Decart Lucy Restyle

Decart Lucy Restyle

Playground

Lucy-Restyle is a state-of-the-art text-guided video editing model that transforms videos while preserving original motion, camera angles, and temporal consistency. Edit videos with natural language prompts. Ready-to-use REST inference API, ultra-fast processing, studio-grade quality.

Features

Lucy Edit Dev is a state-of-the-art text-guided video editing model. Give it a source video and a short prompt, and it will transform the content while preserving timing, camera motion, and overall composition.

What Lucy Edit Dev can do

• Prompt-based video editing Change clothing, add or remove objects, alter styles, or adjust scene appearance using natural language instructions.

• Structure-preserving edits Keeps original framing, motion, and pacing while modifying only the requested elements.

• High temporal consistency Edits stay stable across frames, avoiding heavy flicker or “teleporting” artifacts.

• Fast turnaround Optimized for quick responses so you can try multiple prompts and versions in minutes, not hours.

Inputs

• video (required) The source clip to edit. The output duration matches the input duration (subject to platform limits).

• prompt (required) A concise description of the desired edit, such as: “Turn the city into a futuristic neon metropolis” “Replace all cars with horse-drawn carriages” “Dress the people in medieval armor”

Pricing

• Price per second: $0.030

How to use

1. Upload or paste the URL of your source video.
2. Write a clear prompt describing what should change and what should stay the same.
3. Click Run.
4. Preview the edited clip; if needed, tweak the prompt and re-run to iterate quickly.

Tips for best results

• Keep prompts focused and specific (“Add light snowfall and winter coats” is better than “Make it different”).
• Use reasonably clear, well-lit footage; very dark or heavily compressed videos reduce edit quality.
• When refining a look, keep the core prompt and only adjust small details to get consistent outcomes.

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"
}
JSON
)

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