Flux Kontext Max

FLUX.1 Kontext [max] is Black Forest Labs' hosted image-generation and editing variant, positioned for prompt adherence and typography. This record covers black-forest-labs/flux-kontext-max on Replicate; its reference-image, aspect-ratio, seed and format fields belong to that provider's interface.

Review Kontext Pro
Review the separate Pro record and its hosted contract; use the same source image and instruction when evaluating the two variants.
Compare other image-editing models
Browse image-editing models and review the inputs and examples for your editing task.

Platform: Replicate

Text-Based Image EditingTypography GenerationStyle TransferObject Modification

1.3M runs

$0.08 per output image

Commercial

🚀Function Overview

Kontext Max accepts text instructions and a reference image for tasks such as changing a poster's wording or replacing a background. BFL's positioning is a vendor claim, not a GetLLMs quality ranking. Kontext is now a previous-generation family, with FLUX.2 recommended by BFL for new projects. Max is separate from Pro and the downloadable Dev checkpoint. The Sources section identifies BFL guidance and Replicate's hosted contract, checked October 28, 2026; listed run totals are historical snapshots.

Key Features

Transforms images using text prompts
BFL positions Max for typography and prompt adherence; check every letter rather than assuming correct text
Style transfer for art styles like watercolor or oil painting
Object/clothing modification (e.g., hairstyles, colors)
Background swapping while preserving subjects
Designed for character consistency across edits; verify identity and untouched details in each output
For a background edit, try: Put the mug on a wooden table, keeping its shape, logo and viewing angle unchanged. This instruction example has not been executed by GetLLMs
BFL documents missed instructions and visual degradation during repeated edits; save the original and compare each result before using it
Replicate's safety_tolerance range is 0 to 6, but its documented maximum is 2 when an input image is used; do not transfer another provider's settings into this request

Use Cases

•Editing text in images (signs, posters, labels)
•Changing art styles via style transfer
•Modifying objects or clothing in photos
•Swapping backgrounds while keeping subjects intact
•Creating consistent character portraits
•Professional headshot generation

⚙️Input Parameters

prompt

string

Text description of what you want to generate, or the instruction on how to edit the given image.

input_image

string

Image to use as reference. Must be jpeg, png, gif, or webp.

aspect_ratio

string

Aspect ratio of the generated image. Use 'match_input_image' to match the aspect ratio of the input image.

seed

integer

Random seed. Set for reproducible generation

output_format

string

Output format for the generated image

safety_tolerance

integer

Safety tolerance, 0 is most strict and 6 is most permissive. 2 is currently the maximum allowed when input images are used.

💡Usage Examples

Example 1

Input Parameters

{
  "prompt": "Make the letters 3D, floating in space on a city street",
  "input_image": "https://replicate.delivery/xezq/XfwWjHJ7HfrmXE6ukuLVEpXWfeQ3PQeRI5mApuLXRxST7XMmC/tmpc91tlq20.png",
  "aspect_ratio": "match_input_image",
  "output_format": "jpg",
  "safety_tolerance": 2
}

Output Results

https://replicate.delivery/xezq/Mbbd8Tx2YfRYXSEmLgblTzGtj4ZurpgPjLui6jAqfXLasRzUA/tmpkav_ivyd.jpg

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type: Not specified
Run Count: 1.3M
Commercial Use: Supported
Pricing: $0.08 per output image
Platform: Replicate

Flux Kontext Max

🚀Function Overview

Key Features

Use Cases

⚙️Input Parameters

prompt

input_image

aspect_ratio

seed

output_format

safety_tolerance

💡Usage Examples

Example 1

Input Parameters

Output Results

Quick Actions

Technical Specifications

Sources

Related Keywords

Related Models