FLUX.1 Kontext [pro] edits images using simple text prompts. No complex workflows or fine-tuning needed.
Try it live - Test image editing in our playground by uploading an image and typing what you want to change.

​
Examples of Editing

​
Basic Object Modifications

FLUX.1 Kontext is really good at straightforward object modification, for example if we want to change the colour of an object, we can prompt it. For example: Change the car color to red

Before editing

After editing

​
Iterative Editing

FLUX.1 Kontext excels at character consistency, even after multiple edits. Starting from a reference picture, we can see that the character is consistent throughout the sequence. The prompts used for each edit are shown in the captions below each image.

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.

​
Text Editing

FLUX.1 Kontext can directly edit text that appears in images, making it easy to update signs, posters, labels, and more without recreating the entire image. The most effective way to edit text is using quotation marks around the specific text you want to change: Prompt Structure: Replace '[original text]' with '[new text]' Example - We can see below where we have an input image with “Choose joy” written, and we replace “joy” with “BFL” - note the upper case format for BFL.
Input image: Sign saying 'Choose joy'

Input image

Output image: Sign changed to 'Choose BFL'

JOY replaced with BFL

Input image:

Input image

Output image: Text replaced with 'FLUX & JOY'

Sync & Bloom changed to 'FLUX & JOY'

​
Edit Images with Annotation Boxes

FLUX.1 Kontext allows using bright colored boxes as annotations for targeted local editing. Local annotated edits specifically work well for text edits that require text repositioning and resizing. Annotation boxes make referencing specific parts of the image in your prompt even more seamless.
Input image: Cleaning detergent advertisement

Input image with annotation

Output image: Cleaning detergent advertisement with replaced text

Replace text with 'COOL!!'

FLUX Kontext [pro] automatically acknowledges annotation boxes when included as part of input_image. In the output sample annotation boxes are removed automatically.

​
Using FLUX.1 Kontext API for Image Editing

This requires both a text prompt and an input image to work, with the input image serving as the base that will be edited according to your prompt. To use Kontext for image editing, you’ll make a request to the /flux-kontext-pro endpoint:

​
Create Request

# Install `curl` and `jq`, then run:
request=$(curl -X POST \
  'https://api.bfl.ai/v1/flux-kontext-pro' \
  -H 'accept: application/json' \
  -H "x-key: ${BFL_API_KEY}" \
  -H 'Content-Type: application/json' \
  -d '{
    "prompt": "<What you want to edit on the image>",
    "input_image": "<base64 converted image>",
}')
echo $request
request_id=$(echo $request | jq -r .id)
polling_url=$(echo $request | jq -r .polling_url)
A successful response will be a json object containing the request’s id, that will be used to retrieve the actual result.

​
Poll for Result

After submitting a request, you need to poll using the returned polling_url to retrieve the output when ready. 
while true; do
  sleep 0.5
  result=$(curl -s -X 'GET' \
    "${polling_url}" \
    -H 'accept: application/json' \
    -H "x-key: ${BFL_API_KEY}")
  
  status=$(echo $result | jq -r .status)
  echo "Status: $status"
  
  if [ "$status" == "Ready" ]; then
    echo "Result: $(echo $result | jq -r .result.sample)"
    break
  elif [ "$status" == "Error" ] || [ "$status" == "Failed" ]; then
    echo "Generation failed: $result"
    break
  fi
done
A successful response will be a json object containing the result, and result['sample'] is a signed URL for retrieval.
Our signed URLs are only valid for 10 minutes. Please retrieve your result within this timeframe.

​
FLUX.1 Kontext Image Editing Parameters

For image editing, FLUX.1 Kontext tries to match the input image dimensions as closely as possible (rounded to multiples of 32). Use aspect_ratio to override this behavior if needed.
  • Supported Range: Aspect ratios can range from 3:7 (portrait) to 7:3 (landscape).
List of FLUX.1 Kontext parameters for image editing via the /flux-kontext-pro endpoint:
ParameterTypeDefaultDescriptionRequired
promptstringText description of the edit to be applied.Yes
input_imagestringBase64 encoded image to use as reference. Supports up to 20MB or 20 megapixels.Yes
aspect_ratiostring / null"1:1"Desired aspect ratio (e.g., “16:9”). All outputs are ~1MP total. Supports ratios from 3:7 to 7:3.No
seedinteger / nullnullSeed for reproducibility. If null or omitted, a random seed is used. Accepts any integer.No
prompt_upsamplingbooleanfalseIf true, performs upsampling on the promptNo
safety_toleranceinteger2Moderation level for inputs and outputs. Value ranges from 0 (most strict) to 6 (more permissive).No
output_formatstring"jpeg"Desired format of the output image. Can be “jpeg” or “png”.No
webhook_urlstring / nullnullURL for asynchronous completion notification. Must be a valid HTTP/HTTPS URL.No
webhook_secretstring / nullnullSecret for webhook signature verification, sent in the X-Webhook-Secret header.No