> ## Documentation Index > Fetch the complete documentation index at: https://docs.modellix.ai/llms.txt > Use this file to discover all available pages before exploring further. # HappyHorse 1.1 R2V > [Core Function] HappyHorse 1.1 R2V is Alibaba's latest reference-image-to-video model. [Strengths] It uses 1-9 reference images to preserve subject or character appearance while generating new video actions, supports 720P/1080P output, 3-15 second duration, and expanded aspect ratios including 4:5, 5:4, 9:21, and 21:9. [Best For] Highly recommended for: character-consistent storytelling, reference-based product shots, and multi-image subject composition. [Limitations] Do NOT use if the user simply wants to animate a single image exactly as provided; use HappyHorse I2V instead. [Routing] Use when the user provides one or more reference images and asks for a newly generated HappyHorse video. ## OpenAPI ````yaml /model-api/alibaba/alibaba-i2v.json post /alibaba/happyhorse-1.1-r2v openapi: 3.1.0 info: description: The image-to-video models API from Alibaba. version: 1.0.0 contact: name: Modellix Support email: support@modellix.ai title: Alibaba Image-to-Video Models API servers: - url: https://api.modellix.ai/api/v1 description: The image-to-video models API from Alibaba. security: - bearerAuth: [] paths: /alibaba/happyhorse-1.1-r2v: post: summary: HappyHorse 1.1 R2V description: >- [Core Function] HappyHorse 1.1 R2V is Alibaba's latest reference-image-to-video model. [Strengths] It uses 1-9 reference images to preserve subject or character appearance while generating new video actions, supports 720P/1080P output, 3-15 second duration, and expanded aspect ratios including 4:5, 5:4, 9:21, and 21:9. [Best For] Highly recommended for: character-consistent storytelling, reference-based product shots, and multi-image subject composition. [Limitations] Do NOT use if the user simply wants to animate a single image exactly as provided; use HappyHorse I2V instead. [Routing] Use when the user provides one or more reference images and asks for a newly generated HappyHorse video. operationId: happyhorse11R2vAsync requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/Happyhorse11R2vRequest' examples: single_image: summary: Single reference image value: reference_images: - https://example.com/girl.jpg prompt: >- A woman character1 wearing a red qipao, the camera moves smoothly multiple_images: summary: Multiple reference images with character references value: reference_images: - https://example.com/girl.jpg - https://example.com/fan.jpg - https://example.com/earrings.jpg prompt: >- A woman character1 in a red qipao, gracefully opens a folding fan character2 as her tassel earrings character3 sway with head movement resolution: 1080P ratio: '16:9' duration: 5 advanced: summary: Advanced with all parameters value: reference_images: - https://example.com/person.jpg - https://example.com/object1.jpg - https://example.com/object2.jpg prompt: >- Character1 interacts with object character2 and character3 in a cinematic scene resolution: 1080P ratio: '16:9' duration: 10 seed: 12345 vertical_video: summary: Vertical video format (9:16) value: reference_images: - https://example.com/portrait.jpg prompt: Character1 gracefully turns in front of the camera resolution: 1080P ratio: '9:16' duration: 5 maximum_images: summary: Maximum 9 reference images value: reference_images: - https://example.com/img1.jpg - https://example.com/img2.jpg - https://example.com/img3.jpg - https://example.com/img4.jpg - https://example.com/img5.jpg - https://example.com/img6.jpg - https://example.com/img7.jpg - https://example.com/img8.jpg - https://example.com/img9.jpg prompt: >- A complex scene featuring character1 through character9 interacting together resolution: 720P ratio: '16:9' duration: 15 image_reference_prompt: summary: Prompt using image references value: reference_images: - https://example.com/girl.jpg - https://example.com/fan.jpg prompt: >- [Image 1] character gracefully opens the folding fan from [Image 2] in a cinematic close-up resolution: 1080P ratio: '21:9' duration: 5 responses: '200': description: Task submitted successfully content: application/json: schema: $ref: '#/components/schemas/AsyncTaskResponse' components: schemas: Happyhorse11R2vRequest: type: object required: - reference_images - prompt properties: prompt: type: string description: >- Text prompt describing the scene and referencing images. Required. Use [Image 1], [Image 2], etc. to reference images in the reference_images array. Supports any language input. Maximum length: 5000 non-Chinese characters or 2500 Chinese characters (automatically truncated if exceeded). minLength: 1 maxLength: 5000 examples: - '[Image 1] character walks through a neon-lit city street' - >- [Image 1] character picks up the object from [Image 2] in a cinematic scene reference_images: type: array description: >- Array of reference image URLs. Supports 1-9 images. Images can be referenced in the prompt by position, such as [Image 1], [Image 2], following array order. Image requirements: JPEG/JPG/PNG/WEBP, short edge >= 400 pixels, 720P+ recommended, file size <= 20MB per image. Supports HTTP/HTTPS URLs. minItems: 1 maxItems: 9 items: type: string format: uri pattern: ^https?:// examples: - https://example.com/image1.jpg - https://example.com/image2.png resolution: type: string default: 1080P description: >- Video resolution level. The model automatically scales to the nearest total pixels based on the selected resolution enum: - 720P - 1080P ratio: type: string default: '16:9' description: Video aspect ratio. Determines the output video dimensions enum: - '16:9' - '9:16' - '1:1' - '4:3' - '3:4' - '4:5' - '5:4' - '9:21' - '21:9' duration: type: integer default: 5 description: Video duration in seconds. Must be an integer between 3 and 15 minimum: 3 maximum: 15 enum: - 3 - 4 - 5 - 6 - 7 - 8 - 9 - 10 - 11 - 12 - 13 - 14 - 15 seed: type: integer description: >- Random seed for reproducibility. If not specified, the system generates a random seed. Note: Due to the probabilistic nature of model generation, even with the same seed, results may not be completely identical minimum: 0 maximum: 2147483647 AsyncTaskResponse: type: object required: - code - message - data properties: code: type: integer description: Response code, 0 indicates success example: 0 message: type: string description: Response message example: success data: type: object required: - status - task_id - model_id properties: status: type: string enum: - pending - processing description: Task status example: pending task_id: type: string description: Unique task identifier example: task-abc123 model_id: type: string description: Model ID example: model-123 get_result: type: object description: API information to query the task result properties: method: type: string description: HTTP method example: GET url: type: string description: Full URL to query the task result example: https://api.modellix.ai/api/v1/tasks/task-abc123 description: Detailed data about the submitted asynchronous task. securitySchemes: bearerAuth: type: http scheme: bearer description: 'API Key authentication. Format: `Bearer YOUR_API_KEY`.' ````