kwaivgi/kling-video/v3/4k/image-to-video
Kling Video V3 4k by KwaiVGI - animate still images into dynamic videos with AI. Transform photos into cinematic clips with natural motion, camera movement, and optional audio generation.
Input
Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both.
PNG, JPEG, WebP, or GIF · 20 MiB maximum
URL of the image to be used for the video
This field is required.
PNG, JPEG, WebP, or GIF · 20 MiB maximum
URL of the image to be used for the end of the video
The duration of the generated video in seconds Allowed values: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15.
Whether to generate native audio for the video. Supports Chinese and English voice output. Other languages are automatically translated to English. For English speech, use lowercase letters; for acronyms or proper nouns, use uppercase.
The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure. Allowed values: customize, intelligent.
List of prompts for multi-shot video generation. If provided, divides the video into multiple shots.
Idle
Example output — click Run to generate your own
Production endpoint
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
POST
https://api.sandbase.ai/v1/runModel ID
kwaivgi/kling-video/v3/4k/image-to-video01
Input Schema
7 parameters · 2 required · 5 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
image | string | Required | URL of the image to be used for the video |
prompt | string | Required | Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both. · Max length: 2500 |
duration | integer | Optional | The duration of the generated video in seconds · Options: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 · Default: 5 3456789101112131415 |
end_image | string | Optional | URL of the image to be used for the end of the video |
shot_type | string | Optional | The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure. · Options: customize, intelligent · Default: "customize" customizeintelligent |
multi_prompt | object[] | Optional | List of prompts for multi-shot video generation. If provided, divides the video into multiple shots. |
generate_audio | boolean | Optional | Whether to generate native audio for the video. Supports Chinese and English voice output. Other languages are automatically translated to English. For English speech, use lowercase letters; for acronyms or proper nouns, use uppercase. · Default: true |
02
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, ortimeout - Retrieve — Read
outputsfrom the completed response
03
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/v3/4k/image-to-video",
"image": "https://storage.googleapis.com/falserverless/example_inputs/kling-v3/pro-i2v/start_image.png",
"prompt": "The craftsman slowly examines the bowl, turning it gently in his weathered hands. His eyes reflect years of wisdom. Subtle smile forms on his face. Dust particles drift in warm light. Breathing motion, blinking eyes.",
"duration": 12,
"shot_type": "customize",
"generate_audio": true
}'
# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
-H "Authorization: Bearer YOUR_API_KEY"API README
Kling Video V3 Native 4K Image-to-Video
Kling Video V3 Native 4K Image-to-Video is the image-led route for projects whose final video specification is 4K. A starting frame and written direction define the core request, with optional ending-frame and shot settings available for a more structured result. The route returns the finished video through a downloadable URL.
Durations range from 3 to 15 seconds, and audio can be included in the same request. The opening image supplies the composition and frame shape, so visual planning begins before generation. This workflow avoids adding a separate resolution-conversion stage after the clip is created.
Highlights
- Native 4K output. This exact V3 route directly outputs professional-grade 4K video in one step. It removes the need for post-production upscaling.
- Stable reference consistency. The model preserves element features, stylistic expression, color, lighting, and overall mood from the input image. Those characteristics remain the visual basis of the 4K motion.
- Realistic material response. The exact route describes natural response for skin, facial expressions, fabric, hair, metal, and liquid. This supports detailed portrait and close-up animation.
- Cinema-grade clarity. The route is documented for ultra-clear visuals that retain intricate input-image details. Sharpness, atmosphere, and lighting carry into the generated video.
Pricing
| Duration | Price |
|---|---|
| 3 seconds | $1.26 |
| 4 seconds | $1.68 |
| 5 seconds | $2.10 |
| 6 seconds | $2.52 |
| 7 seconds | $2.94 |
| 8 seconds | $3.36 |
| 9 seconds | $3.78 |
| 10 seconds | $4.20 |
| 11 seconds | $4.62 |
| 12 seconds | $5.04 |
| 13 seconds | $5.46 |
| 14 seconds | $5.88 |
| 15 seconds | $6.30 |
When to Use
| ✅ Good fit | ❌ Consider alternatives |
|---|---|
| Prepare a short clip for a large display or 4K master. | Use a lower-resolution sibling when the delivery does not need 4K. |
| Animate a product close-up where small surface details matter. | Create a scene without a starting image; use text-to-video. |
| Add subtle expression and hair or fabric movement to a portrait. | Need a single request longer than 15 seconds. |
| Transition between two approved keyframes for a campaign asset. | Need to select frame shape independently of the opening image. |
| Deliver picture and generated sound from one image-led request. | Need voice behavior outside the documented language handling. |
Prompt Guide
Describe the motion that should emerge from the opening image. Specify subject action, camera, material behavior, lighting continuity, sound, and the desired final state.
Subject motion: [action and expression]
Camera: [framing and path]
Materials: [fabric, hair, metal, liquid, or skin response]
Lighting and color: [details to carry into motion]
Audio: [ambience, effects, or speech when enabled]
End state: [arrival at the optional final image]
{
"image": "<start-image-url>",
"prompt": "The craftsman slowly examines the bowl, turning it gently in his hands. Dust particles drift through warm light while subtle breathing and blinking add natural motion.",
"duration": 5,
"generate_audio": true,
"shot_type": "customize"
}
Technical Specs
| Spec | Value |
|---|---|
| Required inputs | image, prompt |
| Prompt length | Up to 2,500 characters |
| Output resolution | Native 4K |
| Duration | 3–15 seconds; default 5 |
| Frame guidance | Required image; optional end_image |
| Multi-shot | multi_prompt with per-shot prompt and duration |
| Shot types | customize, intelligent |
| Native audio | Optional; default enabled |
| Output | Video URL with optional file metadata |
Related
- Kling Video V3 Pro Image-to-Video — Use the non-4K Pro image route.
- Kling Video V3 4K Text-to-Video — Generate native 4K video from text.