> ## Documentation Index > Fetch the complete documentation index at: https://powower.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Vidu Reference-to-Video viduq4-preview > Use Vidu's latest flagship model (preview) viduq4-preview to generate a video based on reference images and reference audio. This model supports referencing 1-15 images and 0-3 audio files. After submitting a task, query its status via `GET /vidu/ent/v2/tasks/{task_id}/creations`. Uses model viduq4-preview. ## OpenAPI ````yaml api-reference/en/zmodelVideo/vidu/viduq4-preview-reference-to-video.json POST /vidu/ent/v2/reference2video openapi: 3.0.1 info: title: Vidu Reference-to-Video (viduq4-preview) version: 1.0.0 servers: - url: https://baze-api.powerbuyin.top security: [] paths: /vidu/ent/v2/reference2video: post: summary: Vidu Reference-to-Video (viduq4-preview) description: >- Use Vidu's latest flagship model (preview) viduq4-preview to generate a video based on reference images and reference audio. This model supports referencing 1-15 images and 0-3 audio files. After submitting a task, query its status via `GET /vidu/ent/v2/tasks/{task_id}/creations`. Uses model viduq4-preview. operationId: viduReferenceToVideoEnViduq4Preview requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ReferenceToVideoRequest' examples: basic_reference_video: summary: Reference-to-video example value: model: viduq4-preview images: - >- https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-1.png - >- https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-2.png - >- https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-3.png sounds: - >- https://scene-aliyun.vidu.zone/media-asset/022634-H3gq7ivRZgfAYKs3.mp3 prompt: >- In the scene of reference image 1, reference image 2 uses reference audio 1 and says to reference image 3: "What are you doing?", reference image 3 excitedly says: "q4 is a big hit!!!" duration: 5 seed: 0 aspect_ratio: '3:4' resolution: 1080p with_4k_resolution: summary: 4K resolution example value: model: viduq4-preview images: - >- https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-1.png prompt: >- Cinematic shot: an astronaut walks slowly on the lunar surface, camera pulls back from close-up to wide shot. audio: true duration: 8 resolution: 4K responses: '200': description: Submission successful, returns a video task object. content: application/json: schema: $ref: '#/components/schemas/ReferenceToVideoResponse' examples: success: summary: Submission successful value: task_id: your_task_id_here state: created model: viduq4-preview images: - >- https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-1.png - >- https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-2.png - >- https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/reference2video-3.png sounds: - >- https://scene-aliyun.vidu.zone/media-asset/022634-H3gq7ivRZgfAYKs3.mp3 prompt: >- In the scene of reference image 1, reference image 2 uses reference audio 1 and says to reference image 3: "What are you doing?", reference image 3 excitedly says: "q4 is a big hit!!!" duration: 5 seed: 123456789 resolution: 1080p payload: '' credits: 10 created_at: '2025-01-01T15:41:31.968916Z' '400': description: Invalid request parameters. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: invalid_request: summary: Invalid parameters value: code: bad_request_body message: Request body format error or invalid field values data: null '401': description: Authentication failed. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: unauthorized: summary: Unauthorized value: code: access_denied message: Invalid token data: null '429': description: Rate limit exceeded or insufficient quota. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: quota_exceeded: summary: Insufficient quota value: code: insufficient_user_quota message: Insufficient account quota, please try again later data: null '500': description: Internal server error. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: server_error: summary: Server error value: code: internal_server_error message: Internal server error, please try again later data: null security: - BearerAuth: [] components: schemas: ReferenceToVideoRequest: type: object required: - model - images - prompt properties: model: type: string enum: - viduq4-preview description: >- Model name. Available value: viduq4-preview - viduq4-preview: Vidu's latest flagship model (preview), supports referencing 1-15 images and 0-3 audio files images: type: array minItems: 1 maxItems: 15 items: type: string description: >- Supports multiple images. The model generates a video with subject consistency based on the subjects in the images provided. Requirements: Note 1: viduq4-preview model supports uploading 1-15 images; Note 2: Supports image Base64 encoding or image URL (ensure accessibility); Note 3: Supports png, jpeg, jpg, webp formats, max 50MB per image; Note 4: http request post body must not exceed 20MB, and encoding must include an appropriate content-type string, e.g.: data:image/png;base64,{base64_encode} sounds: type: array maxItems: 3 items: type: string description: >- Supports uploading 0-3 audio files. The model uses the audio provided as reference to generate a video with subject consistency. Note 1: Each reference audio duration range is 3-12s; Note 2: Supports mp3 format; Note 3: Each audio file must not exceed 50MB; Note 4: http request post body must not exceed 20MB, and encoding must include an appropriate content-type string, e.g.: data:video/mp3;base64,{base64_encode} prompt: type: string maxLength: 20000 description: |- Text prompt for video generation. Note: Character length must not exceed 20000 characters audio: type: boolean default: true description: >- Whether to use audio-visual direct output - false: no audio-visual direct output, outputs a silent video - true: requires audio-visual sync, outputs a video with sound (including dialogue and sound effects) Note: viduq4-preview model default is true duration: type: integer description: |- Video duration parameter Default: 5 Enum: 3 - 16 minimum: 3 maximum: 16 default: 5 seed: type: integer description: >- Random seed. When not provided or set to 0, a random number is used; when manually set, the configured seed is used. aspect_ratio: type: string enum: - '16:9' - '9:16' - '1:1' - '3:4' - '4:3' default: '16:9' description: |- Video aspect ratio parameter Default: 16:9 Enum: 1:1 / 9:16 / 16:9 / 3:4 / 4:3 resolution: type: string enum: - 540p - 720p - 1080p - 2K - 4K description: |- Video resolution parameter Default: 720p Enum: 540p / 720p / 1080p / 2K / 4K Note: viduq4-preview supports 2K and 4K video output payload: type: string maxLength: 1048576 description: >- Passthrough parameter, no processing, only data transmission. Note: maximum 1048576 characters. watermark: type: boolean default: false description: >- Whether to add watermark - true: add watermark - false: no watermark Note: Currently watermark content is fixed and AI-generated; not added by default wm_position: type: integer description: >- Watermark position, indicating where the watermark appears on the image. Options: 1: top-left 2: top-right 3: bottom-right 4: bottom-left Default: 3 default: 3 enum: - 1 - 2 - 3 - 4 minimum: 1 maximum: 4 x-options: - label: Top-left value: 1 - label: Top-right value: 2 - label: Bottom-right value: 3 - label: Bottom-left value: 4 wm_url: type: string description: >- Watermark content. This is an image URL; when not provided, the default watermark (AI-generated content) is used. meta_data: type: string description: >- Metadata identifier, a JSON format string passthrough field. You can customize the format or use the example format below: { "Label": "your_label","ContentProducer": "your_content_producer","ContentPropagator": "your_content_propagator","ProduceID": "your_product_id", "PropagateID": "your_propagate_id","ReservedCode1": "your_reserved_code1", "ReservedCode2": "your_reserved_code2" } When this parameter is empty, the Vidu-generated metadata identifier is used by default. callback_url: type: string description: >- Callback protocol You need to actively set callback_url when creating a task. The request method is POST. When the video generation task changes status, Vidu will send a callback request containing the latest task status to this address. The callback request body structure is consistent with the query task API response body. The "status" returned by the callback includes the following states: - processing: task is being processed - success: task completed (if sending fails, callback retries three times) - failed: task failed (if sending fails, callback retries three times) Vidu uses a callback signature algorithm for authentication, see: https://platform.vidu.cn/docs/callback-signature ReferenceToVideoResponse: type: object properties: task_id: type: string description: Task ID generated by Vidu. state: type: string enum: - created - queueing - processing - success - failed description: |- Processing state Available values: created: task created successfully queueing: task in queue processing: task being processed success: task succeeded failed: task failed model: type: string description: Model name used for this call. prompt: type: string description: Prompt parameter used for this call. images: type: array items: type: string description: Image parameter used for this call. sounds: type: array items: type: string description: The sound parameter for this call duration: type: integer description: Video duration parameter used for this call. seed: type: integer description: Random seed parameter used for this call. resolution: type: string description: Resolution parameter used for this call. payload: type: string description: Passthrough parameter passed in for this call. credits: type: integer description: Number of credits consumed for this call. watermark: type: boolean description: Whether a watermark was used for this task submission. created_at: type: string format: date-time description: Task creation time. ErrorResponse: type: object properties: code: type: string description: Error code. message: type: string description: Error description message. data: type: object nullable: true description: Additional error data (optional). securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: JWT description: 'Pass `Authorization: Bearer ` in the request header.' ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.