying localized changes.

• Seed control Fix a seed for repeatable outputs and more consistent iteration across prompt variations.

Parameters

How to Use

1. Upload your image(s) — provide the main image to edit. Add up to 3 images for style or background reference.
2. Write your prompt — describe both what to change and what must stay the same. For example: “Color-match the skirt in Figure 1 according to the colors of the bird in Figure 2, keeping the clothing style and model unchanged.”
3. Set size (optional) — specify output dimensions, or leave empty to match the original image size.
4. Set seed (optional) — fix a seed to make iterations more comparable and reproducible.
5. Submit — preview the output and iterate step by step if needed.

Pricing

Just $0.075 per run.

Best Use Cases

• Product Photography — Retouch and edit product images at high resolution for e-commerce and print.
• Fashion & Apparel — Swap clothing styles, colors, or materials while preserving pose and identity.
• Background Replacement — Change scene environment or mood at high fidelity without affecting the subject.
• Style Transfer — Apply detailed artistic or visual style shifts to an existing image.
• Print & Large Format — Generate edited assets at resolutions suitable for physical print and high-DPI displays.

Pro Tips

• Structure your prompt in two parts: what to change, and what to keep. Example: “Change the jacket to leather, keep the face and pose unchanged.”
• If edits spill into areas you want to preserve, strengthen constraints: “keep the face unchanged”, “keep the background intact”, “do not alter the text.”
• Use a fixed seed to make iterative prompt refinements more comparable across runs.
• If outputs look inconsistent, simplify your prompt and iterate with smaller changes.
• Higher output resolutions will take longer to generate — use the standard model for rapid iteration and Pro for final renders.

Notes

• Both images and prompt are required fields.
• Output size defaults to the original image dimensions if size is not specified.
• Output size range is 512–4096 pixels per dimension, with total pixels between 768×768 and 2048×2048 and aspect ratio between 1:8 and 8:1.

Related Models

• Wan 2.7 Image Edit — Standard version at lower cost for everyday editing needs.
• Wan 2.6 Image Edit — Previous generation Wan image-edit model with a similar prompt-driven workflow.
• Qwen Image Edit — General-purpose AI image editing with strong prompt adherence for everyday creative and product workflows.
• Google Nano Banana Pro Edit — High-fidelity image editing with strong composition preservation and reliable text handling.

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'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "images": [
    "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
  ],
  "seed": -1
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/alibaba/wan-2.7/image-edit-pro" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters