# Bytedance | Seedance 2.0 | Reference to Video

An advanced video generation model delivering cinematic visuals with native audio, realistic physics, and director-level camera control, supporting text, image, audio, and video inputs. "Please use this model only with AI-generated human faces, not real human faces. If you use real human faces, you accept full responsibility and liability for any consequences."

## API Information

- **Model Slug:** bytedance-seedance-2-0-reference-to-video
- **Branded URL:** https://www.eachlabs.ai/bytedance/seedance-2-0/bytedance-seedance-2-0-reference-to-video
- **Provider:** ByteDance
- **Category:** Image to Video
- **Output Type:** video
- **Status:** active
- **Base Cost:** 720p (default): approximately $0.174 per second of output video
- **Estimated Processing Time:** 290 seconds
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/bytedance-seedance-2-0-reference-to-video

## Pricing

- **Charge Type:** dynamic
- **Pricing Details:** 720p (default): approximately $0.174 per second of output video

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| length(to_array(input.video_urls \|\| `[]`)[?@ != '' && @ != `null`]) > "0" AND resolution == "480p" | With reference video, 480p: approximately $0.048 per second of output video, plus the reference video's input tokens |
| length(to_array(input.video_urls \|\| `[]`)[?@ != '' && @ != `null`]) > "0" AND resolution == "1080p" | With reference video, 1080p: approximately $0.263 per second of output video, plus the reference video's input tokens |
| length(to_array(input.video_urls \|\| `[]`)[?@ != '' && @ != `null`]) > "0" AND resolution == "4k" | With reference video, 4k: approximately $0.537 per second of output video, plus the reference video's input tokens |
| length(to_array(input.video_urls \|\| `[]`)[?@ != '' && @ != `null`]) > "0" | With reference video, 720p (default): approximately $0.107 per second of output video, plus the reference video's input tokens |
| resolution == "480p" | 480p: approximately $0.077 per second of output video |
| resolution == "1080p" | 1080p: approximately $0.430 per second of output video |
| resolution == "4k" | 4k: approximately $0.894 per second of output video |
| Rule 8 | 720p (default): approximately $0.174 per second of output video |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | The text prompt used to generate the video. |
| image_urls | array | No | - | - | Reference images to guide video generation. Refer to them in the prompt as @Image1, @Image2, etc. Supported formats: JPEG, PNG, WebP. Max 30 MB per image. Up to 9 images. Total files across all modalities must not exceed 12. |
| video_urls | array | No | - | - | Reference videos to guide video generation. Refer to them in the prompt as @Video1, @Video2, etc. Supported formats: MP4, MOV. Up to 3 videos, combined duration must be between 2 and 15 seconds, total size under 50 MB. Each video must be between ~480p (640x640) and ~720p (834x1112) in resolution. |
| audio_urls | array | No | - | - | Reference audio to guide video generation. Refer to them in the prompt as @Audio1, @Audio2, etc. Supported formats: MP3, WAV. Up to 3 files, combined duration must not exceed 15 seconds. Max 15 MB per file. If audio is provided, at least one reference image or video is required. |
| resolution | string | No | 720p | 480p, 720p, 1080p, 4k | Video resolution - 480p for faster generation, 720p for balance, 1080p for highest quality. |
| duration | string | No | auto | auto, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 | Duration of the video in seconds. Supports 4 to 15 seconds, or auto to let the model decide based on the prompt. |
| aspect_ratio | string | No | auto | auto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | The aspect ratio of the generated video. Use 16:9 for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide cinematic, or auto to let the model decide. |
| generate_audio | boolean | No | true | - | Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated or not. |
| seed | string | No | - | - | Random seed for reproducibility. Note that results may still vary slightly even with the same seed. |
| enable_safety_checker | boolean | No | true | - | Whether to enable the safety checker on inputs and outputs. Defaults to true. |

## 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": "bytedance-seedance-2-0-reference-to-video",
  "input": {
    "prompt": "A vacant lot between two red brick English terraced houses slowly transforms over time. First the empty overgrown plot with a wooden hoarding fence, then a timber frame skeleton rising with scaffolding, finally a fully completed brick house matching the neighbours perfectly. Camera is fixed straight-on from across the street, continuous timelapse transition between all three stages. Camera is fixed timelapse."
  }
}'
```

## 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

**Bytedance | Seedance 2.0 | Reference to Video Overview**

Bytedance | Seedance 2.0 | Reference to Video transforms static images, videos, audio, and text into cinematic videos with native audio synchronization and precise motion control. Developed by ByteDance as part of the Seedance family, this multimodal model excels in image-to-video generation, preserving subject identity, composition, and style while adding realistic physics and director-level camera movements. Its standout differentiator is support for up to 12 mixed reference files—images, videos, and audio—in a single generation, enabling Hollywood-grade outputs that outperform single-input competitors. Available via APIs like on each::labs, Bytedance | Seedance 2.0 | Reference to Video empowers creators to produce 1080p clips up to 60 seconds with lip-synced dialogue and sound effects, revolutionizing workflows from storyboards to final edits.

## 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.