Bytedance Dreamactor V2

Bytedance Dreamactor V2

Playground

Try it on WaveSpeedAI!

DreamActor V2 transfers motion from a driving video to characters in an image. Great performance for non-human and multiple characters. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

DreamActor V2 is advanced motion transfer model that animates any character image using a driving video. Upload a portrait or character image and a reference video — the model makes your character perform the same movements, expressions, and gestures as the person in the driving video.


Why Choose This?

  • Motion transfer Transfer movements, expressions, and gestures from a driving video to any character image.

  • Any character Works with photos, illustrations, anime characters, or any portrait-style image.

  • Expression capture Accurately captures facial expressions, head movements, and body gestures.

  • Natural animation Generates smooth, realistic motion that matches the driving video timing.

  • Simple workflow Just two inputs — an image and a video — no complex setup required.


Parameters

ParameterRequiredDescription
imageYesCharacter image to animate (URL or upload)
videoYesDriving video with movements to transfer (URL or upload)

How to Use

  1. Upload your character image — provide a portrait or character image to animate.
  2. Upload your driving video — provide a video with the movements you want to transfer.
  3. Run — submit and download the animated video.

Pricing

Video DurationCost
1 second$0.05
5 seconds$0.25
10 seconds$0.50
30 seconds$1.50

Billing Rules

  • Rate: $0.05 per second of driving video
  • Total cost = video duration × $0.05

Best Use Cases

  • Virtual Avatars — Create animated avatars that mirror real human movements.
  • Content Creation — Make characters or illustrations come to life with realistic motion.
  • Digital Humans — Generate expressive digital human videos for marketing or entertainment.
  • Social Media — Create engaging character animations for viral content.
  • Gaming & Entertainment — Animate game characters or mascots with real motion capture.

Pro Tips

  • Use a clear, front-facing character image for best results.
  • The driving video should have clear, visible movements and expressions.
  • Ensure good lighting in the driving video for accurate motion capture.
  • Shorter driving videos are faster to process and more cost-effective for testing.
  • Use videos with a single person and minimal background movement.

Notes

  • Both image and video are required fields.
  • Billing is based on the duration of the driving video.
  • Ensure uploaded URLs are publicly accessible.

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'
{
  "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
  "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/bytedance/dreamactor-v2" \
  -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
imagestringYes-Reference image (JPEG/PNG). Max 4.7MB. Resolution: 480x480 to 1920x1080.
videostringYes-Driving video (MP4/MOV/WebM). Max 30 seconds. Resolution: 200x200 to 2048x1440.
enable_sync_modebooleanNofalse-If set to `true`, the request attempts to wait for the generated result and return outputs in the same response. If the result is not ready within the sync wait window, the API can return a timeout body while the task continues processing. This option is only available via the API and is supported only by some models.
enable_base64_outputbooleanNofalse-If set to `true`, the prediction's `output` strings are returned as **naked base64** (no `data:<mime>;base64,` prefix). When `false` (default), outputs are returned as URLs pointing to our CDN.

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.