Tạo tác vụ tạo ảnh

POST

/ent/v2/reference2image

• Tài liệu chính thức: https://platform.vidu.cn/docs/image-generation
• Tạo tác vụ tạo ảnh; trả về task_id hoặc chi tiết tác vụ
• Điều khiển bằng tham số yêu cầu

Authorizations

bearer

Type

HTTP (bearer)

Request Body

application/json

object

Text prompt
Text description for generation; max 2000 characters
Note: viduq2 supports text-to-image; when using viduq2 with no images uploaded, the model generates from this text

Model name
Allowed: viduq2, viduq1
viduq2: text-to-image, image edit, reference-to-image
viduq1: reference-to-image only

Random seed
If omitted or 0, a random value is used
If set manually, that seed is used

Image reference
viduq2: 0–7 images
viduq1: 1–7 images
The model uses subjects in these images as reference for generation.
Note 1: Base64 or image URL (must be accessible)
Note 2: png, jpeg, jpg, webp
Note 3: Min 128×128 pixels; aspect ratio under 1:4 or 4:1
Note 4: Max 50 MB
Note 5: HTTP POST body max 20 MB; encoding must include content type, e.g.:

data:image/png;base64,{base64_encode}

Aspect ratio (varies by model):
viduq1: default 16:9; 16:9, 9:16, 1:1, 3:4, 4:3
viduq2: default 16:9; 16:9, 9:16, 1:1, 3:4, 4:3, 21:9, 2:3, 3:2

• auto: same as first input image

Resolution (varies by model):
viduq1: default 1080p; 1080p only
viduq2: default 1080p; 1080p, 2K, 4K

Passthrough parameter
Not processed; data transfer only
Note: Max 1048576 characters

Callback URL (POST). Set when creating the task; Vidu sends status updates. Body matches query task API.
Callback status:

• processing: in progress
• success: completed (retried up to 3 times on failure)
• failed: failed (retried up to 3 times on failure)
  Vidu uses callback signature authentication

Responses

Thành công

Content-Type

application/json

object