## Basic model info - Model name: minimax/minimax minimax-h3 - Model description: MiniMax H3: native-2K multimodal video model with text-to-video, first/last-frame image-to-video, and reference-based generation from up to 9 images, 3 video clips, and 3 audio tracks, with synchronized audio in one pass. - Endpoint name: reference-to-video ## Model schema The model schema is defined in the OpenAPI schema: [OpenAPI Schema](https://oapi.sunra.ai/main/minimax/minimax-h3/latest.json) ### Model input schema The model input schema is: ```json { "properties": { "prompt": { "description": "Text prompt for video generation. Refer to reference assets by their modality and order in the reference lists: Image 1, Image 2, Video 1, Audio 1, and so on.", "maxLength": 2000, "minLength": 1, "title": "Prompt", "type": "string", "x-sr-order": 200 }, "aspect_ratio": { "default": "adaptive", "description": "The aspect ratio of the generated video.", "enum": [ "adaptive", "21:9", "16:9", "4:3", "1:1", "3:4", "9:16" ], "title": "Aspect Ratio", "type": "string", "x-sr-order": 401 }, "duration": { "default": 5, "description": "The duration of the video in seconds.", "enum": [ 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 ], "title": "Duration", "type": "integer", "x-sr-order": 402 }, "reference_audios": { "anyOf": [ { "items": { "anyOf": [ { "format": "uri", "maxLength": 2083, "minLength": 1, "type": "string" }, { "type": "string" } ] }, "maxItems": 3, "type": "array" }, { "type": "null" } ], "description": "URLs of reference audio clips (up to 3, 2-15 seconds each, combined duration at most 15 seconds), referenced in the prompt as Audio 1, Audio 2, and so on. Audio cannot be the only reference input.", "title": "Reference Audios", "x-sr-order": 303 }, "reference_images": { "anyOf": [ { "items": { "anyOf": [ { "format": "uri", "maxLength": 2083, "minLength": 1, "type": "string" }, { "type": "string" } ] }, "maxItems": 9, "type": "array" }, { "type": "null" } ], "description": "URLs of subject/style reference images (up to 9), referenced in the prompt as Image 1, Image 2, and so on.", "title": "Reference Images", "x-sr-order": 301 }, "reference_videos": { "anyOf": [ { "items": { "anyOf": [ { "format": "uri", "maxLength": 2083, "minLength": 1, "type": "string" }, { "type": "string" } ] }, "maxItems": 3, "type": "array" }, { "type": "null" } ], "description": "URLs of motion/reference video clips (up to 3, 2-15 seconds each, combined duration at most 15 seconds), referenced in the prompt as Video 1, Video 2, and so on.", "title": "Reference Videos", "x-sr-order": 302 } }, "required": [ "prompt" ], "title": "ReferenceToVideoInput", "type": "object" } ``` ### Model output schema The model output schema is: ```json { "properties": { "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" ], "title": "VideoOutput", "type": "object" } ``` ## Example inputs and outputs Use the following example inputs and outputs to understand the model. ### Input example ```json { "prompt": "", "aspect_ratio": "adaptive", "duration": 5, "reference_audios": null, "reference_images": null, "reference_videos": null } ``` ### Output example ```json { } ``` ## Model code examples ### JavaScript ```javascript import { sunra } from "@sunra/client"; const result = await sunra.subscribe("minimax/minimax-h3/reference-to-video", { input: { prompt: '', reference_images: null, reference_videos: null, reference_audios: null, aspect_ratio: 'adaptive', duration: 5 }, 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( "minimax/minimax-h3/reference-to-video", arguments={ "prompt": "", "reference_images": None, "reference_videos": None, "reference_audios": None, "aspect_ratio": "adaptive", "duration": 5 }, 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( "minimax/minimax-h3/reference-to-video", SubscribeOptions.builder() .input(Map.of( "prompt", "", "reference_images", null, "reference_videos", null, "reference_audios", null, "aspect_ratio", "adaptive", "duration", 5)) .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 = "minimax/minimax-h3/reference-to-video", input = mapOf( "prompt" to "", "reference_images" to null, "reference_videos" to null, "reference_audios" to null, "aspect_ratio" to "adaptive", "duration" to 5), 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/minimax/minimax-h3/reference-to-video \ --header "Authorization: Key $SUNRA_KEY" \ --header "Content-Type: application/json" \ --data '{"prompt":"","reference_images":null,"reference_videos":null,"reference_audios":null,"aspect_ratio":"adaptive","duration":5}' ``` ## Model readme >