Wan 2.1 Synthetic to Real Ditto | AI Video Enhancement API

WAN 2.1 Synthetic-To-Real Ditto — Video-to-Video Model

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.

Wan 2.1 Synthetic To Real Ditto API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.1/synthetic-to-real-ditto with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Wan 2.1 Synthetic To Real Ditto below.

HTTP example

# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.1/synthetic-to-real-ditto" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d '{
    "video": "https://example.com/your-input.mp4",
    "resolution": "480p",
    "seed": -1
}'

# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY"

# When status is "completed", read the output from data.outputs[0].

Node.js example

// npm install wavespeed
const WaveSpeed = require('wavespeed');

const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env

const result = await client.run("wavespeed-ai/wan-2.1/synthetic-to-real-ditto", {
        "video": "https://example.com/your-input.mp4",
        "resolution": "480p",
        "seed": -1
});

console.log(result.outputs[0]); // → URL of the generated output

Python example

# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "wavespeed-ai/wan-2.1/synthetic-to-real-ditto",
    {
    "video": "https://example.com/your-input.mp4",
    "resolution": "480p",
    "seed": -1
}
)

print(output["outputs"][0])  # → URL of the generated output

Wan 2.1 Synthetic To Real Ditto API — Frequently asked questions

What is the Wan 2.1 Synthetic To Real Ditto API?

Wan 2.1 Synthetic To Real Ditto is a WaveSpeedAI model for video editing, exposed as a REST API 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. You can call it programmatically or try it from the playground above.

How do I call the Wan 2.1 Synthetic To Real Ditto API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/wan-2.1-synthetic-to-real-ditto.

How much does Wan 2.1 Synthetic To Real Ditto cost per run?

Wan 2.1 Synthetic To Real Ditto starts at $0.20 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Wan 2.1 Synthetic To Real Ditto accept?

Key inputs: `video`, `resolution`, `seed`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/wavespeed-ai/wan-2.1-synthetic-to-real-ditto.

How do I get started with the Wan 2.1 Synthetic To Real Ditto API?

Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.

Can I use Wan 2.1 Synthetic To Real Ditto outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

ExamplesView all

Related Models

README