Wan 2.1 Synthetic To Real Ditto
Playground
Try it on WaveSpeedAI!WAN 2.1 Synthetic To Real Ditto mirrors motion and facial expressions in video-to-video synthetic-to-real conversion. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
WAN 2.1 Synthetic-To-Real Ditto converts stylized or synthetic videos (3D, anime, game footage, VTuber-style avatars, etc.) into realistic, live-action–like footage. It mirrors the original motion and facial expressions while replacing the look with a more natural, photographic style. The model is exposed through a ready-to-use REST inference API with fast warm-starts and affordable pricing.
What it does
- Takes a source video with a synthetic or stylized character.
- Tracks body motion, facial expressions, and timing.
- Generates a new realistic human version of the same performance.
- Preserves framing and pacing so you can swap footage without re-editing your timeline.
This makes it ideal for:
- Upgrading animated storyboards into realistic previews
- Turning VTuber or game-style performances into semi-realistic actors
- Rapid prototyping of live-action shots from synthetic previz
Key Capabilities
- High-fidelity motion mirroring Copies head turns, eye blinks, lip movements, and body motion from the input clip with tight temporal alignment.
- Synthetic-to-real translation Transforms toon, 3D, or heavily stylized characters into natural-looking humans while keeping their core identity and staging.
- Consistent lighting and shading Adapts the original scene’s lighting so the new actor feels anchored in the same environment.
- Resolution flexibility Supports both 480p and 720p output for different production needs.
Inputs and Controls
-
video (required) Upload or paste the URL of the source video.
-
resolution
-
480p
-
720p
Pricing
| Resolution | Price per second | Min billed seconds | Min total price | Max billed seconds | Max total price |
|---|---|---|---|---|---|
| 480p | $0.04 | 5 s | $0.20 | 120 s | $4.80 |
| 720p | $0.08 | 5 s | $0.40 | 120 s | $9.60 |
How to Use
- Upload your synthetic or stylized video in the video field. (up to 120s)
- Select the desired resolution (480p or 720p).
- Make sure Enable Safety Checker is checked.
- Click Run.
- After processing, preview the real-style output in the right panel and download it for editing or further post-production.
Tips for Best Results
- Use clips with clear, front-facing characters and stable framing to get the best facial detail.
- Avoid heavy motion blur or rapid strobing; clean animation yields more faithful translations.
- Keep clips short when iterating (around 3–5 seconds) to explore different looks quickly and control costs.
- Once you find a look you like, batch-convert key shots from your project to build a consistent, realistic version of your synthetic footage.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
set -euo pipefail
export WAVESPEED_API_KEY="your-api-key"
REQUEST_BODY=$(cat <<'JSON'
{
"video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
"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/synthetic-to-real-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
doneParameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| video | string | Yes | - | URL to the video to use as the input for the generation. | |
| resolution | string | No | 480p | 480p, 720p | The resolution of the output video. |
| seed | integer | No | -1 | - | The random seed to use for the generation. -1 means a random seed will be used. |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Output values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array<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.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to poll for the prediction result |
| data.status | string | Status: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |