Available now

FLUX.1 [dev] Redux: image variations

By Black Forest Labs

FLUX.1 [dev] Redux takes one image and makes new variations of it, keeping its subject and style without a prompt.

Model ID
Maker
Black Forest Labs

Input

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

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB

Additional settings

The number of inference steps to perform.

The same seed and the same prompt given to the same version of the model will output the same image every time.

The speed of the generation. The higher the speed, the faster the generation.

Price$0.04 / megapixel

You sign up first. Your settings are kept.

About this model

Overview

Upload an image and FLUX.1 [dev] Redux draws new versions that share its look, content and mood. There is no prompt: the image alone guides the result.

Make one to four variations per run in a square, portrait or landscape size. More steps and a higher guidance value change how closely the output follows the source; a seed repeats a result.

What you can build

  • Several takes on one product shot or illustration
  • A set of images that share one style
  • Square, portrait and landscape versions of the same idea
  • Fresh backgrounds and textures based on a sample

Prompting tips

  • Use a clean, well-lit source image; its colors and style carry into every variation.
  • Ask for four images per run and pick the strongest.
  • Keep the seed of a result you like to repeat it in another size.

What to check

Compare silhouette and composition with the source, then inspect new details at full size.

Inputs

  • Image (required): The URL of the image to generate an image from.
  • Image Size (optional): The size of the generated image. Options: Square HD, Square, Portrait 4:3, Portrait 16:9, Landscape 4:3, Landscape 16:9.
  • Number of Inference Steps (optional): The number of inference steps to perform. From 1 to 50.
  • Seed (optional): The same seed and the same prompt given to the same version of the model will output the same image every time.
  • Guidance scale (CFG) (optional): The CFG (Classifier Free 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 1 to 20.
  • Number of Images (optional): The number of images to generate. From 1 to 4.
  • Output Format (optional): The format of the generated image. Options: jpeg, png.
  • Acceleration (optional): The speed of the generation. The higher the speed, the faster the generation. Options: none, regular, high.

Output and limits

  • Image sizes: 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.
  • Up to 4 images per run.
  • 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 megapixel: $0.04 / megapixel