Skip to main content
Image to Image

Flux.2 Image Editor

Edit images using natural language instructions with FLUX.2 Edit

View details
Try it in Ampere

Inputs

Loading input fields...
Execution Steps

Loading workflow structure...

Loading curated examples...

Overview

Flux.2 Image Editor edits up to three source images from natural-language instructions and can return one to four edited images. Use it for product, campaign, social, or brand-asset revisions when you want multi-source editing with preset or custom sizing, acceleration, prompt expansion, safety, guidance, output-format, and seed controls.

Use cases

  • Edit a product or campaign visual from one to three source images.
  • Create several edited options from the same source image set and prompt.
  • Use acceleration when speed matters for early creative exploration.
  • Compare PNG, JPEG, or WebP outputs for different handoff needs.

Input tips

  • Provide 1-3 public image_urls that can be fetched without login.
  • Write a prompt that says what to change and what should stay fixed.
  • Choose num_images from 1-4 when you want multiple edit options.
  • Use image_size presets or custom dimensions only when the output canvas matters.
  • Set output_format to png, jpeg, or webp based on the final handoff need.
  • Adjust acceleration, prompt expansion, safety checker, guidance scale, inference steps, 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 seed and cost metadata. The shared FLUX output view renders a single image or gallery and shows available generation metadata such as seed, image count, timings, safety status when flagged, and the Flux.2 Image Editor model label.

Caveats

  • Input image URLs must be public and reachable.
  • This AI Tool accepts at most three source images.
  • Prompt wording strongly affects what changes and what stays fixed.
  • Custom sizing or acceleration 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