Steady Dancer

Steady Dancer

Playground

SteadyDancer is a 14B-parameter human image animation framework that transforms static images into coherent dance videos. Features first-frame preservation, robust identity consistency, and temporal coherence for realistic motion generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Steady Dancer is WaveSpeedAI’s motion-transfer model: you upload a character image and a driving video, and it generates a new clip where your character follows the motion from the video while keeping a stable face, outfit, and overall identity. Ideal for dance edits, cosplay previews, and social short-form content.

What is SteadyDancer?

SteadyDancer is a 14-billion parameter human image animation framework that converts static images into coherent dance motion videos. Built on diffusion models, it uses an Image-to-Video paradigm with key innovations for high-quality animation.

✨ Highlights

• Image-driven identity – Uses your uploaded image as the main reference for face, outfit, and body shape.
• Video-driven motion – Copies camera movement and body motion from the driving video.
• Stability-focused – Designed to keep faces, limbs, and outfit details consistent across frames.
• Resolution choices – Output at 480p for quick previews or 720p for higher-quality clips.
• Prompt-guided style (optional) – Add a short text prompt to nudge colour, atmosphere, or style, or leave blank for neutral transfer.

🧩 Parameters

• image* – Required. The character / subject image to insert into the motion.
• video* – Required. Driving video whose motion and camera you want to reuse.
• prompt – Optional text description for style / mood (e.g. “cinematic lighting, soft film grain, vivid colours”).
• resolution – Output resolution: 480p or 720p.
• seed – -1 for random; any other integer for reproducible results.

💰 Pricing

Pricing is based on video length, resolution, and billed in 5-second blocks, with:

• Minimum billable length: 5 seconds
• Maximum billable length: 120 seconds (anything longer is charged as 120 s)
• Base price: $0.2 per 5 seconds at 480p

Effective rates:

Internally, the system:

• Takes your video duration (capped at 120 s),
• Rounds it into 5-second blocks,
• Multiplies by the base price, and
• Applies a ×2 multiplier for 720p.

🚀 How to Use

1. Upload image – choose the face / character you want to animate.
2. Upload video – select the motion source clip.
3. (Optional) Enter a prompt to guide overall look and mood.
4. Choose resolution (start with 480p for fast tests; switch to 720p for final export).
5. (Optional) Set a fixed seed if you want to reproduce or slightly tweak the same take later.
6. Click Run and download the generated video once completed.

🎯 Recommended Use Cases

• Dance and performance remixes using a static character or avatar.
• Cosplay or outfit previews based on a single photo.
• VTuber / virtual idol short clips for social platforms.
• Quick pre-viz for ad concepts or character motion tests.

💡 Tips & Notes

• For best results, keep framing similar between the image and driving video (e.g. both full-body or both mid-shot).
• Avoid extremely fast motion, strong occlusions, or very busy backgrounds in the driving video for first tests.
• If faces look unstable, try a clearer input image or reduce extreme camera shake in the driving clip.

Reference

• Read the details from official page.

Try other models and see the difference

• fun-control — A playful motion-remix model built on ’s Wan 2.2, for controllable character and camera movement from simple prompts.
• wan-animate — A general animation model powered by ’s Wan 2.2, turning text or images into smooth, high-quality short videos.

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",
  "resolution": "480p",
  "seed": -1
}
JSON
)

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