bytedance/dreamactor/2.0

Name: DreamActor 2.0
Author: Bytedance

DreamActor M2.0 by ByteDance generates videos by animating a reference image using motion from a driving video. It replicates motion, facial expressions, and lip movements from the template video while preserving the sub...

Input

Image URL or upload(string)

Upload

PNG, JPEG, WebP, or GIF · 20 MiB maximum

The URL of the reference image to animate. Supports real people, animation, pets, etc. Format: jpeg, jpg or png. Max size: 4.7 MB. Resolution: between 480x480 and 1920x1080 (larger images will be proportionally reduced).

This field is required.

Video Url(string)

The URL of the driving template video providing motion, facial expressions, and lip movement reference. Max duration: 30 seconds. Format: mp4, mov or webm. Resolution: between 200x200 and 2048x1440. Supports full face and body driving.

Trim First Second(boolean)

Whether to crop the first second of the output video. The output has a 1-second transition at the beginning; enable this to remove it.

Idle

Example output — click Run to generate your own

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run

Model IDbytedance/dreamactor/2.0

Input Schema

3 parameters · 1 required · 2 optional

Parameter	Type	Required	Description
`image`	string	Required	The URL of the reference image to animate. Supports real people, animation, pets, etc. Format: jpeg, jpg or png. Max size: 4.7 MB. Resolution: between 480x480 and 1920x1080 (larger images will be proportionally reduced).
`video`	string	Optional	The URL of the driving template video providing motion, facial expressions, and lip movement reference. Max duration: 30 seconds. Format: mp4, mov or webm. Resolution: between 200x200 and 2048x1440. Supports full face and body driving.
`trim_first_second`	boolean	Optional	Whether to crop the first second of the output video. The output has a 1-second transition at the beginning; enable this to remove it. · Default: true

Output Schema

Field	Type	Description
`id`	string	Unique identifier for the generation task
`status`	string	Task status: pending, running, completed, failed, timeout
`model`	string	Model used for the generation
`outputs`	array	Array of output items
`outputs[].url`	string	URL of the generated artifact
`outputs[].content_type`	string	MIME type (e.g. image/png, video/mp4)
`error`	object \| null	Error details if failed, null on success
`error.type`	string	Machine-readable error type code
`error.message`	string	Human-readable error description

Async Workflow

This model uses asynchronous execution. Submit a request and poll for the result.

Submit — POST to /v1/run, receive an id
Poll — GET /v1/run/{id} until status is completed, failed, or timeout
Retrieve — Read outputs from the completed response

Code Examples

Ready-to-run snippets

# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "bytedance/dreamactor/2.0",
  "image": "https://static.sandbase.ai/examples/bytedance/dreamactor/2.0/input_image_0.png",
  "video": "https://static.sandbase.ai/examples/bytedance/dreamactor/2.0/input_video_1.mp4",
  "trim_first_second": true,
  "prompt": "a beautiful sunset over mountains"
}'

# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
  -H "Authorization: Bearer YOUR_API_KEY"

← Back to DreamActor 2.0

API README

Bytedance Dreamactor 2.0

Bytedance Dreamactor 2.0 is built for animating a reference character from driving motion for expressive performance video. It gives creative and production teams a focused way to move from an approved brief or source asset to a reviewable result without fragmenting the job across unrelated tools. The model is most valuable when visual intent, brand suitability, and downstream usability all matter, because its output can enter an editorial, campaign, product, or content pipeline as a purposeful asset rather than an isolated experiment.

In practice, teams can use Bytedance Dreamactor 2.0 during a structured cycle of briefing, generation, comparison, and refinement. Establish the subject, audience, visual objective, and acceptance criteria first; prepare any reference media at suitable quality; then evaluate alternatives for composition, continuity, realism, and communication value before delivery. This workflow keeps creative judgment central while making repeated production easier to review, reproduce, and scale for the specific bytedance/dreamactor/2.0 task.

Highlights

Reference appearance retention. Reference appearance retention gives bytedance › dreamactor › 2.0 a recognizable technical advantage: reviewers can assess this property directly in the generated asset instead of inferring it from request mechanics.

Motion-driven character animation. bytedance › dreamactor › 2.0 applies motion-driven character animation to the visual or temporal result itself, helping artists make a meaningful quality decision during selection and refinement.

Expressive body performance. For bytedance › dreamactor › 2.0, expressive body performance supports coherent assets across the intended creative workflow and distinguishes this capability from a simple format or delivery option.

Temporally coherent rendering. The practical value of temporally coherent rendering is visible in the finished media from bytedance › dreamactor › 2.0, where it supports repeatable art direction rather than merely exposing another request setting.

Pricing

Billing basis	Rate
Driving-video runtime	$0.050000 per second

When to Use

✅ Good fit	❌ Consider alternatives
Use it when animating a reference character from driving motion for expressive performance video is the central production goal	Choose a different model when the required media task is fundamentally different
The team needs several reviewable creative alternatives	Exact deterministic reproduction is mandatory
Visual quality and practical downstream use both matter	Editable source layers or native project files are required
A managed generation step fits the delivery workflow	A live frame-by-frame interactive editor is essential
The documented inputs cover the available source assets	Required source media or controls fall outside the documented fields

Prompt Guide

State the intended result first, then describe the subject, environment, action, visual treatment, and delivery constraints. Keep instructions concrete, avoid conflicting directions, and change one creative variable at a time when comparing outputs. For source-driven work, describe what should remain recognizable as clearly as what should change.

{
  "image": "https://static.sandbase.ai/examples/bytedance/dreamactor/2.0/input_image_0.png",
  "video": "https://static.sandbase.ai/examples/bytedance/dreamactor/2.0/input_video_1.mp4"
}

Technical Specs

Property	Details
`image`	Type / options: string<br>Required: Yes<br>Description: The URL of the reference image to animate. Supports real people, animation, pets, etc. Format: jpeg, jpg or png. Max size: 4.7 MB. Resolution: between 480x480 and 1920x1080 (larger images will be proportionally reduced).
`video`	Type / options: string<br>Required: No<br>Description: The URL of the driving template video providing motion, facial expressions, and lip movement reference. Max duration: 30 seconds. Format: mp4, mov or webm. Resolution: between 200x200 and 2048x1440. Supports full face and body driving.
`trim_first_second`	Type / options: boolean<br>Required: No<br>Description: Whether to crop the first second of the output video. The output has a 1-second transition at the beginning; enable this to remove it.

Related Models

bytedance/lynx
bytedance/omnihuman/1.0
bytedance/omnihuman/1.5