FLUX.1 Fill [pro] example output
PRO

FLUX.1 Fill [pro]

Black Forest Labs' state-of-the-art inpainting model. Mask-based precision, outpainting, surgical edits.

FLUX.1 Fill [pro] is Black Forest Labs' dedicated mask-based inpainting model. Unlike full-image regeneration, it applies generation quality only to the masked region while leaving the rest of the image pixel-perfect. Built for surgical object removal, material swaps, scene extension, and architectural edits where only a specific region should change. Benchmarks put it at state-of-the-art inpainting performance.

Example outputs

FLUX.1 Fill [pro] example 1

Remove the scaffolding from the facade and extend the brickwork behind it to match the existing pattern

FLUX.1 Fill [pro] example 2

Replace the product label with a clean minimal Japanese typographic design, match the marble surface lighting

FLUX.1 Fill [pro] example 3

Extend the left edge of this landscape photograph to show more of the coastline, golden hour lighting continuous

FLUX.1 Fill [pro] example 4

Swap the concrete wall behind the model for a richly textured timber panel, preserve the direction of light

FLUX.1 Fill [pro] example 5

Remove the tourists from the background of this architectural shot, reconstruct the paved plaza underneath

FLUX.1 Fill [pro] example 6

Replace the central logo with a geometric gold foil monogram on dark navy, keep the poster layout and rhythm

How it works

01

Describe your vision

Type a detailed prompt or upload a reference sketch, photo, or mood board.

02

Choose your settings

Pick your resolution and aspect ratio. See the credit cost before you generate.

03

Generate in seconds

Your image is delivered in seconds. Download, iterate, or pipe into video.

Ready to create with FLUX.1 Fill [pro]?

Jump into the Studio and start generating. Plans from £10/month.

Choose a Plan

Mask-based inpainting from Black Forest Labs.

FLUX.1 Fill [pro] is Black Forest Labs' dedicated inpainting and outpainting model, built to solve one problem exceptionally well: modifying specific regions of an image while leaving everything outside the mask pixel-perfect. It is not a general-purpose image generator. It is a precision tool. Black Forest Labs' own research places Fill [pro] at state-of-the-art inpainting performance, ahead of competing methods.

The model's approach is distinct from multi-reference editing systems. Rather than composing new content from multiple input images, Fill [pro] takes one base image, one mask, and one prompt describing what should appear in the masked area. That constraint is also its strength. The model concentrates on the masked region without distractions, producing edits that integrate naturally with the surrounding lighting, perspective, and texture.

For design professionals, the use cases cluster around precision work. Product photography where a single element needs replacing. Architectural visualisation where a specific material or element is wrong. E-commerce catalogues where batch-consistent edits matter. The model also handles outpainting, extending image boundaries with context-aware content that matches the original composition.

State-of-the-art mask-based editing

Fill [pro] preserves unmasked regions untouched while regenerating the masked area at full model quality. No degradation to the rest of the image, no bleed across the mask boundary. The edit looks native, not composited.

Outpainting with context awareness

Extend an image beyond its original frame and Fill [pro] generates continuation content that matches lighting, perspective, and style. Useful for turning square product shots into wide hero banners, or recovering content lost when a photo was cropped too tight.

Two flexible mask inputs

Supply a separate black-and-white mask image, or a PNG with an alpha channel where transparent areas mark the edit region. Both approaches produce identical quality and fit different toolchains and studio pipelines.

Frequently asked

Questions about FLUX.1 Fill [pro].

FLUX.1 Fill [pro] is Black Forest Labs' dedicated mask-based inpainting model. Unlike full-image regeneration, it applies generation quality only to the masked region while leaving the rest of the image pixel-perfect. Built for surgical object removal, material swaps, scene extension, and architectural edits where only a specific region should change. Benchmarks put it at state-of-the-art inpainting performance.
Built differently

Why Stensyl?

A small indie studio building creative tools the way they should be built. No VC theatre, no funnel games, no faceless support.