Kirin V2.6 - Image to Video

API Notes

kirin_v2_6_i2v only supports video with sound when mode is pro and sound is on.

kirin_v2_6_i2v only supports both image and image_tail parameters when mode is pro.

kirin_v2_6_i2v generates silent video when both image and image_tail parameters are used (first and last frame mode).

Authentication

authorization string required

All APIs require authentication via Bearer Token.

Get API Key:

Visit API Key Management Page to get your API Key.

Usage:

Add to request header:

Authorization: Bearer YOUR_API_KEY

Parameters

model string required

Model ID to use for the request

Value: kirin_v2_6_i2v

---

image string required

Reference image

Supports Base64 encoded image or image URL (ensure accessible)

Please note, if you use Base64, ensure all image data parameters use Base64 encoding format. Do not add any prefix such as data:image/png;base64, before the Base64 string. The correct format should be the Base64 encoded string directly

Image requirements:
Format: .jpg, .jpeg, .png
File size: Less than 10MB
Dimensions: Width and height at least 300px, aspect ratio between 1:2.5 and 2.5:1

image parameter and image_tail parameter must have at least one, both cannot be empty at the same time

---

image_tail string

Reference image - tail frame control

Supports Base64 encoded image or image URL (ensure accessible)

Please note, if you use Base64, ensure all image data parameters use Base64 encoding format. Do not add any prefix such as data:image/png;base64, before the Base64 string. The correct format should be the Base64 encoded string directly

Image requirements:
Format: .jpg, .jpeg, .png
File size: Less than 10MB
Dimensions: Width and height at least 300px, aspect ratio between 1:2.5 and 2.5:1

image parameter and image_tail parameter must have at least one, both cannot be empty at the same time

Note: Only supported when mode is pro for first and last frame mode, and videos generated with first and last frame are silent

---

prompt string

Positive text prompt, maximum 2500 characters

Use <<<voice_1>>> to specify voice timbre, the number corresponds to the order of voices referenced in the voice_list parameter

A video generation task can reference at most 2 voice timbres. When specifying voice timbre, the sound parameter value must be on

The simpler the syntax structure, the better. For example: Man <<<voice_1>>> says: “Hello”

---

negative_prompt string

Negative text prompt, maximum 2500 characters

---

mode string

Video generation mode

std: Standard mode with high cost-effectiveness
pro: Professional mode, takes longer to generate videos but produces higher quality output

Options: std, pro

Default: std

---

sound string

Whether to generate sound simultaneously when generating video

Note: Only supported when mode is pro

Options: on, off

Default: off

---

voice_list array

List of voice timbres referenced when generating video

A video generation task can reference at most 2 voice timbres

When voice_list parameter is not empty and voice ID is referenced in the prompt parameter, the video generation task will be metered and billed as “with specified voice timbre”

---

duration string

Video duration in seconds

Options: 5, 10

Default: 5

---

watermark_info array

Whether to generate results with watermarks simultaneously

Defined via the enabled parameter, specific format as follows:

"watermark_info": {
  "enabled": boolean // true for generation, false for no generation
}

Custom watermarks are not currently supported

---

callback_url string

Callback notification address for this task result. If configured, the server will actively notify when the task status changes

---

external_task_id string

Custom task ID

User-defined task ID, will not overwrite the system-generated task ID when provided, but supports task query via this ID

Please note that uniqueness must be ensured under a single user

---

Polling

Since video generation takes time, you need to poll the task status after creation

The initial response returns the task ID and initial status. The actual generation results must be obtained through polling the task status endpoint

Response Format

error object

Error information. Only present when status is failed

code string

Error code

error_message string

Detailed error message

---

output array

Generation results. Only present when status is completed

content array

List of generated content

type string

Resource type, e.g., video

url string

Generated content URL

---

usage object

Usage statistics. Only present when status is completed

cost string

Total cost in USD

discount number

Discount amount

---

metadata object

Metadata information

---

Error Codes

Error Code	Description
002013095	Internal generation error
002013096	Result parsing error
002013097	HTTP error response
002013098	Status check error
002013099	Task creation error