curl --request POST \
--url https://api.modellix.ai/api/v1/alibaba/happyhorse-1.1-r2v \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"reference_images": [
"https://example.com/girl.jpg"
],
"prompt": "A woman character1 wearing a red qipao, the camera moves smoothly"
}
'{
"code": 0,
"message": "success",
"data": {
"status": "pending",
"task_id": "task-abc123",
"model_id": "model-123",
"get_result": {
"method": "GET",
"url": "https://api.modellix.ai/api/v1/tasks/task-abc123"
}
}
}HappyHorse 1.1 R2V
Alibaba’s reference-to-video model for a scene that keeps several characters consistent, with native sound. It uses 1 to 9 reference images in a 3 to 15 second clip at 720P or 1080P.
curl --request POST \
--url https://api.modellix.ai/api/v1/alibaba/happyhorse-1.1-r2v \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"reference_images": [
"https://example.com/girl.jpg"
],
"prompt": "A woman character1 wearing a red qipao, the camera moves smoothly"
}
'{
"code": 0,
"message": "success",
"data": {
"status": "pending",
"task_id": "task-abc123",
"model_id": "model-123",
"get_result": {
"method": "GET",
"url": "https://api.modellix.ai/api/v1/tasks/task-abc123"
}
}
}Body
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).
1 - 5000"[Image 1] character walks through a neon-lit city street"
"[Image 1] character picks up the object from [Image 2] in a cinematic scene"
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.
1 - 9 elements^https?://