Available now

FLUX.2 [klein] 9B Base: text to image

By Black Forest Labs

Black Forest Labs' FLUX.2 [klein] 9B Base creates images from a prompt and edits up to four images, with a negative prompt to keep things out.

Model ID
Maker
Black Forest Labs

Input

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

Example prompt. Edit it or write your own.

Additional settings

Negative prompt for classifier-free guidance. Describes what to avoid in the image.

Guidance scale for classifier-free guidance.

If not provided, a random seed will be used.

The number of inference steps to perform.

The acceleration level to use for image generation.

Price$0.02 / megapixel

You sign up first. Your settings are kept.

About this model

Overview

FLUX.2 [klein] 9B Base makes one to four images per run in six preset shapes, as JPEG, PNG or WebP. Unlike most FLUX.2 cards, it takes a negative prompt.

Its edit mode changes one to four uploaded images from a written instruction; leave the size empty to keep the size of the input image. Steps, guidance scale and acceleration are adjustable in both modes.

What you can build

  • Scenes with clear exclusions, such as no people or no text
  • Product images in several shapes
  • Edits that change the color, material or setting of a photo
  • Composites built from up to four images

Prompting tips

  • Put what you do not want in the negative prompt instead of writing "no" in the main prompt.
  • When editing, describe only the change and say what stays the same.
  • Lower the guidance scale for looser, more varied results; raise it to follow the prompt more closely.

What to check

Review fine structure and omissions at actual output size, not only the catalog thumbnail.

Inputs

  • Prompt (required): The prompt to generate an image from.
  • Negative Prompt (optional): Negative prompt for classifier-free guidance. Describes what to avoid in the image.
  • Guidance Scale (optional): Guidance scale for classifier-free guidance. 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. Options: Square HD, Square, Portrait 4:3, Portrait 16:9, Landscape 4:3, Landscape 16:9.
  • Number of Images (optional): The number of images to generate. From 1 to 4.
  • Acceleration (optional): The acceleration level to use for image generation. Options: none, regular, high.
  • Output Format (optional): The format of the generated image. Options: jpeg, png, webp.

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, WEBP.
  • 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: $0.02 / megapixel