Bytedance Dreamactor V2 API Documentation

Bytedance Dreamactor V2 API Documentation

Playground

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

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

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 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|deleted) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters