Openjutsu API Documentation

Openjutsu API Documentation

Playground

Try it on WaveSpeedAI!

Replace the main person in a video with the character from a single image, keeping the scene, motion and original audio.

Features

OpenJutsu Character Swap replaces the main person in a video with a character from a single image. The scene, camera movement, performance and original audio are kept; only the person changes.


Why Choose This?

  • One image, one swap Provide a source video and a character image. The most prominent person in the video is replaced by the character.

  • Performance preserved Body motion, timing and framing follow the source video, so the result stays in sync with the original sound.

  • Original audio kept The soundtrack of the source video is carried over to the result.

  • Up to 15 seconds The result follows the length of your video, up to 15 seconds. Longer videos use their first 15 seconds.


Parameters

ParameterRequiredDescription
videoYesURL of the source video, at least 2 seconds. Use a single shot with a person visible in the first frame. The result follows its length, up to 15 seconds.
imageYesURL of the character image that replaces the person.
resolutionNoOutput resolution: 480p or 768p. Default: 768p.
seedNoRandom seed for generation. A negative value means a random seed will be used.

Tips

  • Use a source video with one continuous shot and a clearly visible person. Videos without a person are rejected.
  • If several people appear, only the most prominent one is replaced.
  • The result can be slightly shorter than your video (by up to about 10%). Billing follows the length of your video.

Pricing

> Billing duration: The length of your input video is rounded up to whole seconds. The minimum billed duration is 3 seconds; shorter videos are billed as 3 seconds. Videos longer than 15 seconds are billed as 15 seconds, and only their first 15 seconds are used.

The price depends on the billed length and the resolution. The character image adds a flat fee.

ResolutionPrice per secondMax billed length
768p0.20 USD15 s
480p0.10 USD15 s

A flat 0.02 USD is added to every run for the character image.

Billing rules

  • Billed duration = input video length rounded up to whole seconds, clamped to 3-15 seconds.
  • 768p: 0.20 USD per billed second.
  • 480p: half of 768p, 0.10 USD per billed second.
  • Total = billed seconds x rate per second + 0.02 USD.

So, for example:

  • 10 s video at 768p: 10 x 0.20 + 0.02 = 2.02 USD
  • 10 s video at 480p: 10 x 0.10 + 0.02 = 1.02 USD
  • 15 s video at 768p: 15 x 0.20 + 0.02 = 3.02 USD
  • 15 s video at 480p: 15 x 0.10 + 0.02 = 1.52 USD
  • 2 s video at 768p (billed as 3 s): 3 x 0.20 + 0.02 = 0.62 USD
  • 30 s video at 768p (billed as 15 s): 3.02 USD

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'
{
  "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
  "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
  "resolution": "768p"
}
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/wavespeed-ai/openjutsu" \
  -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

Retry temporary errors only while polling, never the submit request. Errors, retries and timeouts

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
videostringYes-URL of the source video. The most prominent person in it is replaced; the scene, motion and original audio are kept. Use a single shot with a person in the first frame. The output follows the video's length, up to 15 seconds.
imagestringYes-URL of the character image that replaces the person.
resolutionstringNo768p480p, 768pOutput resolution. 480p is billed at half the 768p price.
seedintegerNo--The random seed to use for the generation. A negative value means a random seed will be used.

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.statusstringTask status. completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses.
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.statusstringStatus: completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses
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.