Available now

FLUX.3 Image: text to image

By Black Forest Labs

Black Forest Labs' FLUX.3 Image creates images from a prompt and edits with up to 10 reference images, at sizes up to 4K.

Model ID
Maker
Black Forest Labs
Added
October 3, 2026

Input

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

Example prompt. Edit it or write your own.

Auto uses the first reference image when editing.

Output resolution tier. 4k can take several minutes.

Additional settings

Expand the prompt while preserving its intent and reference roles.

Safety tolerance, from 0 (strictest) to 4.

The model version.

Starting price$0.07 / image

You sign up first. Your settings are kept.

About this model

Overview

FLUX.3 Image renders at four resolution tiers, from a 768 square to 1K, 2K and 4K, in 14 aspect ratios from 21:9 to 1:2 or an automatic shape. Output is JPEG or PNG.

The edit mode takes one to 10 images in order. Refer to them by number in the prompt; with the automatic shape, the first image sets the aspect ratio of the result.

What you can build

  • Large 4K images for print and big screens
  • Ads and posters with a fixed layout and readable text
  • A product placed into scenes taken from other photos
  • Edits that combine a person, an outfit and a setting from separate images

Prompting tips

  • Draft at 1K, then render the final at 2K or 4K; 4K can take several minutes.
  • In the edit mode, name each reference by its number, such as "the jacket from image 2".
  • Put the image that should set the shape first when you leave the aspect ratio on auto.

What to check

Compare the result with your source, especially object boundaries, fine text, faces and shadows.

Inputs

  • Prompt (required): The prompt to generate an image from.
  • Aspect Ratio (optional): Output aspect ratio. Auto uses the first reference image when editing. Options: auto, 21:9, 2:1, 16:9, 3:2, 7:5, 4:3, 5:4, 1:1, 4:5, 3:4, 5:7, 2:3, 9:16, 1:2.
  • Resolution (optional): Output resolution tier. 4k can take several minutes. Options: 768sq, 1k, 2k, 4k.
  • Enable Prompt Expansion (optional): Expand the prompt while preserving its intent and reference roles.
  • Safety Tolerance (optional): Safety tolerance, from 0 (strictest) to 4.
  • Output Format (optional): The format of the generated image. Options: jpeg, png.
  • Version (optional): The model version.

Output and limits

  • Resolutions: 768sq, 1k, 2k, 4k.
  • Aspect ratios: auto, 21:9, 2:1, 16:9, 3:2, 7:5, 4:3, 5:4, 1:1, 4:5, 3:4, 5:7, 2:3, 9:16, 1:2.
  • File formats: JPEG, PNG.
  • 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

  • 768sq · up to: $0.07 / image
  • 1k · up to: $0.08 / image
  • 2k · up to: $0.16 / image
  • 4k · up to: $0.97 / image