About Kling 4.0 - Image to Video
Kling 4.0 animates images into cinematic video with native audio, in single takes of 3 to 30 seconds at 720p or 1080p. Give it a first frame, a last frame, and up to 10 keyframes in total, and it moves smoothly through each one in order.
Keyframes make it suited to choreographed shots: a fashion walk that hits set poses, a product turning through planned angles, or a scene that travels between locations. Refer to frames in the prompt as @image_1, @image_2, and so on, counting from the first frame, to say what should carry over from each.
See what this model can do
A handful of real prompts and their outputs.
Ready to build with Kling 4.0 - Image to Video?
Try Kling 4.0 - Image to Video in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
curl -sSf -X POST https://hub.oxen.ai/api/ai/videos/generate \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OXEN_API_KEY" \
-d '{
"model": "kling-video-v4-0-image-to-video",
"prompt": "A cat sitting on a chair",
"resolution": "1080p",
"duration": 5
}'Request parameters
Every field Kling 4.0 - Image to Video accepts in the request body. See the API reference for response formats.
https://hub.oxen.ai/api/ai/videos/generate| Field | Type | Required | Default | Description |
|---|---|---|---|---|
prompt | string | Yes | — | Describe the motion, camera, and sound. Refer to frames as @image_1, @image_2, ... counting from the first frame. |
input_image | stringuri | No | — | Image the video starts on. |
keyframe_images | array<string> | No | — | Keyframes the video passes through between the first and last frame, in order. Up to 10 frames in total. |
tail_image_url | stringuri | No | — | Image the video ends on. |
resolution | string | No | "1080p" | 720p1080p |
duration | integer | No | 5 | Range: 3 – 30 |