Alibaba Wan 2.7 Video Edit API Documentation

Alibaba Wan 2.7 Video Edit API Documentation

Playground

WAN 2.7 Video Edit performs prompt-driven video editing with multi-image reference support, supporting 720p/1080p output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Wan 2.7 Video Edit performs prompt-driven editing on existing videos with optional multi-image reference support. Upload a source video, describe the desired edits in natural language, and optionally provide reference images to guide the target style or element appearance — the model applies precise, context-aware edits while preserving motion and temporal consistency throughout the clip.

• Need to extend a video? Try Wan 2.7 Video Extend
• Need to generate from an image? Try Wan 2.7 Image-to-Video

Why Choose This?

• Natural-language video editing Describe your edit in plain text — swap colors, change objects, alter styles — without manual masking or keyframing.

• Multi-image reference support Upload 1 to 9 reference images to guide the target element, style, or appearance in the edited output.

• Audio control Choose between auto mode (model decides) or origin to preserve the original audio track.

• Negative prompt support Specify what to avoid in the edit for more precise control over the output.

• Prompt expansion Enable enable_prompt_expansion to let the model automatically enrich and optimize your prompt before generation.

• Resolution options Generate at 720p or 1080p to match your delivery requirements.

Parameters

How to Use

1. Upload your video — provide the source clip to edit via URL or drag-and-drop.
2. Write your prompt — describe exactly what should change (e.g., “Change the motorcycle’s color to blue.”).
3. Add reference images (optional) — upload images to guide the look of elements or styles in the edit.
4. Add negative prompt (optional) — specify elements you want to exclude from the output.
5. Select resolution — 720p for standard output, 1080p for higher-quality results.
6. Set duration (optional) — leave at 0 to match the input video length, or set 2–10 to trim.
7. Set audio_setting (optional) — choose auto or origin to preserve original audio.
8. Enable prompt expansion (optional) — let the model automatically enrich your prompt.
9. Set seed (optional) — fix the seed to reproduce a specific result in future runs.
10. Submit — generate, preview, and download your edited video.

Pricing

Both the input video and output video are billed by duration.

Billing Rules

• Both the input video and output video are billed.
• 720p: $0.10 per second for input and $0.10 per second for output.
• 1080p: $0.15 per second for input and $0.15 per second for output.
• Minimum billed duration: 2 seconds.
• Maximum billed duration: 10 seconds.
• When duration is 0, billing uses the input video duration, rounded up to a whole second and limited to 2–10 seconds.
• Failed requests are not billed.

Best Use Cases

• Color & Style Changes — Swap object colors, materials, or visual styles across the entire clip.
• Object Replacement — Replace specific elements in the video with different objects or variants.
• Scene Adjustments — Change background mood, lighting, or environment without reshooting.
• E-commerce — Edit product videos to showcase different variants or settings from a single source clip.
• Content Iteration — Rapidly test multiple edit directions on the same source footage.

Pro Tips

• Be specific and descriptive in your prompt — the more detail you provide, the more accurate the edit.
• Upload reference images when you want the model to match a specific target appearance or style.
• Use negative_prompt to prevent edits from bleeding into areas you want to preserve.
• Enable prompt expansion for shorter or less detailed prompts to get richer output automatically.
• Use 720p to test your edit direction before committing to a 1080p final render.

Notes

• Both video and prompt are required fields; all other parameters are optional.
• Billed duration is clamped between 2 and 10 seconds regardless of actual video length.
• Ensure video and image URLs are publicly accessible if using links rather than direct uploads.
• Please ensure your content complies with usage policies.

Related Models

• Wan 2.7 Video Extend — Extend existing videos with last frame control.
• Wan 2.7 Image-to-Video — Animate a reference image into a cinematic video clip.
• Wan 2.7 Text-to-Video — Generate video from text prompts without existing footage.

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",
  "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
  "resolution": "720p",
  "duration": 0,
  "audio_setting": "auto",
  "enable_prompt_expansion": false,
  "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/video-edit" \
  -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