FLUX.1 Kontext

byBlack Forest Labs

Surgically edit, restyle, and combine visual scenes through plain text instructions without masking or tedious rework

FLUX.1 Kontext

How FLUX.1 Kontext works

From single-image tweaks to multi-reference composites, edit scenes naturally using conversational directions instead of complex node trees.

Load Your Reference Frames

Load Your Reference Frames

Upload up to four source images or begin directly with a standalone text prompt.

Describe the Transformation

Describe the Transformation

Specify exactly what to modify, insert, or replace while dictating which ambient elements must remain untouched.

Render Contextual Variations

Render Contextual Variations

Select Pro for high-speed turns or Max for fine spatial reasoning and crisp typographic fidelity.

What FLUX.1 Kontext is good at

Built on a 12-billion parameter multimodal flow transformer, Kontext blends requested changes into native lighting, geometry, and spatial context.

Mask-Free Surgical Edits

Mask-Free Surgical Edits

Modify specific objects, wardrobe elements, or colors within an existing scene without tedious manual masking, letting the flow transformer match ambient lighting automatically.

Multi-Image Context Fusion

Multi-Image Context Fusion

Feed up to four reference images into the multi-input endpoint to merge character likeness, specific wardrobe textures, and architectural scenery into a unified composite.

Perspective-Locked Typography

Perspective-Locked Typography

Switch to the Max tier for complex spatial layout reasoning and crisp sign rendering that maps new letterforms seamlessly to angled surfaces.

Cohesive Aesthetic Transfer

Cohesive Aesthetic Transfer

Translate portraits or environments into new artistic mediums and historical palettes while locking identity, facial geometry, and lighting structure.

Made with FLUX.1 Kontext

Explore how surgical object swaps, era transfers, and precision typography retain consistent character and environmental cohesion.

Night runner on salt flats

Night runner on salt flats

Graphic portrait with bold type

Graphic portrait with bold type

Sculptural footwear design

Sculptural footwear design

Archival desert rally motorcycle

Archival desert rally motorcycle

What people build with FLUX.1 Kontext

See how art directors, product designers, and campaign visualizers use instruction-guided editing to streamline creative production.

Fashion Lookbook Iteration

01

Swap textile swatches, colorways, and seasonal patterns across existing model lookbooks without re-shooting entire editorial campaigns.

Industrial Prototyping

02

Test finish variations, materials, and form factors on vehicle or consumer hardware concepts while preserving studio rig lighting.

Brand Campaign Localization

03

Replace billboard slogans, packaging labels, and localized store signage in high-res key art without distorting photographic perspective.

Film Pre-Visualization

04

Place recurring characters into distinct set designs and lighting conditions to maintain visual continuity across storyboard sequences.

Visual Social Content

05

Remix key visual assets into striking, high-contrast social banners and vertical graphics with custom-placed typographic hooks.

Frequently Asked Questions

The Max variant provides enhanced spatial layout reasoning, tighter prompt adherence, and higher precision for typography and multi-image blends at 110.3 credits per generation. The standard Pro variant processes at 55.2 credits per generation, offering faster iteration speeds for everyday edits.

Use the multi-image endpoint when combining elements from up to four distinct references, such as applying a specific outfit from one image to a subject in another. For localized modifications to an existing frame, the single-image endpoint provides faster, targeted results.

FLUX.1 Kontext excels at surgical local object edits, style transfers, context-aware typography replacement, character consistency across scenes, and historical photo restoration without requiring manual inpainting masks.

Avoid stacking multiple distinct changes into a single complex instruction, as sequential edits yield cleaner results. Additionally, avoid feeding more than three reference images at once, using vague pronouns like 'it' or 'her', or writing non-English prompts.

FLUX.1 Kontext was created by Black Forest Labs and runs on a 12-billion parameter multimodal flow transformer architecture that processes text instructions and image latent representations concurrently.

Try FLUX.1 Kontext on Fuser

Surgically edit, restyle, and combine visual scenes through plain text instructions without masking or tedious rework