Video model guide

Kling 2.5 Turbo Pro video generation with a negative prompt and a strength control

Generate from a description or animate one starting picture, in 5 or 10 seconds. Both workspaces carry a negative prompt and a CFG Scale field, and the image entry takes a closing frame.

Controls and specifications

Kling 2.5 Turbo Pro appears as one entry in each workspace. Both offer 5 or 10 seconds, a description of up to 2500 characters, a negative prompt and a CFG Scale field that shapes how closely the result follows the prompt. Neither workspace offers a resolution setting.

Text mode offers 16:9, 9:16 and 1:1. Image mode accepts one starting image and an optional closing frame, with no aspect-ratio selector. Its negative prompt has a lower character limit than text mode.

Clip length
5 · 10 s
Audio
No audio on/off control
Shape options in text mode
16:9 · 9:16 · 1:1
Prompt limit
2500 characters

Choose 5 or 10 seconds, and a shape from 16:9, 9:16 or 1:1 in text mode. Both workspaces take a negative prompt and an optional CFG Scale from 0 to 1; in image mode the negative prompt is capped at 500 characters against 2500 in text mode. There is no resolution setting and no sound switch on either entry.

What this model is good at

A steer for the details you do not want

The negative prompt describes what to keep out of the frame. Use it for recurring artefacts such as stray text or unwanted hands, and save the wording with the rest of a brief so the next task starts from the same place.

A strength control on the same entry

CFG Scale runs from 0 to 1 and is optional. Lower values leave the model more room, higher values hold it closer to the description, and the field starts empty so a task can be sent without touching it.

A closing frame in the image workspace

Give the image entry a starting picture and a closing picture and describe the move between them. The result is one clip rather than two that have to be joined.

Typical projects

Prepare a product shot

Describe the shot and use the negative prompt to request exclusions. Check labels, lettering and fine details in the result before publishing.

Move between two stills

Start from an approved product image, add the composition the clip should land on, and describe the move. One task covers the whole move instead of two that have to be matched in the edit.

Change one control at a time

Keep the description fixed when comparing CFG Scale values. Review the result before deciding whether to change the wording or the setting.

Limits to know before you start

  • Neither workspace offers a resolution setting, so there is no tier to compare. Prepare the source picture at the size you need and check the delivered file before publishing.
  • Generated clips can include audio. Neither entry has a sound on/off switch; review the soundtrack and mute it in your editor when you need silence.
  • The image entry accepts one starting picture plus one optional closing frame, and nothing else. There is no second start frame, no reference set and no named subject, product or voice material.
  • Image mode has no aspect-ratio selector. Use a suitably composed source and check the output framing; exact framing is not guaranteed.
  • Descriptions are capped at 2500 characters and are required in the text workspace; in the image workspace an empty description is sent as a short instruction asking for natural motion. The negative prompt is a separate field with a cap of 500 characters in image mode against 2500 in text mode, and there is no seed field.

How to start

1

Open the workspace

Use a button on this page. It opens the right workspace with this model already selected, in the language you are reading now.

2

Describe the result

Write what should happen in the shot or image. Concrete subjects, framing and action give the model more to work with than short labels.

3

Set the controls and confirm

Choose length or quality tier, shape and sound where offered, then read the credit quote for those exact settings before you generate.

What it costs

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 packages

Questions about this model

Is this the same product as Kling 2.6 or Kling 3.0?

No. The selector lists Kling 2.5 Turbo Pro as its own entry next to them, with its own controls. Neither workspace on this entry offers a resolution setting, which is the clearest difference from Kling 3.0.

How long can the clip be?

5 or 10 seconds, in both the text and the image workspace. The two lengths are the only options, so plan the shot around one of them.

What does the CFG Scale field do?

It is an optional value from 0 to 1 that shapes how closely the result follows the description. Lower values leave the model more room, higher values hold it closer. Leave it empty to send the default behaviour.

Can I set the shape of the video?

Text mode offers 16:9, 9:16 and 1:1. Image mode has no aspect-ratio selector; review the generated framing before use.

Does it generate sound?

Generated clips can include audio. Neither entry has a sound on/off switch; review the soundtrack and mute it in your editor when you need silence.

What does a task cost?

The figure follows the entry and the length you pick, and the workspace shows the total for those exact settings before you confirm.