## Basic model info - Model name: bytedance/bytedance seedance-2.5-flash - Model description: Seedance 2.5 Flash is ByteDance's fast multimodal video model for coherent 4–30 second generation with synchronized audio, first/last frames, and image, video, or audio references. - Endpoint name: reference-to-video ## Model schema The model schema is defined in the OpenAPI schema: [OpenAPI Schema](https://oapi.sunra.ai/main/bytedance/seedance-2.5-flash/ddf6cb742904d9f8bc15081a014eb7c7ba010943.json) ### Model input schema The model input schema is: ```json { "description": "Omni-reference generation, editing, and extension.\n\nBytePlus independently caps the aggregate duration of reference videos and\nreference audios at 30 seconds. The adapter measures HTTP video references\nwhere safe; BytePlus remains authoritative for opaque assets and audio.", "properties": { "prompt": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "Optional prompt. Use @Image1, @Video1, and @Audio1 for references.", "title": "Prompt", "x-sr-order": 200 }, "duration": { "default": -1, "description": "Output duration: 4–30 seconds, or -1 for automatic/follow-input behavior.", "title": "Duration", "type": "integer", "x-sr-order": 403 }, "generate_audio": { "default": true, "description": "Whether to generate synchronized audio.", "title": "Generate Audio", "type": "boolean", "x-sr-order": 501 }, "omni_reference_task_type": { "anyOf": [ { "enum": [ "auto", "reference", "edit", "extend" ], "type": "string" }, { "type": "null" } ], "description": "Optional Ark task-type pin. Edit requires duration=-1; edit/extend require adaptive ratio.", "title": "Omni Reference Task Type", "x-sr-order": 404 }, "output_format": { "default": "mp4", "description": "Output container.", "enum": [ "mp4", "mov" ], "title": "Output Format", "type": "string", "x-sr-order": 405 }, "ratio": { "default": "adaptive", "description": "Output aspect ratio. Edit and extend tasks require adaptive.", "enum": [ "21:9", "16:9", "4:3", "1:1", "3:4", "9:16", "adaptive" ], "title": "Ratio", "type": "string", "x-sr-order": 402 }, "reference_audios": { "anyOf": [ { "items": { "anyOf": [ { "format": "uri", "maxLength": 2083, "minLength": 1, "type": "string" }, { "type": "string" } ] }, "maxItems": 5, "minItems": 0, "type": "array" }, { "type": "null" } ], "description": "Up to 5 wav/mp3 references, 2–30 seconds each and 30 seconds total. Audio-only input is supported.", "title": "Reference Audios", "x-sr-order": 303 }, "reference_images": { "anyOf": [ { "items": { "anyOf": [ { "format": "uri", "maxLength": 2083, "minLength": 1, "type": "string" }, { "type": "string" } ] }, "maxItems": 10, "minItems": 0, "type": "array" }, { "type": "null" } ], "description": "Up to 10 reference images.", "title": "Reference Images", "x-sr-order": 301 }, "reference_videos": { "anyOf": [ { "items": { "anyOf": [ { "format": "uri", "maxLength": 2083, "minLength": 1, "type": "string" }, { "type": "string" } ] }, "maxItems": 5, "minItems": 0, "type": "array" }, { "type": "null" } ], "description": "Up to 5 reference videos, 2–30 seconds each and 30 seconds total (4–30 seconds for edit).", "title": "Reference Videos", "x-sr-order": 302 }, "resolution": { "default": "720p", "description": "Output resolution. Seedance 2.5 Flash supports 480p and 720p.", "enum": [ "480p", "720p" ], "title": "Resolution", "type": "string", "x-sr-order": 401 } }, "title": "ReferenceToVideoInput", "type": "object" } ``` ### Model output schema The model output schema is: ```json { "properties": { "fps": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "title": "Fps" }, "seed": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "title": "Seed" }, "duration": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "title": "Duration" }, "ratio": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Ratio" }, "resolution": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Resolution" }, "total_tokens": { "description": "Authoritative billed token count.", "title": "Total Tokens", "type": "integer" }, "units": { "description": "Billing units; 1,000 units equal USD 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": "Seedance25FlashOutput", "type": "object" } ``` ## Example inputs and outputs Use the following example inputs and outputs to understand the model. ### Input example ```json { "prompt": null, "duration": -1, "generate_audio": true, "omni_reference_task_type": null, "output_format": "mp4", "ratio": "adaptive", "reference_audios": null, "reference_images": null, "reference_videos": null, "resolution": "720p" } ``` ### Output example ```json { } ``` ## Model code examples ### JavaScript ```javascript import { sunra } from "@sunra/client"; const result = await sunra.subscribe("bytedance/seedance-2.5-flash/reference-to-video", { input: { prompt: null, reference_images: null, reference_videos: null, reference_audios: null, resolution: '720p', ratio: 'adaptive', duration: -1, omni_reference_task_type: null, output_format: 'mp4', generate_audio: true }, 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-flash/reference-to-video", arguments={ "prompt": None, "reference_images": None, "reference_videos": None, "reference_audios": None, "resolution": "720p", "ratio": "adaptive", "duration": -1, "omni_reference_task_type": None, "output_format": "mp4", "generate_audio": True }, 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-flash/reference-to-video", SubscribeOptions.builder() .input(Map.of( "prompt", null, "reference_images", null, "reference_videos", null, "reference_audios", null, "resolution", "720p", "ratio", "adaptive", "duration", -1, "omni_reference_task_type", null, "output_format", "mp4", "generate_audio", true)) .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( endpointId = "bytedance/seedance-2.5-flash/reference-to-video", input = mapOf( "prompt" to null, "reference_images" to null, "reference_videos" to null, "reference_audios" to null, "resolution" to "720p", "ratio" to "adaptive", "duration" to -1, "omni_reference_task_type" to null, "output_format" to "mp4", "generate_audio" to true), 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-flash/reference-to-video \ --header "Authorization: Key $SUNRA_KEY" \ --header "Content-Type: application/json" \ --data '{"prompt":null,"reference_images":null,"reference_videos":null,"reference_audios":null,"resolution":"720p","ratio":"adaptive","duration":-1,"omni_reference_task_type":null,"output_format":"mp4","generate_audio":true}' ``` ## Model readme >