Available now

Krea 2 Large: text to image

By Krea

Krea 2 Large turns a written description into one image, with a creativity setting that decides how freely it reads your prompt.

Model ID
Maker
Krea

Input

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

Text description of the image to generate.

Example prompt. Edit it or write your own.

Additional settings

Random seed for reproducible generation.

Estimated total$0.10

You sign up first. Your settings are kept.

About this model

Overview

Krea 2 Large makes one image per run from a prompt of up to 5000 characters, in eight shapes from 2.35:1 cinema width to 9:16 tall. Its creativity setting runs from raw through low and medium to high: low values stay close to your words, high values take more liberties.

What you can build

  • Cinematic stills in the wide 2.35:1 format
  • Mood images and concept art for a pitch
  • Portrait shots for social posts in 4:5
  • Literal renders of a precise brief

Prompting tips

  • Use raw or low creativity when every detail of the prompt must show up; use high when you want surprises.
  • Write the light, the lens and the color palette into the prompt, such as 35mm film, low sun or muted greens.
  • Fix the seed and change only the creativity level to see how far the model drifts.

What to check

Check whether creativity changed important objects or layout. Inspect lettering and proportions at full size.

Inputs

  • Prompt (required): Text description of the image to generate.
  • Aspect Ratio (optional): Aspect ratio of the generated image. Options: 1:1, 4:3, 3:2, 16:9, 2.35:1, 4:5, 2:3, 9:16.
  • Creativity (optional): Controls how loosely the model interprets the prompt. Higher values produce more creative results that may drift from the prompt; lower values stay closer to the prompt. Options: raw, low, medium, high.
  • Seed (optional): Random seed for reproducible generation.

Output and limits

  • Aspect ratios: 1:1, 4:3, 3:2, 16:9, 2.35:1, 4:5, 2:3, 9:16.
  • 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

  • 1 request: $0.10 / request