Available now

FLUX1.1 [pro] ultra: text to image

By Black Forest Labs

Black Forest Labs' FLUX1.1 [pro] ultra turns a written prompt into one to four images, with an optional image to guide the result and a raw mode for a more natural look.

Model ID
Maker
Black Forest Labs

Input

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

Example prompt. Edit it or write your own.

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB

Additional settings

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

The safety tolerance level for the generated image. 1 is the most strict and 6 the most permissive.

Whether to enhance the prompt for better results.

The strength of the image prompt, between 0 and 1.

Generate less processed, more natural-looking images.

Price$0.10 / run

You sign up first. Your settings are kept.

About this model

Overview

FLUX1.1 [pro] ultra makes one to four images per run in nine shapes, from a wide 21:9 to a tall 9:21, as JPEG or PNG.

Add an image to steer the composition and set how strongly it counts. Raw mode gives less processed, more natural-looking pictures, and prompt enhancement can expand a short prompt for you.

What you can build

  • Photo-style scenes for articles, ads and social posts
  • Wide 21:9 banners and tall 9:21 story images
  • New takes on a reference image that keep its layout
  • Candid, natural-looking shots with raw mode on

Prompting tips

  • Turn raw mode on for candid photos and documentary scenes; leave it off for polished, retouched results.
  • Keep image prompt strength low when the reference should only hint at the layout, and raise it to follow it more closely.
  • Fix the seed while you adjust the prompt, so each change is easy to compare.

What to check

Compare source resemblance and altered details; image guidance does not guarantee identity or exact composition.

Inputs

  • Prompt (required): The prompt to generate an image from.
  • Seed (optional): The same seed and the same prompt given to the same version of the model will output the same image every time.
  • 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.
  • Safety Tolerance (optional): The safety tolerance level for the generated image. 1 is the most strict and 6 the most permissive. Options: 1, 2, 3, 4, 5, 6.
  • Enhance Prompt (optional): Whether to enhance the prompt for better results.
  • Image (optional): The image URL to generate an image from.
  • Image Prompt Strength (optional): The strength of the image prompt, between 0 and 1.
  • Aspect Ratio (optional): The aspect ratio of the generated image. Options: 21:9, 16:9, 4:3, 3:2, 1:1, 2:3, 3:4, 9:16, 9:21.
  • Raw (optional): Generate less processed, more natural-looking images.

Output and limits

  • Aspect ratios: 21:9, 16:9, 4:3, 3:2, 1:1, 2:3, 3:4, 9:16, 9:21.
  • 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

  • up to, default options: $0.10 / run