Available now

Kling O3 Image: text to image

By Kuaishou

Kling O3 Image makes single images or a related series from a prompt or from up to 10 reference images, at 1K, 2K or 4K.

Model ID
Maker
Kuaishou

Input

Fields marked * are required. Review the price before generating.

Text prompt for image generation. Max 2500 characters.

Example prompt. Edit it or write your own.

Optional: Elements (characters/objects) for face control. Reference in prompt as @Element1, @Element2, etc.

1K: standard, 2K: high-res, 4K: ultra high-res.

Number of images to generate (1-9).

Additional settings

'single' for one image, 'series' for a series of related images.

Number of images in series (2-9).

Price$0.05 / run

You sign up first. Your settings are kept.

About this model

Overview

Kling O3 Image makes up to nine single images, or a series of two to nine related images, at 1K, 2K or 4K in eight aspect ratios from 21:9 to 9:16. Add elements, each a front photo of a character or object with one or three extra views, to keep faces and objects the same across images.

The image-to-image mode takes up to 10 reference images, which you name in the prompt by number, such as @Image1.

What you can build

  • A storyboard or comic sequence with the same character
  • A product shown in several scenes in one series
  • Character portraits that keep one face across images
  • New scenes that combine several reference images

Prompting tips

  • Choose series when the images should belong together; choose single for separate variations.
  • Name each element in the prompt as @Element1, @Element2 and so on, and add one or three extra views, not two.
  • In image-to-image, say what each reference brings, for example the jacket from @Image1 and the street from @Image2.

What to check

Inspect details, text and consistency across a series at full size.

Inputs

  • Prompt (required): Text prompt for image generation. Max 2500 characters.
  • Elements (optional): Optional: Elements (characters/objects) for face control. Reference in prompt as @Element1, @Element2, etc.
  • Resolution (optional): Image generation resolution. 1K: standard, 2K: high-res, 4K: ultra high-res. Options: 1K, 2K, 4K.
  • Result Type (optional): Result type. 'single' for one image, 'series' for a series of related images. Options: single, series.
  • Number of Images (optional): Number of images to generate (1-9).
  • Series Amount (optional): Number of images in series (2-9).
  • Aspect Ratio (optional): Aspect ratio of generated images. Options: 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3, 21:9.
  • Output Format (optional): The format of the generated image. Options: jpeg, png, webp.

Output and limits

  • Resolutions: 1K, 2K, 4K.
  • Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3, 21:9.
  • File formats: JPEG, PNG, WEBP.
  • Up to 9 images per run.
  • Small or dense text in the image can come out misspelled.
  • Hands, crowds and complex poses can show artifacts; generate a few variations and pick the best.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • up to, default options: $0.05 / run