Skip to main content
FLUX.2 brings enterprise-grade efficiency and professional precision to text-to-image generation. It closes the gap between generated and real imagery with accurate hands, faces, and textures—all while respecting brand guidelines through hex-code color steering. [max] offers the highest quality with grounding search for real-time information.
Try it live — Test FLUX.2 [max], [pro], [flex] and [klein] in the playground. [klein] is also available on Hugging Face.

​
Examples

​
Photorealistic

Cinematic landscape with sentient tree

At high noon on a blustery day, capture the surreal presence of a sentient tree, seemingly rooted underwater just off a tumultuous ocean shore. Employ a sweeping panning shot, bathing the scene in cinematic natural light and a stark palette of winter whites and greys, as if glimpsing a spectral sentinel through a watery veil.

​
Typography & Design

Samsung Galaxy S25 Ultra product advertisement

Samsung Galaxy S25 Ultra product advertisement, 'Ultra-strong titanium' headline, 'Shielded in a strong titanium frame, your Galaxy S25 Ultra always stays protected' subtext, close-up of phone edge showing titanium frame, dark gradient background, clean minimalist tech aesthetic, professional product photography

Cinematic lighting portrait
Realistic skin texture close-up
Hyper-realistic close-up portrait
Product photography quality output
Freiburg infographic with clean typography
Ad creative with embedded text
Magazine cover layout
Automotive advertisement with headline
FLUX.2 [max] searches the web when prompted, so you can generate visuals grounded in real-time information — sports scores, weather, or historical events.
Football game score generated from real-time data
Real-time weather visualization for Freiburg
Historical event recreation — Fall of the Berlin Wall
Starlink satellite launch visualization
Specify brand colors via hex codes with precision matching — no approximation.
Vase with gradient hex colors and pink flowers

A vase on a table in living room, the color of the vase is a gradient of color, starting with color #02eb3c and finishing with color #edfa3c. The flowers inside the vase have the color #ff0088

Eyeshadow palette with precise hex colors

Luxury eyeshadow palette with 6 pans: top row #B76E79, #E8D5B7, #8B4789; bottom row #CD7F32, #F8F6F0, #800020

Use JSON-structured prompts for precise control over generation — ideal for production workflows and automation.
Example: Structured Prompting
{
  "subject": "Mona Lisa painting by Leonardo da Vinci",
  "background": "museum gallery wall, ornate gold frame",
  "lighting": "soft gallery lighting, warm spotlights",
  "style": "digital art, high contrast",
  "camera_angle": "eye level view",
  "composition": "centered, portrait orientation"
}
Mona Lisa in museum — eye level view
Mona Lisa in museum — worm's eye view
Comic book panel 1
Comic book panel 2
Comic book panel 3
Comic book panel 4

​
API Integration

​
Create Request

request=$(curl -X POST \
  'https://api.bfl.ai/v1/flux-2-pro-preview' \
  -H 'accept: application/json' \
  -H "x-key: ${BFL_API_KEY}" \
  -H 'Content-Type: application/json' \
  -d '{
    "prompt": "A serene mountain landscape at golden hour, soft diffused light filtering through clouds",
    "width": 1024,
    "height": 1024
  }')
echo $request
request_id=$(echo $request | jq -r .id)
polling_url=$(echo $request | jq -r .polling_url)

import os
import requests

response = requests.post(
    'https://api.bfl.ai/v1/flux-2-pro-preview',
    headers={
        'accept': 'application/json',
        'x-key': os.environ.get("BFL_API_KEY"),
        'Content-Type': 'application/json',
    },
    json={
        'prompt': 'A serene mountain landscape at golden hour, soft diffused light filtering through clouds',
        'width': 1024,
        'height': 1024,
    },
).json()

request_id = response["id"]
polling_url = response["polling_url"]

​
Poll for Result

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

import time
import os
import requests

while True:
  time.sleep(0.5)
  result = requests.get(
      polling_url,
      headers={
          'accept': 'application/json',
          'x-key': os.environ.get("BFL_API_KEY"),
      },
      params={'id': request_id}
  ).json()

  if result['status'] == 'Ready':
      print(f"Image ready: {result['result']['sample']}")
      break
  elif result['status'] in ['Error', 'Failed']:
      print(f"Generation failed: {result}")
      break
Signed URLs are only valid for 10 minutes. Please retrieve your result within this timeframe.
For all available parameters, endpoints, and model options, see the API Reference.