Available now

FLUX.2 [max]: image editing

By Black Forest Labs

Build a new composition with FLUX.2 Max, or upload a reference and explain what to change. The edit mode can combine references into a single image.

Model ID
Maker
Black Forest Labs

Input

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

Example prompt. Edit it or write your own.

If auto, the size will be determined by the model.

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB

Additional settings

The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive.

Starting price$0.45 / run

You sign up first. Your settings are kept.

About this model

Overview

The text mode makes one image per run in square, portrait or landscape presets, as JPEG or PNG. Apart from the seed and a safety tolerance from 1, the strictest, to 5, the most permissive, there is nothing to tune.

The edit mode takes one or more images and the change to make: swap the background, add or remove an object, change the light or merge subjects into one scene. It keeps the shape of your input by default, or takes a size you pick.

What you can build

  • Product shots and still lifes from a detailed brief
  • Product photos placed in new settings
  • Portraits with a different outfit, light or backdrop
  • One scene built from subjects in separate photos
  • Landscape banners and portrait posters

Prompting tips

  • Write the subject first, then the setting, light, lens and mood; there are no other dials to lean on.
  • When editing, say what must stay the same, such as the face, the logo or the product's color, as well as what should change.
  • With several uploads, refer to each one by what it shows, for example "the chair from the second image".
  • Keep the same seed when you change one detail of the prompt, so the rest of the image stays close.

What to check

Inspect the full-size output and compare details and subject appearance with your source.

Inputs

  • Prompt (required): The prompt to generate an image from.
  • Image Size (optional): The size of the generated image. If `auto`, the size will be determined by the model. Options: Auto, Square HD, Square, Portrait 4:3, Portrait 16:9, Landscape 4:3, Landscape 16:9.
  • Seed (optional): The seed to use for the generation.
  • Safety Tolerance (optional): The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive. Options: 1, 2, 3, 4, 5.
  • Output Format (optional): The format of the generated image. Options: jpeg, png.
  • Images (required): List of URLs of input images for editing.

Output and limits

  • Image sizes: Auto, Square HD (1024×1024), Square (512×512), Portrait 4:3 (768×1024), Portrait 16:9 (576×1024), Landscape 4:3 (1024×768), Landscape 16:9 (1024×576).
  • 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

  • up to · 1 input image: $0.45 / run
  • up to · 2 input images: $0.64 / run