Kling AI · video model
from 1.5 credits / second · every plan · price breakdown · API playground
Made with Kling 4 · Action and camera
Kling 4 is Kling AI’s fourth-generation video model. It makes 3 to 30 second clips with native sound at 720p or 1080p, from a text prompt or from a start image, with an optional end frame.
Original results
These examples use media produced for Made. Prompts are included when the production record allows them.
“A skateboarder kickflips down five concrete stairs in an empty parking garage at night, lands clean and rolls straight at the camera, sodium lights strobing overhead, the crack of the board and the roar of the wheels echoing, low handheld fisheye follow.”
“She slurps the noodles, bursts out laughing and points the chopsticks at the camera as the washer behind her starts to spin, a fluorescent tube flickers, the hum of the machines and the clink of chopsticks, handheld phone camera.”
“Wide shot: a thumb-sized man in a grey business suit rows a white teacup across a bubble bath as if it were a lake, a yellow rubber duck drifting past like a ship. Cut to a close-up of his little oar splashing through the foam. The camera pushes in as he looks up and waves at a giant hand reaching for the soap. Soft bathroom window light, water lapping, a faint whistled tune.”
“Use this image as the opening composition.”
“A single frame from the clip above, straight from Kling 4.”
“A single frame from the clip above, straight from Kling 4.”
These are the controls exposed by Made, which may be narrower than a provider’s full API.
Write a prompt on its own, or add a start image (and optionally an end frame) to anchor the clip.
Say what moves, how the camera follows it, and what we hear. Kling 4 generates audio with every clip.
Pick 16:9, 9:16, 1:1, or 21:9 for text-to-video, and any length from 3 to 30 seconds.
Clips start at 720p. Switch to 1080p for the take you keep.
video
Kling 3 Pro is the benchmark tier of Kling AI’s third-generation video model, generating 3 to 15 second clips with optional native audio and the cinematic motion the Kling line is known for.
Explore model →video
Kling O3 Pro is Kling AI’s realism-focused O3 line, generating 3 to 15 second clips with steady, believable motion and optional start and end frames for controlled transitions.
Explore model →video
Seedance 2.5 is ByteDance’s newest video model in Made, generating clips up to 30 seconds in a single pass with native audio at 480p to 1080p — the longest single-shot ceiling in the Made library.
Explore model →Turn any image into a captivating video. Upload a photo, describe the motion you want, and watch AI bring it to life with realistic movement, cinematic camera work, and professional quality.
See the tool →Create scroll-stopping product photos and marketing visuals in seconds. Describe your shot, pick your style, and get professional images ready for your store, social feed, or ad campaign.
See the tool →It is Kling AI’s fourth-generation video model, made by Kuaishou, and the newest Kling in Made.