Wan 2.1 Ditto

Wan 2.1 Ditto

Playground

Wan2.1-DITTO is a unified video-to-video model for realistic style transfer and reenactment, replicating holistic movement and expressions across frames. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Wan2.1-DITTO is an optimized video-to-video generation model that transforms existing footage into new visual styles guided by text or style prompts. With unified diffusion tuning, it delivers cinematic motion, smooth temporal consistency, and vivid artistic expression across multiple resolutions.

Why it looks great

• Unified Diffusion Core – Enhances motion smoothness and temporal consistency across frames.
• Style-flexible generation – Switch seamlessly between realism, anime, sketch, or cinematic tones.
• Precision color mapping – Retains natural tones and contrast even in stylized conversions.
• Resolution scalability – Available in both 480p and 720p, optimized for balance between speed and clarity.
• Consistent motion fidelity – Avoids flicker and deformation during high-action sequences.

Pricing

How to Use

1. Enter prompt — Describe or select the desired style for your video.
2. Choose resolution — 480p or 720p.
3. Run generation — Wait for AI rendering and preview results.
4. Review & iterate — Fix seed for reproducibility, change seed for variation.

Pro tips for best quality

• Keep your source video stable and clear for best transformation results.

• Higher resolution (720p) is ideal for professional output, while 480p suits faster drafts.

Note

• Actual render time varies with resolution and server load.

• Videos longer than 120 s should be split into multiple segments and merged after processing.

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": "RealDomain",
  "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/wan-2.1/ditto" \
  -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