## Basic model info

- Model name: bytedance/bytedance seedance-2.5
- Model description: Generate up to 30-second coherent videos with synchronized audio using Seedance 2.5, ByteDance's flagship video model. Supports up to 50 multimodal references (30 images, 10 videos, 10 audios), video editing and extension.
- Endpoint name: draft-to-video


## Model schema

The model schema is defined in the OpenAPI schema: [OpenAPI Schema](https://oapi.sunra.ai/main/bytedance/seedance-2.5/latest.json)

### Model input schema

The model input schema is:



```json
{
  "description": "Finalize a 480p draft into a 1080p video via the byteplus channel.\n\nContent, seed, duration, aspect ratio and audio settings are reused from the\ndraft. Treat the draft id like a signed URL: anyone holding it can finalize\nit at 1080p on their own account.",
  "properties": {
    "draft_task_id": {
      "description": "Draft id returned as draft_task_id, valid for 7 days from creation and usable only on the channel that generated it (byteplus). Treat the draft id like a signed URL: anyone holding it can finalize it at 1080p on their own account.",
      "maxLength": 128,
      "minLength": 1,
      "title": "Draft Task Id",
      "type": "string",
      "x-sr-order": 301
    },
    "output_format": {
      "default": "mp4",
      "description": "Output video format for the 1080p final. 'mov' (H.264 + yuv444p + PCM) preserves color fidelity for professional editing workflows.",
      "enum": [
        "mp4",
        "mov"
      ],
      "title": "Output Format",
      "type": "string",
      "x-sr-order": 404
    }
  },
  "required": [
    "draft_task_id"
  ],
  "title": "DraftToVideoInput",
  "type": "object"
}
```



### Model output schema

The model output schema is:



```json
{
  "description": "Output schema for Seedance 2.5 video generation.",
  "properties": {
    "fps": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "description": "Output frames per second, as reported by the provider.",
      "title": "Fps"
    },
    "seed": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "description": "Generation seed, as reported by the provider.",
      "title": "Seed"
    },
    "draft_task_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "description": "Draft id usable for draft-to-video within 7 days of draft creation, only on the channel that generated the draft. Returned for both draft and finalized videos.",
      "title": "Draft Task Id"
    },
    "duration": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "description": "Actual output video duration in seconds, as reported by the provider.",
      "title": "Duration"
    },
    "ratio": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "description": "Resolved output aspect ratio, as reported by the provider.",
      "title": "Ratio"
    },
    "resolution": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "description": "Output resolution tier, as reported by the provider.",
      "title": "Resolution"
    },
    "total_tokens": {
      "description": "Total tokens consumed for this generation",
      "title": "Total Tokens",
      "type": "integer"
    },
    "units": {
      "description": "Billing units. 1000 units = $1.",
      "title": "Units",
      "type": "number"
    },
    "video": {
      "properties": {
        "content_type": {
          "description": "The mime type of the file.",
          "title": "Content Type",
          "type": "string"
        },
        "file_name": {
          "description": "The name of the file. It will be auto-generated if not provided.",
          "title": "File Name",
          "type": "string"
        },
        "file_size": {
          "description": "The size of the file in bytes.",
          "title": "File Size",
          "type": "integer"
        },
        "url": {
          "description": "The URL where the file can be downloaded from.",
          "title": "Url",
          "type": "string"
        }
      },
      "required": [
        "content_type",
        "file_name",
        "file_size",
        "url"
      ],
      "title": "SunraFile",
      "type": "object"
    }
  },
  "required": [
    "video",
    "total_tokens",
    "units"
  ],
  "title": "Seedance25Output",
  "type": "object"
}
```



## Example inputs and outputs

Use the following example inputs and outputs to understand the model.

### Input example



```json
{
  "draft_task_id": "",
  "output_format": "mp4"
}
```



### Output example



```json
{
}
```



## Model code examples

### JavaScript



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

const result = await sunra.subscribe("bytedance/seedance-2.5/draft-to-video", {
  input: {
  	draft_task_id: '',
  	output_format: 'mp4'
  },
  logs: true,
  onQueueUpdate: (update) => {
    console.log(`Status Update: ${update.status}, Request ID: ${update.request_id}`);
  },
});
console.log(result.data);
console.log(result.requestId);
```



### Python



```python
import sunra_client

result = sunra_client.subscribe(
    "bytedance/seedance-2.5/draft-to-video",
    arguments={
        "draft_task_id": "",
        "output_format": "mp4"
    },

    with_logs=True,
    on_enqueue=print,
    on_queue_update=print,
)
print(result)
```



### Java



```java
import ai.sunra.client.*;
import java.util.Map;
import com.google.gson.JsonObject;

var client = SunraClient.withEnvCredentials();

var response = client.subscribe(
    "bytedance/seedance-2.5/draft-to-video",
    SubscribeOptions.<JsonObject>builder()
        .input(Map.of(
            "draft_task_id", "",
            "output_format", "mp4"))

        .resultType(JsonObject.class)
        .onQueueUpdate(update -> System.out.printf(
            "\nStatus Update: %s, Request ID: %s%n",
            update.getStatus(),
            update.getRequestId()
        ))
        .logs(true)
        .build()
);

System.out.println("Completed!");
System.out.println(response.getData());
  
```



### Kotlin



```kotlin
import ai.sunra.client.kt.*
import com.google.gson.JsonObject

val client = createSunraClient()

val response = client.subscribe<JsonObject>(
    endpointId = "bytedance/seedance-2.5/draft-to-video",
    input = mapOf(
            "draft_task_id" to "",
            "output_format" to "mp4"),
    options = ai.sunra.client.kt.SubscribeOptions(logs = true),
    onUpdate = { update ->
        println("\nStatus Update: ${update.status}, Request ID: ${update.requestId}")
    }
)

println("Completed!")
println(response.data)
  
```



### Curl



```bash

curl --request POST \
  --url https://api.sunra.ai/v1/queue/bytedance/seedance-2.5/draft-to-video \
  --header "Authorization: Key $SUNRA_KEY" \
  --header "Content-Type: application/json" \
  --data '{"draft_task_id":"","output_format":"mp4"}'
    
```



## Model readme

>