# Seedance 2.0 Reference to Video

> Generate a video steered by up to 9 reference images — keep a character, outfit, product, or location consistent by naming each reference in the prompt.

## Overview

- **Endpoint**: `https://queue.modelrunner.run/bytedance/seedance-v2/reference-to-video`
- **Model ID**: `bytedance/seedance-v2/reference-to-video`
- **Category**: image-to-video
- **Kind**: inference
- **Tags**: video, image-to-video, reference-to-video, reference-image, character-consistency, video generation, audio, bytedance, seedance

## Pricing

- **Price**: $0.227 per output second

## Request Lifecycle

This model runs on the ModelRunner **asynchronous queue API** — a single POST does not return the output. Every call requires an `Authorization: Key $MODEL_RUNNER_KEY` header. Run three steps:

1. **Submit** — `POST https://queue.modelrunner.run/bytedance/seedance-v2/reference-to-video` with a JSON body holding the input fields at the top level. The body may also include a reserved top-level `metadata` object — a flat string map (max 16 keys, key ≤64 / value ≤512 chars) stored on the request for your own tagging. It is never sent to the model; filter your request history with `GET https://queue.modelrunner.run/requests?metadata=<url-encoded JSON>` (exact key=value matches, AND-ed). The response carries request handles only (no output yet):

```json
{
  "status": "IN_QUEUE",
  "request_id": "<21-char id>",
  "status_url": "https://queue.modelrunner.run/bytedance/seedance-v2/reference-to-video/requests/<request_id>/status",
  "response_url": "https://queue.modelrunner.run/bytedance/seedance-v2/reference-to-video/requests/<request_id>",
  "cancel_url": "https://queue.modelrunner.run/bytedance/seedance-v2/reference-to-video/requests/<request_id>/cancel"
}
```

2. **Poll status** — `GET <status_url>` until `status` is `COMPLETED`. Possible values are `IN_QUEUE`, `IN_PROGRESS`, `COMPLETED`, `FAILED`, `CANCELLED`. A `FAILED` request responds with HTTP 400 and an `error` field.

3. **Read result** — `GET <response_url>`. Returns the finished request, including the generated `output`:

```json
{ "id": "<request_id>", "status": "COMPLETED", "output": ..., "input": ... }
```

The JavaScript and Python SDKs below perform steps 2–3 for you. In any language without an SDK (Swift, Go, Kotlin, etc.) you must implement the polling loop and the final result fetch yourself — see the cURL example for the full flow.

### Input Schema

- **`prompt`** (`string`, _required_):
  Describe the shot, the action, the camera move, and the sound. Address the reference assets positionally as @Image1..@Image9 and @Audio1..@Audio3, numbered by their order in reference_images and reference_audios — a reference the prompt never names is usually ignored. English, Chinese, Japanese, Indonesian, Spanish and Portuguese prompts are all understood.

- **`duration`** (`integer`, _optional_):
  Clip length in seconds.
  - Default: `5`
  - Range: `4` to `15`

- **`resolution`** (`resolution`, _optional_):
  Output resolution of the clip. Higher resolutions cost more per second of video.
  - Default: `"720p"`
  - Options: `"480p"`, `"720p"`, `"1080p"`

- **`aspect_ratio`** (`aspect_ratio`, _optional_):
  Frame shape of the clip. Reference images do not fix the framing, so set this to the shape you want; adaptive lets the model choose.
  - Default: `"16:9"`
  - Options: `"16:9"`, `"4:3"`, `"1:1"`, `"3:4"`, `"9:16"`, `"21:9"`, `"adaptive"`

- **`generate_audio`** (`boolean`, _optional_):
  Generate a synchronized soundtrack (dialogue, ambience and sound effects) together with the picture. Set false for a silent clip; the price is the same either way.
  - Default: `true`

- **`reference_audios`** (`array<string>`, _optional_):
  Up to 3 short audio references the generated soundtrack should follow. MP3 or WAV, under 15 MB each and 15 seconds combined. Addressed as @Audio1..@Audio3. Cannot be supplied on their own — at least one reference image is always required.

- **`reference_images`** (`array<string>`, _required_):
  1 to 9 reference images that steer identity, wardrobe, product, location or style. JPEG, PNG or WebP, under 30 MB each. The first entry is @Image1 in the prompt, the second @Image2, and so on.

### Output Schema

_No `Output` schema properties are available._

## Default Example

**Input**

```json
{
  "prompt": "@Image1 rests half-submerged on the wet rocks beneath the lighthouse from @Image2, waves breaking and washing around the brass as the beam sweeps overhead through the sea spray.",
  "duration": 5,
  "resolution": "480p",
  "aspect_ratio": "16:9",
  "generate_audio": true,
  "reference_images": [
    "https://media.modelrunner.ai/mszOvkXm9bhk9bEmJRsGy.jpeg",
    "https://media.modelrunner.ai/g6ez6XYfi55kQUkDYLgjq.jpeg"
  ]
}
```

**Output**

```json
"https://media.modelrunner.ai/8HZsHAqtQltv9jL6EUIs7.mp4"
```
## Usage Examples

### cURL

The queue API is asynchronous: submit the request, poll `status_url` until it is `COMPLETED`, then read the result from `response_url`. Requires `jq`.

```bash
# 1. Submit the request (returns request handles, not the output)
SUBMIT=$(curl --silent --request POST \
  --url https://queue.modelrunner.run/bytedance/seedance-v2/reference-to-video \
  --header "Authorization: Key $MODEL_RUNNER_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "prompt": "@Image1 rests half-submerged on the wet rocks beneath the lighthouse from @Image2, waves breaking and washing around the brass as the beam sweeps overhead through the sea spray.",
  "duration": 5,
  "resolution": "480p",
  "aspect_ratio": "16:9",
  "generate_audio": true,
  "reference_images": [
    "https://media.modelrunner.ai/mszOvkXm9bhk9bEmJRsGy.jpeg",
    "https://media.modelrunner.ai/g6ez6XYfi55kQUkDYLgjq.jpeg"
  ]
}')

STATUS_URL=$(echo "$SUBMIT" | jq -r '.status_url')
RESPONSE_URL=$(echo "$SUBMIT" | jq -r '.response_url')

# 2. Poll until the request leaves the queue / in-progress state
while true; do
  STATUS=$(curl --silent --url "$STATUS_URL" \
    --header "Authorization: Key $MODEL_RUNNER_KEY" | jq -r '.status')
  echo "Status: $STATUS"
  case "$STATUS" in
    COMPLETED) break ;;
    FAILED|CANCELLED) echo "Request $STATUS"; exit 1 ;;
  esac
  sleep 1
done

# 3. Read the finished request, including the generated output
curl --silent --url "$RESPONSE_URL" \
  --header "Authorization: Key $MODEL_RUNNER_KEY"
```

### JavaScript

```javascript
import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("bytedance/seedance-v2/reference-to-video", {
  input: {
  "prompt": "@Image1 rests half-submerged on the wet rocks beneath the lighthouse from @Image2, waves breaking and washing around the brass as the beam sweeps overhead through the sea spray.",
  "duration": 5,
  "resolution": "480p",
  "aspect_ratio": "16:9",
  "generate_audio": true,
  "reference_images": [
    "https://media.modelrunner.ai/mszOvkXm9bhk9bEmJRsGy.jpeg",
    "https://media.modelrunner.ai/g6ez6XYfi55kQUkDYLgjq.jpeg"
  ]
}
});

console.log(result.data);
```

### Python

```python
import asyncio
import modelrunner_ai

async def main():
    response = await modelrunner_ai.submit_async(
        "bytedance/seedance-v2/reference-to-video",
        arguments={
  "prompt": "@Image1 rests half-submerged on the wet rocks beneath the lighthouse from @Image2, waves breaking and washing around the brass as the beam sweeps overhead through the sea spray.",
  "duration": 5,
  "resolution": "480p",
  "aspect_ratio": "16:9",
  "generate_audio": true,
  "reference_images": [
    "https://media.modelrunner.ai/mszOvkXm9bhk9bEmJRsGy.jpeg",
    "https://media.modelrunner.ai/g6ez6XYfi55kQUkDYLgjq.jpeg"
  ]
}
    )
    result = await response.get()
    print(result["output"])

asyncio.run(main())
```

## Additional Resources

- [Playground](https://modelrunner.ai/models/bytedance/seedance-v2/reference-to-video)
- [OpenAPI Schema](https://modelrunner.ai/models/bytedance/seedance-v2/reference-to-video/openapi.json)
- [LLM Instructions](https://modelrunner.ai/models/bytedance/seedance-v2/reference-to-video/llms.txt)