Decart Lucy Edit Pro API Documentation

Decart Lucy Edit Pro API Documentation

Playground

Try it on WaveSpeedAI!

Lucy Edit Pro is a state-of-the-art video editing model that produces studio-quality results in minutes, not weeks. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Features

Lucy Edit Pro is a high-end, text-guided video editing model for precise, cinematic transformations. Provide a source video and a natural-language prompt, and the model redraws clothing, style, and scene details frame by frame while preserving motion, timing, and composition. Compared with the Dev edition, Pro prioritizes visual fidelity, temporal stability, and 720p output quality.


What Lucy Edit Pro does

  • Advanced prompt-based video editing Transform outfits, add props, restyle scenes, or change visual themes using simple text instructions.

  • Structure-preserving edits Keeps original camera motion, pacing, and blocking; only the requested elements are modified.

  • High temporal consistency Reduces flicker and frame-to-frame drift, especially on detailed clothing, hair, and accessories.

  • 720p-ready quality Designed for sharper, more detailed output suitable for social content, previews, and concept shots.


Inputs

  • video (required): The source clip to edit. The output duration matches the input duration (up to the maximum supported length).

  • prompt (required): A clear description of the desired edit, for example: “Transform the woman’s outfit into a regal medieval gown with a jeweled crown.” “Turn the kitchen into a futuristic laboratory with glowing panels.”

  • resolution

  • 480p

  • 720p


Pricing

ResolutionPrice per second
480p$0.100
720p$0.150

Maximum supported duration per request: 120 seconds.


How to use

  1. Upload or paste the URL of your source video.
  2. Choose the output resolution (480p for cheaper drafts, 720p for higher quality).
  3. Write a focused prompt describing exactly what should change and what should remain.
  4. Run the model and review the edited clip.
  5. Refine the prompt and rerun to iterate on details such as style, color, or accessories.

Tips for best results

  • Use well-lit, reasonably clean footage; extreme compression and heavy motion blur reduce quality.
  • Keep prompts specific (“Replace her clothes with a red sci-fi pilot suit with metallic details”) rather than vague.
  • When iterating, keep the core prompt stable and only adjust small parts to maintain consistency.

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"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/decart/lucy-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

ParameterTypeRequiredDefaultRangeDescription
promptstringYes-The prompt to edit the video.
videostringYes-The video to translate.
resolutionstringNo720p720p, 480pThe resolution of the video (720p/480p).

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayOutput values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction
data.modelstringModel ID used for the prediction
data.outputsarray<string | object>Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model.
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to poll for the prediction result
data.statusstringStatus: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2026 WaveSpeedAI. All rights reserved.