Create Video (Reference-Image-to-Video)

POST

/v1/videos

Note: Video duration is determined by the model ID; e.g. choosing gemini-veo-3.1-generate-preview-6s yields a 6-second video.

Model IDs:
The following models (up to 2 reference images):

gemini-veo-3.1-generate-preview-4s

gemini-veo-3.1-generate-preview-6s

gemini-veo-3.1-generate-preview-8s
The following models (up to 3 reference images):

gemini-veo-3.1-generate-preview-ref-4s

gemini-veo-3.1-generate-preview-ref-6s

gemini-veo-3.1-generate-preview-ref-8s

Request

Authorization

Provide your bearer token in the

Authorization

header when making requests to protected resources.

Example:

Authorization: Bearer ********************

Body Params application/jsonRequired

Example

{
    "model": "gemini-veo-3.1-generate-preview-ref-8s",
    "prompt": "The picture shows a woman in a red cheongsam. The camera first captures the tailored and S-shaped curve of the cheongsam from a side medium shot, then switches to a low-angle overhead shot to capture the details of the dangling pendant earrings as the lady gently raises her slender hand to unfold the fan, picture 2. The earrings swing gracefully with her head movement. Finally, it zooms in to a close-up of her face, freezing the subtle charm as she gently touches the fan ribs with her fingertips and her eyes move with a gentle expression. The picture presents the Eastern charm from multiple perspectives and in a comprehensive way.",
    "size": "720x1280",
    "images": [
        "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260424/mvzfud/hh-v2v-girl.jpg",
        "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260424/fvuihk/hh-v2v2-folding-fan.jpg",
        "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260424/imerii/hh-v2v-earrings.jpg"
    ]
}

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location 'https://www.aiide.com/v1/videos' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
    "model": "gemini-veo-3.1-generate-preview-ref-8s",
    "prompt": "The picture shows a woman in a red cheongsam. The camera first captures the tailored and S-shaped curve of the cheongsam from a side medium shot, then switches to a low-angle overhead shot to capture the details of the dangling pendant earrings as the lady gently raises her slender hand to unfold the fan, picture 2. The earrings swing gracefully with her head movement. Finally, it zooms in to a close-up of her face, freezing the subtle charm as she gently touches the fan ribs with her fingertips and her eyes move with a gentle expression. The picture presents the Eastern charm from multiple perspectives and in a comprehensive way.",
    "size": "720x1280",
    "images": [
        "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260424/mvzfud/hh-v2v-girl.jpg",
        "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260424/fvuihk/hh-v2v2-folding-fan.jpg",
        "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260424/imerii/hh-v2v-earrings.jpg"
    ]
}'

Responses

🟢200Success

application/json

Bodyapplication/json

Example

{
    "id": "string",
    "task_id": "string",
    "object": "string",
    "model": "string",
    "status": "string",
    "progress": 0,
    "created_at": 0
}

🟠429Rate Limit

🟠400Bad Request

Modified at 2026-09-10 06:20:41

Create Video (Text-to-Video)

Get Video Generation Task Status