# ByteDance DreamActor 2.0 API

> DreamActor 2.0 by ByteDance transfers motion, facial expressions and lip movement from a driving video to the character in a reference image.

Source: https://www.sandbase.ai/models/bytedance/dreamactor/2.0
API reference: https://www.sandbase.ai/models/bytedance/dreamactor/2.0/docs

## Facts

- Provider: ByteDance
- Type: Video model
- Model ID: `bytedance/dreamactor/2.0`
- Price: From $0.25 per run
- Capabilities: video to video
- Billing: pay per use from one SandBase balance; no provider account or subscription needed

## Call it

- Unified Run API: `POST https://api.sandbase.ai/v1/run`

```bash
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "bytedance/dreamactor/2.0",
  "image": "https://static.sandbase.ai/examples/alibaba/wan/2.2/animate/move/input_image_1.png",
  "video": "https://static.sandbase.ai/examples/alibaba/wan/2.2/animate/move/input_video_0.mp4",
  "trim_first_second": true
}'
```

The response returns a run id; poll `GET https://api.sandbase.ai/v1/run/{id}` until the status is `completed` or `failed`.

## FAQ

### How do I call ByteDance DreamActor 2.0 through SandBase?

Create a SandBase API key, then send requests with the model ID "bytedance/dreamactor/2.0" to Unified Run API (/v1/run) at https://api.sandbase.ai. The request examples on this page show the exact payload.

### Do I need a separate ByteDance account?

No. One SandBase API key and balance gives you access to ByteDance DreamActor 2.0 and the other models in the catalog; you do not need to sign up with ByteDance separately.

## README

### ByteDance DreamActor 2.0

DreamActor 2.0 transfers body motion, facial expression, and lip movement from a driving `video` to the character in `image`.

#### Fields

| Field | Type | Default | Notes |
|---|---|---|---|
| `image` | image URL, required | — | Character to animate. JPEG, PNG, or WebP URL. |
| `video` | video URL, required | — | Driving video that supplies motion and expression. |
| `trim_first_second` | boolean | true | Drop the first second, which is often used for alignment. |

#### Billing

$0.05 per output second. The quote before submission assumes 5 seconds; the final charge uses the measured length.

| Output | Price |
|---|---|
| 5s | $0.25 |
| 10s | $0.50 |
| 30s | $1.50 |

Failed runs are not charged.

#### Prompting

- Use a driving video with one clearly visible face and body.
- Match the character image's framing to the driving video.

#### Limits

- Output length follows the driving video.

#### Also on SandBase

Related: `bytedance/omnihuman/1.5` (audio-driven).