Overview of FLUX.1 Kontext, a model that combines text-to-image generation with context-aware image editing. For new projects, we recommend FLUX.2.
FLUX.2 is now our recommended model for image generation and editing. It offers superior quality, multi-reference support (up to 10 images), improved text editing, and output up to 4MP. Get started with FLUX.2 →
FLUX.1 Kontext [pro] is a previous-generation model that combines text-to-image generation with image editing.
Want to try first? Test FLUX.1 Kontext [pro] & [max] in our playground before integrating the API.
Create stunning images from scratch using simple text prompts. FLUX.1 Kontext [pro] delivers fast generation with strong prompt adherence.
'A small furry elephant pet looks out from a cat house'
'A cute robot repairing a pickup truck, van gogh style'
'Close-up of a vintage car hood under heavy rain'
'A close-up of a face adorned with intricate black and blue patterns'
Edit specific parts of images while keeping everything else untouched using simple text prompts. Just describe what you want to change and get the results.
Before: Original car
After: 'Change the car color to red'
Original image
First edit
Second edit
Maintain character identity and unique features across multiple scenes and iterative edits.
Input Image
Remove the object from her face
She is now taking a selfie in the streets of Freiburg, it's a lovely day out.
It's now snowing, everything is covered in snow.
Replace text in signs, posters, and labels with precision while maintaining the original styling and context. Simply use quotes around the text you want to change: Replace 'old text' with 'new text'.
Original: 'Choose joy'
Edited: Replace 'joy' with 'BFL'
Transform any image into completely different artistic styles or use reference images to apply their style to new scenes.
Original architectural photo
Converted to pencil sketch
Transformed to oil painting
Style reference
'Using this style, a bunny, dog and cat having tea'
