Kling 4.0 Keyframe turns a description or an ordered set of frames into a clip of 3 to 30 seconds that travels between the pictures you supply.
Keyframes and reference materials are different inputs on this platform. This model takes ordered frames: one first frame, up to eight middle frames and one last frame, and the clip moves from one to the next. Named image, video, subject and voice materials belong to the separate Kling 4.0 Reference workspace.
The frame allowance depends on the length you choose. A 3-second task accepts 4 frames, the allowance grows by one frame per extra second, and from 9 seconds up all 10 frames are available. The workspace shows the limit for your duration and asks for fewer frames if you go past it.
Set length, quality tier and shape before you generate. Uploading frames removes the shape selector, because the first frame then decides the output shape.
Upload a first frame, optional middle frames and a last frame in that order to guide the sequence of compositions. Generated transitions may vary from your storyboard.
Pick any whole number of seconds between 3 and 30 at 720p or 1080p, with the frame allowance growing alongside the duration.
In text mode choose automatic, 16:9, 9:16, 1:1 or 21:9. Once frames are uploaded the output follows the first image, so the shape selector is not offered in that mode.
Supply a start, a middle and an end frame to guide a scene through three compositions.
Give several views of the same product as ordered frames and let one clip carry the move between them.
Upload a last frame to guide the closing composition, such as a product view or logo. Check the result before publishing.
Use a button on this page. It opens the right workspace with this model already selected, in the language you are reading now.
Write what should happen in the shot or image. Concrete subjects, framing and action give the model more to work with than short labels.
Choose length or quality tier, shape and sound where offered, then read the credit quote for those exact settings before you generate.
Generation uses account credits. Cost depends on the model, quality and output size or duration. Reference images, video or audio may add charges in some modes. Check the workspace quote for your selected inputs and settings before generating; the pricing page lists credit packages.
See credit packagesUp to ten in total: one first frame, up to eight middle frames and one last frame. The allowance also depends on length, because a 3-second task accepts 4 frames; the workspace shows the limit for the duration you set.
No. You can supply only a first frame, or a first and a last frame. Middle frames always sit between them in the order you upload.
No. Once frames are uploaded the output follows the first image, so the shape selector is only offered in text mode.
There is no sound on/off switch. The finished clip we checked carried a sound track, so plan to mute it if you need silence.
Per generated second at 720p or 1080p. The workspace shows the exact credit amount for the length and tier you pick before you confirm.
Other models on this platform that do a similar job, or that pair well with this one.
Kling 4.0 Reference builds a clip of 3 to 30 seconds from named materials: reference images, reference clips, subjects and voices, each addressed by name in the prompt.
Read the guideWan 3.0 is the standard variant of the Wan 3.0 family on this platform: a wide length range, three quality tiers and shape control in both text and image mode.
Read the guideSeedance 2.5 creates a clip from a written description or from one starting image, with whole-second lengths from 4 to 30 seconds and three quality tiers.
Read the guide