kwaivgi/kling-v4-flash

Kling 4.0 Flash: a faster, cheaper Kling 4.0 that makes 3 to 20 second 720p videos with sound from text, a first frame, reference images, or reference videos, and edits existing videos

95 runs
Playground API Examples README

Kling 4.0 Flash

Kling 4.0 Flash is the lighter, faster version of Kuaishou’s Kling 4.0. It makes 720p videos from 3 to 20 seconds long, with sound, for about 40% less than Kling 4.0 at 720p.

It’s built for when you want lots of drafts quickly: testing ideas, social clips, ad variations, or previews before you spend more on a final render.

What you can do with it

Text to video. Describe a scene and get a video back. Pick the aspect ratio (16:9, 9:16, 1:1, or 21:9) and a duration from 3 to 20 seconds.

First frame to video. Give it a start_image and describe what happens next. The output takes its aspect ratio from your image.

Reference images. Pass up to 10 images of characters, products, places, or styles with reference_images, then point at them in your prompt as @image_1, @image_2, and so on.

Reference videos. Use reference_videos to borrow camera movement, motion, or style from existing footage. Refer to them in the prompt as @video_1, @video_2, and so on.

Video editing. Set base_video and describe the change, like “change the background of @video_1 to a tropical beach”. The output keeps the length and aspect ratio of the original video.

How it’s different from Kling 4.0

  • 720p only. Kling 4.0 also does 1080p.
  • Videos up to 20 seconds. Kling 4.0 goes up to 30.
  • Only a first frame for keyframes. If you need an end frame or frames in the middle, use Kling 4.0.
  • Cheaper and faster.

How references are numbered

Images are numbered in this order: start_image, then reference_images. So if you set a start image and two reference images, the start image is @image_1 and the references are @image_2 and @image_3.

Videos are numbered with base_video first, then reference_videos.

Limits

  • Up to 10 images in total, including start_image.
  • Up to 5 videos in total across base_video and reference_videos.
  • Each input video must be 3 to 20 seconds long, and all input videos together can’t add up to more than 20 seconds.
  • Input videos must be .mp4 or .mov, 700 to 4553 pixels per side, at most 300 MB, with an aspect ratio between 2:5 and 5:2.
  • Images can be up to 30 MB, with an aspect ratio between 2:5 and 5:2.
  • Prompts can be up to 26,000 English characters or 11,000 non-English characters.

Pricing

You pay per second of video:

  • Text, first frame, or reference image inputs: $0.094 per second.
  • With any video input (base_video or reference_videos): $0.063 per second. Billed seconds are the output length plus whichever is longer, the input videos or the output. For example, editing a 5 second video into a 5 second output bills 10 seconds.

Tips for writing prompts

  • Describe the subject, the action, the setting, and the camera, in that order. “A red fox trots across a snowy meadow at sunrise, cinematic tracking shot” works better than “fox in snow”.
  • Describe the sound too, if you care about it: “crunching footsteps and distant birdsong”.
  • When you use references, say what each one is for: “the woman from @image_1 walks into the room from @image_2”.

Privacy policy

https://app.klingai.com/global/dev/document-api/protocols/privacyPolicy

API terms

https://app.klingai.com/global/dev/document-api/protocols/paidServiceProtocol

Service level agreement

https://app.klingai.com/global/dev/document-api/protocols/paidLevelProtocol

Model created
Model updated