Kling 4.0 image-to-video API animates one first-frame image into a clip up to 30 seconds with synchronized audio. Keep the source framing and try it online.
Provider: Kuaishou
Category: video generation
Endpoint: /v1/tasks
Status: Available
Cost: See live page pricing
Kling 4.0 Image-to-Video: animate a first-frame image into a 3-30 second clip with an optional motion prompt. Framing follows the source image when unspecified, at 720p/1080p with synchronized audio.
Pricing
Standard Usage
Ready for generation
Configure your parameters and click "Run" to see the output here.
Image-to-video results
Checks hair and fabric motion, a slow push-in, natural wave ambience and identity kept from the still.
Original prompt
She turns her head further toward the camera, hair and jacket moving in the wind, camera slowly pushes in, waves crashing on the rocks below, natural ambient sound
Choose by starting material, reference method, resolution, and shot-control requirements.
Kling 4.0 Image-to-Video animates one image into a three- to thirty-second clip at 720p or 1080p, with synchronized audio. Leave the aspect ratio empty and the output keeps the source image's framing.
The prompt is optional. The image defines composition and identity; the prompt only directs motion, camera and sound.
These specifications reflect the current HiAPI Kling 4.0 Image-to-Video request contract. Endpoint frames and multimodal references are separate input modes and should not be mixed.
Upload the frame, describe only the motion you want, then raise resolution once the movement is right.
The first frame defines subject, composition, and shape. Add a matching last frame only when the ending state must be fixed, leaving room for the intended motion.
Write the middle process in time order, state whether the camera is locked, preserve stable details, and place sound cues next to their matching events.
Start at 3 seconds to inspect endpoint continuity and subject stability, then increase duration or create the production task with kling-4.0/image-to-video.
This is a minimal asynchronous first-frame request. Use the API docs for callbacks, task retrieval, reference limits, and error handling.
curl --request POST 'https://api.hiapi.ai/v1/tasks' \
--header 'Authorization: Bearer YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
"model": "kling-4.0/image-to-video",
"input": {
"image_urls": [
"https://static.hiapi.ai/admin-assets/kling-4-0/2026/10/23/1792768230745-7143f510a8f7c77f-face-input.jpg"
],
"prompt": "She turns her head toward the camera, hair moving in the wind, slow push-in",
"duration": 5,
"resolution": "720p"
}
}'A publicly reachable jpeg or png URL inside the image_urls array, one image per request. That image becomes the opening frame of the clip.
Output follows the source image's ratio, so a portrait image stays portrait. Set aspect_ratio only when you want to override the original framing.
No. You can let the image move on its own, or describe motion, camera and mood in the prompt. The image already carries composition and style, so shorter prompts often work better.
Per output second, same as text-to-video, with separate tiers for 720p and 1080p and no minimum charge.
Yes. Audio is generated together with the picture and the MP4 carries a soundtrack. Describe the sound you want in the prompt.
Send an asynchronous task to POST /v1/tasks with model set to kling-4.0/image-to-video and image_urls plus optional prompt, duration, resolution and aspect_ratio in input.
HiAPI Blog
