kwaivgi/kling-video/v2.5-turbo/pro/image-to-video

Name: Kling Video V2.5 Turbo Pro
Author: KwaiVGI

Kling Video V2.5 Turbo Pro is KwaiVGI's image-to-video AI model. Bring static images to life with fluid animation, consistent character motion, and professional-grade video output.

Input

Prompt(string)

Image URL or upload(string)

Upload

PNG, JPEG, WebP, or GIF · 20 MiB maximum

URL of the image to be used for the video

This field is required.

Image URL or upload(string)

Upload

PNG, JPEG, WebP, or GIF · 20 MiB maximum

URL of the image to be used for the end of the video

Duration(integer)

The duration of the generated video in seconds Allowed values: 5, 10.

Idle

Example output — click Run to generate your own

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run

Model IDkwaivgi/kling-video/v2.5-turbo/pro/image-to-video

Input Schema

4 parameters · 2 required · 2 optional

Parameter	Type	Required	Description
`image`	string	Required	URL of the image to be used for the video
`prompt`	string	Required	Max length: 2500
`duration`	integer	Optional	The duration of the generated video in seconds · Options: 5, 10 · Default: 5 510
`end_image`	string	Optional	URL of the image to be used for the end of the video

Output Schema

Field	Type	Description
`id`	string	Unique identifier for the generation task
`status`	string	Task status: pending, running, completed, failed, timeout
`model`	string	Model used for the generation
`outputs`	array	Array of output items
`outputs[].url`	string	URL of the generated artifact
`outputs[].content_type`	string	MIME type (e.g. image/png, video/mp4)
`error`	object \| null	Error details if failed, null on success
`error.type`	string	Machine-readable error type code
`error.message`	string	Human-readable error description

Async Workflow

This model uses asynchronous execution. Submit a request and poll for the result.

Submit — POST to /v1/run, receive an id
Poll — GET /v1/run/{id} until status is completed, failed, or timeout
Retrieve — Read outputs from the completed response

Code Examples

Ready-to-run snippets

# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "kwaivgi/kling-video/v2.5-turbo/pro/image-to-video",
  "image": "https://v3.fal.media/files/panda/HnY2yf-BbzlrVQxR-qP6m_9912d0932988453aadf3912fc1901f52.jpg",
  "prompt": "A stark starting line divides two powerful cars, engines revving for the challenge ahead. They surge forward in the heat of competition, a blur of speed and chrome. The finish line looms as they vie for victory.",
  "duration": 5
}'

# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
  -H "Authorization: Bearer YOUR_API_KEY"

← Back to Kling Video V2.5 Turbo Pro

API README

Kling Video V2.5 Turbo Pro Image-to-Video

Kling Video V2.5 Turbo Pro Image-to-Video converts a prepared opening frame into a short clip. The required prompt describes how subjects and the camera should move, while an optional ending image can define the destination of the transition. The route returns either a 5- or 10-second video URL.

This workflow is intentionally compact: one image, one written direction, and a duration selection cover the primary request. It does not expose an audio control or a separate aspect-ratio setting locally. The model fits image-led iteration where the visual start has already been designed.

Highlights

Unparalleled motion fluidity. The exact V2.5 Turbo Pro image route explicitly highlights motion fluidity. This is the route's primary motion capability.
Cinematic visuals. Cinematic visual generation is named for this exact version and tier. The opening image supplies the composition that is animated.
Exceptional prompt precision. The exact route is documented for precise prompt response. Written motion and camera instructions guide the image animation.
Smoother, more stable motion. The official V2.5 Turbo announcement reports smoother and more stable visuals with more accurate real-world physics. This applies to the V2.5 Turbo model's image-to-video capability.

Pricing

Duration	Price
5 seconds	$0.35
10 seconds	$0.70

When to Use

✅ Good fit	❌ Consider alternatives
Animate a racing, sports, or action keyframe for a concept cut.	Generate the scene without an opening image; use text-to-video.
Test a camera-heavy idea from an approved storyboard frame.	Need generated audio in the same request.
Make a five-second previsualization for rapid review.	Need a duration other than 5 or 10 seconds.
Use ten seconds for a longer action progression.	Need to choose frame shape independently of the image.
Connect an opening and ending keyframe in a silent clip.	Need controls beyond image, prompt, duration, and optional end image.

Prompt Guide

Describe motion relative to the supplied opening image. State the subject action, camera path, environmental movement, and the desired final state.

Subject action: [movement over time]
Camera: [framing and movement]
Environment: [light and background motion]
Timing: [pace and progression]
Prompt emphasis: [details that must be followed precisely]
Final state: [arrival at the optional end image]

{
  "image": "<start-image-url>",
  "prompt": "Two powerful cars surge forward from the starting line in a blur of speed and chrome as the camera tracks beside them.",
  "duration": 5
}

Technical Specs

Spec	Value
Required inputs	`image`, `prompt`
Prompt length	Up to 2,500 characters
Duration	5 or 10 seconds; default 5
Frame guidance	Required `image`; optional `end_image`
Native audio	Not exposed by this local route
Output	Video URL with optional file metadata

Kling Video V2.5 Turbo Pro Text-to-Video — Generate without a starting image.
Kling Video V2.6 Pro Image-to-Video — Use the newer Pro image route.