Generate from a description or animate one starting picture. Choose any whole length from 3 to 15 seconds, switch sound on or off, and pick between the Standard and the Pro product.
The workspace lists two Kling 3.0 products: Standard, labelled 720P, and Kling 3.0 Pro, labelled 1080P. Both share the same controls — a length slider from 3 to 15 seconds in whole seconds, a sound switch that starts switched off, and the same prompt box. You change the product in the model selector; neither offers a quality dropdown of its own.
Text mode needs only a description and offers three shapes: 16:9, 9:16 and 1:1. In the image workspace you add exactly one starting picture. That picture decides the proportions of the finished clip, so no shape selector is offered there, and you can leave the description empty — the workspace then sends a short instruction asking for natural motion.
Choose Standard or Pro in the model selector, set a whole-number length between 3 and 15 seconds, and use the sound switch if you want a track. Text mode offers 16:9, 9:16 and 1:1; with a starting picture the shape follows that picture. Descriptions are limited to 2000 characters and are required in the text workspace.
Slide from 3 to 15 seconds in whole seconds instead of choosing between two fixed lengths. Three seconds suit a single gesture or a product turn; longer runs leave room for an action with a beginning and an end. The figure updates as you move the slider.
A sound switch sits next to the length control and starts switched off. Turn it on when the clip should carry its own track, and leave it off when a score or a voice-over will arrive in the edit.
Use a product photo, poster or cover image as the starting frame. Choose an image composed for the placement you need, then inspect the generated framing before publishing.
Cut a 4-second product turn for a short piece or a 12-second establishing move for a longer one without changing products. The slider and the figure move together, so the length decision is settled before you confirm.
Keep the sound switch off when a voice-over or a music bed will carry the audio, then drop the clip into a timeline without having to mute a generated track first.
Start with a finished product image and describe the camera movement or action you want. Check the result for changes to product details and framing before using it in a campaign.
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 packagesBoth are listed in the model selector of the text and the image workspace. Standard is labelled 720P and Pro is labelled 1080P; the rest of the controls are the same. The number for your exact settings is shown before you confirm.
Any whole number of seconds between 3 and 15. The control is a slider, and the workspace updates the number as you move it.
Sound is optional and switched off by default. Enable it when you want generated audio, or leave it off to add your own soundtrack in editing.
The image workspace accepts one starting picture. A separate closing-frame field is not available.
2000 characters. The text workspace requires a description; in the image workspace you can leave it empty and the workspace sends a short instruction asking for natural motion.
Credits depend on duration, Standard or Pro, and whether sound is enabled. The workspace shows the total for your selected settings before generation.
Other models on this platform that do a similar job, or that pair well with this one.
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.
Read the guideKling 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 guide