Skip to main content
Image to Image

Flux.2 Flex Image Editor

Edit images using natural language instructions with FLUX.2 [flex] from Black Forest Labs

View details
Try it in Ampere

Inputs

Loading input fields...
Execution Steps

Loading workflow structure...

Loading curated examples...

Overview

Flux.2 Flex Image Editor edits one or more source images from natural-language instructions and returns edited image output with a seed. Use it for product, campaign, social, or brand-asset revisions when you want flexible image sizing, prompt expansion, safety tolerance, guidance, inference-step, output-format, and seed controls.

Use cases

  • Edit a product or campaign image from a plain-language change request.
  • Use auto, preset, or custom image sizing while applying a visual edit.
  • Turn a short instruction into a fuller edit request with prompt expansion.
  • Use seed and safety controls when repeatable edit exploration matters.

Input tips

  • Provide one or more public image_urls that can be fetched without login.
  • Write a prompt that says what to change and what should stay fixed.
  • Use image_size auto, a preset, or custom width and height when the output canvas matters.
  • Set safety_tolerance from 1-5, where 1 is most strict and 5 is most permissive.
  • Set output_format to png or jpeg based on the final handoff need.
  • Adjust prompt expansion, guidance scale, inference steps, safety checker, or seed only when needed.

Expected output

The AI Tool returns edited image output with downloadable URLs and optional content type, file name, file size, width, and height, plus the seed used and cost metadata. The Flux.2 Flex output view renders a single image or gallery and shows seed, image count, and the Flux.2 Flex Image Editor model label.

Caveats

  • Input image URLs must be public and reachable.
  • This AI Tool does not expose a num_images control.
  • Prompt wording strongly affects what changes and what stays fixed.
  • Custom sizing can alter framing, composition, edges, or fine details.
  • Generated text, logos, product details, faces, and image edges should be reviewed before use.

Related AI Tools