Skip to main content

​
Overview

FLUX is our fastest image generation provider, optimized for speed and creative control. It delivers sub-second inference times while maintaining high image quality.

​
Available Models

​
FLUX/dev

The primary FLUX model optimized for both speed and quality. Endpoint: POST /api/v1/flux/dev Best for:
  • Rapid prototyping
  • Content creation workflows
  • Real-time applications
  • High-volume generation
Performance:
  • Inference time: ~0.5-2 seconds
  • Quality: High
  • Cost: Low

​
Parameters

​
Required Parameters

ParameterTypeDescription
promptstringText description of the image to generate (max 1000 characters)

​
Optional Parameters

ParameterTypeDefaultDescription
num_imagesnumber1Number of images to generate (1-4)
image_sizestring”landscape_4_3”Image dimensions
guidance_scalenumber3.5How closely to follow the prompt (1-20)
num_inference_stepsnumber28Number of denoising steps (1-50)
seednumberrandomRandom seed for reproducible results

​
Image Sizes

SizeDimensionsAspect Ratio
square_hd1024×10241:1
square512×5121:1
portrait_4_3768×10243:4
portrait_16_9576×10249:16
landscape_4_31024×7684:3
landscape_16_91024×57616:9

​
Examples

​
Basic Image Generation

const response = await fetch('/api/v1/flux/dev', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer your_api_key',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    prompt: 'A serene mountain landscape at sunset',
    num_images: 1,
    image_size: 'landscape_16_9'
  })
});

const result = await response.json();
console.log('Image URL:', result.images[0].url);

​
Advanced Generation with Control

const response = await fetch('/api/v1/flux/dev', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer your_api_key',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    prompt: 'A futuristic city with flying cars, cyberpunk style, highly detailed',
    num_images: 2,
    image_size: 'landscape_16_9',
    guidance_scale: 7.5, // More creative control
    num_inference_steps: 35, // Higher quality
    seed: 12345 // Reproducible results
  })
});

const result = await response.json();
result.images.forEach((image, index) => {
  console.log(`Image ${index + 1}:`, image.url);
});

​
Python Example

import requests

def generate_flux_image(prompt, **kwargs):
    response = requests.post(
        'https://firemoon.studio/api/v1/flux/dev',
        headers={
            'Authorization': 'Bearer your_api_key',
            'Content-Type': 'application/json'
        },
        json={
            'prompt': prompt,
            'num_images': kwargs.get('num_images', 1),
            'image_size': kwargs.get('image_size', 'landscape_4_3'),
            'guidance_scale': kwargs.get('guidance_scale', 3.5),
            **kwargs
        }
    )

    response.raise_for_status()
    return response.json()

# Usage
result = generate_flux_image(
    'A beautiful underwater scene with coral reefs',
    num_images=2,
    guidance_scale=5.0
)

for image in result['images']:
    print(f"Generated image: {image['url']}")

​
cURL Example

curl -X POST https://firemoon.studio/api/v1/flux/dev \
  -H "Authorization: Bearer your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A majestic eagle soaring over mountains",
    "num_images": 1,
    "image_size": "landscape_16_9",
    "guidance_scale": 4.0,
    "seed": 42
  }'

​
Best Practices

​
Prompt Engineering

Do:
  • Be specific and descriptive
  • Include style references (e.g., “in the style of impressionist painting”)
  • Mention lighting and mood
  • Specify composition elements
Don’t:
  • Use negative prompts (not supported)
  • Be too vague or abstract
  • Include copyrighted character names

​
Performance Optimization

  1. Use lower guidance_scale for faster generation
  2. Reduce num_inference_steps for speed over quality
  3. Generate multiple images in one request instead of separate calls
  4. Cache successful seeds for reproducible variations

​
Quality vs Speed Trade-offs

Use Caseguidance_scalenum_inference_stepsExpected Time
Fast draft2.0-3.020-250.5-1.0s
Balanced3.5-5.025-301.0-1.5s
High quality5.0-7.530-401.5-2.5s
Maximum quality7.5+40-502.5-4.0s

​
Response Format

{
  "images": [
    {
      "url": "https://blob.vercel-storage.com/...",
      "width": 1024,
      "height": 768,
      "content_type": "image/jpeg"
    }
  ],
  "seed": 123456789,
  "has_nsfw_concepts": [false],
  "timings": {
    "inference": 1.2
  }
}

​
Error Handling

FLUX is generally very reliable, but you may encounter:
  • 400 Bad Request: Invalid parameters or prompt too long
  • 429 Too Many Requests: Rate limit exceeded
  • 500 Internal Server Error: Rare inference failures
Implement proper retry logic for 500 errors and backoff for 429 errors.

​
Pricing

FLUX images are billed at our standard image generation rate. Contact us for volume pricing.
FLUX/dev is our recommended model for most use cases due to its excellent balance of speed, quality, and cost.