Skip to main content
POST
/
v1
/
image_to_video
Create Image to Video Task
curl --request POST \
  --url https://api.keevx.com/v1/image_to_video \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "V",
  "prompt": "A golden retriever running in the grass, sunny day, cinematic lighting",
  "aspect_ratio": "16:9",
  "aspect_resolution": "1080p",
  "duration": 6,
  "image_url": "https://example.com/start_frame.jpg",
  "reference_images": [
    "https://example.com/ref1.jpg",
    "https://example.com/ref2.jpg"
  ],
  "generate_audio": true,
  "generate_count": 1,
  "callback_url": "https://your-server.com/callback"
}
'
{
  "code": 0,
  "msg": "ok",
  "data": {
    "task_ids": [
      "i2v-d6b6472bcf724d0399e06d1390cb964e",
      "i2v-fc654817587e435e937f1e1b80366c00"
    ]
  }
}

Documentation Index

Fetch the complete documentation index at: https://docs.keevx.com/llms.txt

Use this file to discover all available pages before exploring further.

​
Detailed Model Parameter Rules

Depending on the value of model, the required status and valid ranges for parameters are as follows:
Name: Standard Model-Start & End Frame VideoFeatures: Supports audio, multiple resolutions, and three image input modes.
ParameterRequiredDescription
promptYesLimited to 1000 characters.
image_urlNoRequired for Start-Frame Mode.
end_image_urlNoSupports end frame upload.
reference_imagesNoRequired for Multi-Image Mode. (Max 3 images)
aspect_resolutionYesSupports 720p, 1080p, 4k.
durationYesSingle-image: 4, 6, 8s; Multi-image: fixed at 8s.
generate_audioNoSupports audio configuration.

​
end_image_url bad case Notes

End frame aspect ratio should match start frame. Mismatch reduces quality.

​
Callback Notification

After the video generation task is processed, the service will send a POST request to the callback_url provided in the initiation request.

​
Structure

​
code
integer
Response status code. 0 indicates a successful callback transmission.
​
msg
string
Response message, usually “ok”.
​
task_type
string
The type of the task. Enum: image_to_video.
​
data
object
The payload containing the generation results.

​
Callback Example

{
    "code": 0,
    "msg": "ok",
    "task_type": "image_to_video",
    "data": {
        "task_id": "i2v-d6b6472bcf724d0399e06d1390cb964e",
        "status": "SUCCEEDED",
        "video_url": "https://storage.googleapis.com/xiling_us_central1_bucket/backend-saas-cdn/image-to-video/9966750584897124421/sample_0.mp4",
        "thumbnail_url": "https://storage.googleapis.com/xiling_us_central1_bucket/backend-saas-cdn/video-ai/tmp/image2video/veo/022934e6-b6d2-4d15-a320-cd60f6e43ae3/i2v-d6b6472bcf724d0399e06d1390cb964e.webp",
        "error_message": ""
    }
}

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

Create an image-to-video generation task. Supports models V, KL, and S.

​
model
enum<string>
required

Model identifier code.

  • V: Supports single/multi-image, audio, and 4k.
  • KL: Focused on multi-reference image mode.
  • S: Focused on single start-frame mode.
Available options:
V,
KL,
S
Example:

"V"

​
prompt
string
required

Prompt for video generation. Limit: 1000 characters.

Example:

"A golden retriever running in the grass, sunny day, cinematic lighting"

​
aspect_ratio
enum<string>
required

Video aspect ratio.

Available options:
16:9,
9:16
Example:

"16:9"

​
aspect_resolution
enum<string>
required

Video resolution.

  • Model V: 720p, 1080p, 4k
  • Model KL: 720p, 1080p
  • Model S: 720p (fixed)
Available options:
720p,
1080p,
4k
Example:

"1080p"

​
duration
enum<integer>
required

Video duration in seconds.

  • Model V: 4, 6, 8 (single); 8 (multi)
  • Model KL: 5, 10
  • Model S: 4, 8, 12
Available options:
4,
5,
6,
8,
10,
12
Example:

6

​
image_url
string<uri>

URL of the start frame image.

  • This field is required for Model S and Model V when using the Start-Frame mode.
  • Not used in Model KL.
  • Limit: Maximum file size is 20MB.
Example:

"https://example.com/start_frame.jpg"

​
reference_images
string<uri>[]

List of reference image URLs.

  • Required for Model KL and Model V (Multi-image mode).
  • Not used in Model S.
  • Limit: Maximum file size is 20MB.
Example:
[
  "https://example.com/ref1.jpg",
  "https://example.com/ref2.jpg"
]
​
generate_audio
boolean
default:false

Whether to generate audio. Only supported by Model V.

Example:

true

​
generate_count
integer
default:1

Number of videos to generate (1-4).

Required range: 1 <= x <= 4
Example:

1

​
callback_url
string<uri>

Callback URL for task completion notification.

Example:

"https://your-server.com/callback"

Response

Task created successfully

Task creation response wrapper

​
code
integer
required

Status code (0 indicates success)

Example:

0

​
msg
string
required

Response message

Example:

"ok"

​
data
object
required

Payload containing the generated task IDs