# Runway | Act-Two

Runway Act-Two turns performance videos into realistic character animations by transferring gestures and expressions.

## API Information

- **Model Slug:** runway-act-two
- **Branded URL:** https://www.eachlabs.ai/runway/runway/runway-act-two
- **Provider:** Runway
- **Category:** Video to Video
- **Output Type:** video
- **Status:** active
- **Base Cost:** $0.05 per second
- **Estimated Processing Time:** 200 seconds
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/runway-act-two

## Pricing

- **Charge Type:** dynamic
- **Estimate:** $0.05 per second
- **Pricing Details:** default: $0.05

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| character_type | string | No | image | image, video | Type of character input. image: use a still photo of a person as the character (default, best for most use cases — cleaner results with less artifacts). video: use a video clip of a person as the character (useful when you need the character's original appearance in motion as a starting point). |
| character_uri | string | Yes | - | - | Image or video of the character to animate. A face must be clearly visible and remain in frame throughout. For image: recommended 640x640px to 4K. For video: the person's face should be visible throughout the clip. |
| reference_uri | string | Yes | - | - | Video of a person performing the motion and expressions you want transferred to the character. Duration: 3-30 seconds. The performer's face and body should be clearly visible. Supported codecs: H.264, H.265/HEVC, AV1, VP8, VP9, Apple ProRes. Supported containers: MP4, QuickTime, Matroska, WebM, 3GPP, Ogg. |
| aspect_ratio | string | No | 1280:720 | 1280:720, 720:1280, 960:960, 1104:832, 832:1104, 1584:672 | Output video resolution. 1280:720: standard landscape 16:9 (default). 720:1280: standard portrait 9:16, ideal for social media. 960:960: square 1:1. 1104:832: wide landscape 4:3. 832:1104: tall portrait 3:4. 1584:672: ultra-wide cinematic 21:9. |
| body_control | boolean | No | true | - | Enable body movement transfer from the reference video. true: applies both facial expressions and body gestures/movements from the reference (default, recommended for full performance transfer). false: only facial expressions are transferred, body remains static (useful when you only want face animation on a still character). |
| expression_intensity | integer | No | 3 | 1, 2, 3, 4, 5 | Intensity of facial expressions transferred from the reference. 1: subtle, minimal expression (good for calm/professional scenes). 2: mild expression. 3: balanced, natural expression (default, recommended for most use cases). 4: enhanced expression. 5: maximum intensity, exaggerated expressions (good for animated/comedic content). |
| seed | integer | No | - | 1–4294967294 | Random seed for reproducible generation. Set a specific value to get consistent results across runs with identical inputs. Leave empty for random generation. |
| public_figure_moderation | string | No | low | auto, low | Content moderation level for public figures. auto: standard moderation, blocks most public figure likenesses. low: relaxed moderation, allows more creative freedom with public figure references (default). |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "runway-act-two",
  "input": {
    "character_uri": "https://cdn-us.eachlabs.ai/defaults/7031cd09f4289106065eda79d3cf877693ad90980a6a1b6f97d9271ab3229cc5.jpeg",
    "reference_uri": "https://cdn-us.eachlabs.ai/defaults/56bc4528d96e6fdd1ad59944d97731d93dc7cf9326881fed9926ed6b11883922.mp4"
  }
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "string (URL of generated video)",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**runway-act-two — Image-to-Video AI Model**

Runway Act-Two transforms static performance videos into hyper-realistic character animations by precisely transferring gestures, facial expressions, and body movements from an actor to any target character. Developed by Runway as part of the **runway** family, **runway-act-two** solves the challenge of creating lifelike animations without manual keyframing, enabling creators to produce professional-grade videos from simple inputs like a reference performance clip and a character image. This **image-to-video AI model** stands out in **Runway image-to-video** workflows by maintaining temporal consistency and emotional fidelity across extended sequences, ideal for filmmakers and animators seeking "AI character animation from video performance" results.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.