DreamActor M2.0
DreamActor M2.0 from ByteDance makes a character image perform the motion, facial expressions and lip movements of a driving video. Upload a portrait, illustration or mascot plus a clip of someone moving or talking, and get a video of your character doing the same. Billed per second of the driving video.
The character to animate: photo, illustration, anime character or mascot. JPG or PNG, up to 4.7 MB, 480x480 to 1920x1080.
The driving video whose motion, expressions and lip movements are applied. Up to 30 seconds. Billed per second of this video.
Cut First Second
Remove the 1-second transition at the start of the result.
Your result renders here.
Use DreamActor M2.0 via the API
Generate with DreamActor M2.0 from your own code. Async by design: submit a generation, get a run id back instantly, poll until it completes. Billed in credits at the best available provider price — $0.05 per second.
1 — Start a generation
curl -X POST https://app.scenetra.com/api/v1/generate/dreamactor-m2.0 \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"image":"https://example.com/character.png","video":"https://example.com/talking.mp4"}'Response (202)
{
"runId": "run_abc123",
"status": "PENDING",
"model": "dreamactor-m2.0",
"estimatedCredits": 500,
"statusUrl": "/api/v1/runs/run_abc123"
}2 — Poll until COMPLETED (every 2-5 seconds)
curl https://app.scenetra.com/api/v1/runs/run_abc123 \
-H "Authorization: Bearer YOUR_API_KEY"Response
{
"runId": "run_abc123",
"status": "COMPLETED",
"progress": { "completed": 1, "total": 1 },
"outputs": [
{ "type": "video", "url": "https://images.scenetra.com/..." }
],
"error": null,
"estimatedCredits": 500
}Request fields
| Field | Type | Description | Default |
|---|---|---|---|
| image* | string (https URL) | The character to animate: photo, illustration, anime character or mascot. JPG or PNG, up to 4.7 MB, 480x480 to 1920x1080. | — |
| video* | string (https URL) | The driving video whose motion, expressions and lip movements are applied. Up to 30 seconds. Billed per second of this video. | — |
| cut_first_second | boolean | Remove the 1-second transition at the start of the result.true · false | true |
| callbackUrl | string (https URL) | Optional. When the run finishes (completed or failed), we POST the final run status to this URL — same shape as the poll response, plus model, params, and chargedCredits. Best-effort; polling remains the source of truth. | |
Unknown fields are rejected with a helpful 400. Media fields take https URLs. There is no provider parameter — every run is routed to the cheapest capable provider automatically.
Good to know
Billing
Runs bill your account credits at provider cost with 0% markup. The submit response includes the credit estimate; failed generations are refunded automatically. Add ?dryRun=1 to get the estimate without running anything.
Errors
Errors are always { "error": { "code", "message" } } with stable codes: unauthorized, model_not_available, invalid_parameter, insufficient_credits, rate_limited. A failed run is not an HTTP error — poll responses report status: "FAILED" with the reason.
What makes DreamActor M2.0 different
Motion, expressions and lip sync in one pass
DreamActor M2.0 copies more than body movement: head turns, facial expressions and mouth shapes come across from the driving video too. That makes it a strong pick for talking characters, reactions and expressive avatars, not just dances.
Works with photos, art and mascots
The character can be a real photo, an illustration, an anime character or a brand mascot. The look stays with your image while the performance comes from the video.
$0.05 per second, with automatic failover
You pay for the length of the driving video: a 10-second clip costs $0.50, the 30-second maximum $1.50. Scenetra runs each job on the best capable provider and falls back automatically if one is unavailable.
Clean starts
The raw result begins with a 1-second transition. Cut First Second, on by default, removes it so the clip starts on the first real frame of motion.
Parameters
| Parameter | Type | Description | Default |
|---|---|---|---|
| Image* | image | The character to animate: a photo, illustration, anime character or mascot. JPG or PNG, up to 4.7 MB, 480x480 to 1920x1080. | — |
| Template Video* | video | The driving video whose motion, expressions and lip movements are applied. MP4, MOV or WebM, up to 30 seconds. | — |
| Cut First Second | select | Removes the 1-second transition at the start of the result.On · Off | On |
Pricing
$0.05 per second
Pay per generation — only pay for what you use.
Any length up to 30s
$0.05/s
per second of the driving video
What a video costs
| Duration | Any resolution |
|---|---|
| 5-second clip | $0.25 |
| 10-second clip | $0.50 |
| 30-second clip | $1.50 |
Use cases
Avatars & presenters
- Talking avatars from a single photo
- Mascot spokesperson clips
- Animated course presenters
- Reaction characters for streams
Social content
- Character-swap trend videos
- Illustrations that talk and react
- Lip-synced meme clips
- Fan-art animations
Marketing
- Brand mascot performing a script
- Localized presenter variants
- Product explainer characters
- Quick ad concepts
Frequently asked questions
What is DreamActor M2.0?+
DreamActor M2.0 is ByteDance's character animation model. It takes a character image and a driving video and generates a video of the character performing the same motion, facial expressions and lip movements. On Scenetra it runs on the Create page's Motion control tool and as a node on the board.
How much does DreamActor M2.0 cost?+
$0.05 per second of the driving video, rounded up to whole seconds. A 10-second clip costs $0.50 and the 30-second maximum costs $1.50.
How long can the driving video be?+
Up to 30 seconds. The result is about as long as the driving video.
DreamActor M2.0 or Kling 3.0 Motion Control?+
DreamActor M2.0 is the more affordable choice and especially good at facial expressions and lip movements. Kling 3.0 Motion Control renders sharper 720p or 1080p video and holds a character steady through larger body motion. Both are on the same Motion control tool, so you can try your clip on each.
What makes a good driving video?+
One person, clearly visible, with good lighting and little background movement. Front-facing clips give the best expressions and lip sync.
Can I use photos of real people?+
Only photos you have the right to use. Do not upload images of people without their consent, and do not create sexual, deceptive or harmful content with anyone's likeness.
Related models
Kling 3.0 Motion Control
Kling 3.0 Motion Control takes one character image and one motion video and makes the character perform that exact movement — dance, gesture, walk or talk — in 720p. The body motion, timing and camera framing come from your video; the look comes from your image. Billed per second of the motion video.
View model →Kling 3.0 Motion Control Pro
Kling 3.0 Motion Control Pro takes one character image and one motion video and makes the character perform that exact movement — dance, gesture, walk or talk — in 1080p. The body motion, timing and camera framing come from your video; the look comes from your image. Billed per second of the motion video.
View model →Start creating with DreamActor M2.0
Use DreamActor M2.0 alongside 50+ other AI models in Scenetra's visual workflow editor. No setup required.
Get Started