Available now

Luma Uni-1 Max: text to image

By Luma AI

Luma Uni-1 Max is the Max tier of Luma's Uni-1 image model: it makes an image from a written prompt or edits one you upload, with an optional manga style.

Model ID
Maker
Luma AI

Input

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

Text prompt describing the image to generate.

Example prompt. Edit it or write your own.

Additional settings

Visual style of the generated image.

Encoding format of the generated image.

Estimated total$0.17

You sign up first. Your settings are kept.

About this model

Overview

Luma Uni-1 Max makes one image per run from a prompt of up to 6000 characters, in nine shapes from a wide 3:1 to a tall 1:3, as PNG or JPEG.

Its edit mode changes an image you upload from a written instruction. Both modes offer an auto style and a manga style.

What you can build

  • Key art and hero stills from a detailed brief
  • Manga panels and black-and-white comic scenes
  • Wide 3:1 banners and tall 1:3 posters
  • Edits that change the setting, light or style of a photo

Prompting tips

  • Write a full brief: subject, setting, light, camera and mood; the prompt can be long.
  • Pick the manga style for comic pages and leave it on auto for everything else.
  • In the edit mode, describe the change and say what must stay as it is.

What to check

Inspect small details and lettering at full size; judge the actual result before choosing it as a main visual.

Inputs

  • Prompt (required): Text prompt describing the image to generate.
  • Aspect Ratio (optional): Aspect ratio of the generated image. Options: 3:1, 2:1, 16:9, 3:2, 1:1, 2:3, 9:16, 1:2, 1:3.
  • Style (optional): Visual style of the generated image. Options: auto, manga.
  • Output Format (optional): Encoding format of the generated image. Options: png, jpeg.

Output and limits

  • Aspect ratios: 3:1, 2:1, 16:9, 3:2, 1:1, 2:3, 9:16, 1:2, 1:3.
  • File formats: PNG, JPEG.
  • 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 image: $0.17 / image