Available now

FLUX.2 [dev]: image editing

By Black Forest Labs

Black Forest Labs' FLUX.2 [dev] creates images from a written prompt and edits up to four images you upload, with steps and guidance you can set yourself.

Model ID
Maker
Black Forest Labs

Input

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

Example prompt. Edit it or write your own.

The width and height must be between 512 and 2048 pixels.

A maximum of 4 images are allowed, if more are provided, only the first 4 will be used.

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB

Additional settings

Guidance Scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.

If not provided, a random seed will be used.

The number of inference steps to perform.

The acceleration level to use for the image generation.

If set to true, the prompt will be expanded for better results.

Starting price$0.10 / run

You sign up first. Your settings are kept.

About this model

Overview

FLUX.2 [dev] makes one to four images per run in six preset shapes, with sides between 512 and 2048 pixels, as JPEG, PNG or WebP.

Unlike the other FLUX.2 cards, it lets you set the number of steps and the guidance scale, and choose an acceleration level. Its edit mode changes up to four uploaded images from a written instruction.

What you can build

  • Concept images and moodboards from short briefs
  • Product shots in landscape, portrait or square shapes
  • Edits that restyle or relight a photo you upload
  • Scenes that combine elements from several images

Prompting tips

  • Raise the guidance scale when the image drifts from the prompt; lower it for looser, more varied results.
  • Use fewer steps or a higher acceleration level for drafts, then render the final image with the defaults.
  • When editing several images, say which one each element should come from.

What to check

Check perspective and object placement; compare added details with your original brief.

Inputs

  • Prompt (required): The prompt to edit the image.
  • Guidance Scale (optional): Guidance Scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. From 0 to 20.
  • Seed (optional): The seed to use for the generation. If not provided, a random seed will be used.
  • Number of Inference Steps (optional): The number of inference steps to perform. From 4 to 50.
  • Image Size (optional): The size of the image to generate. The width and height must be between 512 and 2048 pixels. Options: Square HD, Square, Portrait 4:3, Portrait 16:9, Landscape 4:3, Landscape 16:9.
  • Acceleration (optional): The acceleration level to use for the image generation. Options: none, regular, high.
  • Enable Prompt Expansion (optional): If set to true, the prompt will be expanded for better results.
  • Output Format (optional): The format of the generated image. Options: jpeg, png, webp.
  • Images (required): The URLs of the images for editing. A maximum of 4 images are allowed, if more are provided, only the first 4 will be used.

Output and limits

  • Image sizes: Square HD, Square, Portrait 4:3, Portrait 16:9, Landscape 4:3, Landscape 16:9.
  • File formats: JPEG, PNG, WEBP.
  • 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: $0.10 / run
  • up to · 2 input images: $0.12 / run