Quick Reference

fal-ai/flux-2-pro

fal-ai/flux/dev

fal-ai/flux/schnell

fal-ai/fast-sdxl

square_hd

landscape_16_9

portrait_16_9

{ width, height }

guidance_scale

num_inference_steps

num_images

When to Use This Skill

Use for text-to-image generation:

• Generating images from text prompts
• Choosing between FLUX and SDXL models
• Configuring image sizes and quality parameters
• Using LoRA models for custom styles
• Batch generating multiple images

Related skills:

• For image editing: see

  fal-image-to-image

• For model comparison: see

  fal-model-guide

• For API integration: see

  fal-api-reference

fal.ai Text-to-Image Models

Complete reference for all text-to-image generation models on fal.ai.

FLUX Models

FLUX.1 [dev]

Endpoint:

fal-ai/flux/dev

The 12B parameter FLUX.1 model offers excellent quality with open-source accessibility.

import { fal } from "@fal-ai/client";

const result = await fal.subscribe("fal-ai/flux/dev", {
  input: {
    prompt: "A serene Japanese garden with cherry blossoms, koi pond, wooden bridge, soft morning light",
    image_size: "landscape_16_9",
    num_inference_steps: 28,
    guidance_scale: 3.5,
    num_images: 1,
    seed: 42,
    enable_safety_checker: true,
    output_format: "jpeg"
  }
});

console.log(result.images[0].url);

import fal_client

result = fal_client.subscribe(
    "fal-ai/flux/dev",
    arguments={
        "prompt": "A serene Japanese garden with cherry blossoms",
        "image_size": "landscape_16_9",
        "num_inference_steps": 28,
        "guidance_scale": 3.5,
        "num_images": 1,
        "seed": 42,
        "enable_safety_checker": True,
        "output_format": "jpeg"
    }
)
print(result["images"][0]["url"])

FLUX Schnell

Endpoint:

fal-ai/flux/schnell

Optimized for speed with only 4 inference steps required.

const result = await fal.subscribe("fal-ai/flux/schnell", {
  input: {
    prompt: "A colorful abstract painting",
    image_size: "square_hd",
    num_inference_steps: 4,  // Optimized for 4 steps
    num_images: 1
  }
});

FLUX Pro

Endpoint:

fal-ai/flux-pro

const result = await fal.subscribe("fal-ai/flux-pro", {
  input: {
    prompt: "Professional product photography of a luxury watch",
    image_size: "square_hd",
    num_inference_steps: 28,
    guidance_scale: 3.5
  }
});

FLUX.2 [pro]

Endpoint:

fal-ai/flux-2-pro

The latest FLUX model with built-in prompt optimization.

const result = await fal.subscribe("fal-ai/flux-2-pro", {
  input: {
    prompt: "A majestic lion in the savanna at golden hour",
    image_size: "landscape_16_9",
    num_inference_steps: 28,
    guidance_scale: 3.5,
    // FLUX 2 Pro features
    safety_tolerance: "2",  // 1-6, higher = more permissive
    raw: false  // Set true to disable prompt enhancement
  }
});

FLUX.2 Pro Specific Parameters:

• safety_tolerance

  : 1-6, controls content filtering sensitivity

• raw

  : Boolean, set to

  true

  to disable automatic prompt enhancement

FLUX LoRA

Endpoint:

fal-ai/flux-lora

Apply custom LoRA models to FLUX generation.

const result = await fal.subscribe("fal-ai/flux-lora", {
  input: {
    prompt: "A portrait in the style of <lora_trigger>",
    loras: [
      {
        path: "https://huggingface.co/user/lora-model/resolve/main/lora.safetensors",
        scale: 0.8
      }
    ],
    image_size: "portrait_4_3",
    num_inference_steps: 28,
    guidance_scale: 3.5
  }
});

LoRA Parameters:

• loras

  : Array of LoRA configurations

  • path

    : URL to LoRA weights (.safetensors)

  • scale

    : 0-1, strength of LoRA effect

FLUX Realism

Endpoint:

fal-ai/flux-realism

const result = await fal.subscribe("fal-ai/flux-realism", {
  input: {
    prompt: "A photorealistic portrait of a young woman, natural lighting, 85mm lens",
    image_size: "portrait_4_3",
    num_inference_steps: 28
  }
});

FLUX Fill (Outpainting)

Endpoint:

fal-ai/flux-pro/v1/fill

const result = await fal.subscribe("fal-ai/flux-pro/v1/fill", {
  input: {
    prompt: "Continue the landscape with mountains",
    image_url: "https://example.com/partial-image.jpg",
    mask_url: "https://example.com/outpaint-mask.png"
  }
});

Stable Diffusion Models

Fast SDXL

Endpoint:

fal-ai/fast-sdxl

const result = await fal.subscribe("fal-ai/fast-sdxl", {
  input: {
    prompt: "A fantasy castle on a cliff, dramatic lighting",
    negative_prompt: "blurry, low quality, distorted",
    image_size: "landscape_16_9",
    num_inference_steps: 25,
    guidance_scale: 7.5,
    num_images: 1,
    seed: 42
  }
});

SDXL-Specific Parameters:

• negative_prompt

  : What to avoid in generation
• Higher

  guidance_scale

  (7-12) works better for SDXL

Stable Diffusion 3 Medium

Endpoint:

fal-ai/stable-diffusion-v3-medium

const result = await fal.subscribe("fal-ai/stable-diffusion-v3-medium", {
  input: {
    prompt: "A sign that says 'Hello World' in neon lights",
    negative_prompt: "blurry, distorted text",
    image_size: "square_hd",
    num_inference_steps: 28,
    guidance_scale: 7.0
  }
});

SDXL Turbo

Endpoint:

fal-ai/sdxl-turbo

const result = await fal.subscribe("fal-ai/sdxl-turbo", {
  input: {
    prompt: "A cute robot",
    num_inference_steps: 1,  // Single step!
    guidance_scale: 0  // No guidance needed
  }
});

SDXL Lightning

Endpoint:

fal-ai/fast-lightning-sdxl

const result = await fal.subscribe("fal-ai/fast-lightning-sdxl", {
  input: {
    prompt: "A beautiful sunset",
    num_inference_steps: 4,
    guidance_scale: 1.5
  }
});

Specialized Models

Recraft V3

Endpoint:

fal-ai/recraft-v3

const result = await fal.subscribe("fal-ai/recraft-v3", {
  input: {
    prompt: "A minimalist logo for a tech startup, clean lines",
    image_size: "square_hd",
    style: "digital_illustration"  // or "realistic_image", "vector_illustration"
  }
});

Recraft Styles:

• realistic_image

• digital_illustration

• vector_illustration

• icon

Ideogram

Endpoint:

fal-ai/ideogram

const result = await fal.subscribe("fal-ai/ideogram", {
  input: {
    prompt: "A vintage poster with the text 'JAZZ FESTIVAL' in art deco style",
    aspect_ratio: "portrait_4_3"
  }
});

Playground v2.5

Endpoint:

fal-ai/playground-v25

const result = await fal.subscribe("fal-ai/playground-v25", {
  input: {
    prompt: "A surreal dreamscape with floating islands",
    image_size: "landscape_16_9",
    guidance_scale: 3.0
  }
});

AuraFlow

Endpoint:

fal-ai/aura-flow

const result = await fal.subscribe("fal-ai/aura-flow", {
  input: {
    prompt: "A magical forest with bioluminescent plants",
    num_inference_steps: 28,
    guidance_scale: 3.5
  }
});

Kolors

Endpoint:

fal-ai/kolors

const result = await fal.subscribe("fal-ai/kolors", {
  input: {
    prompt: "A vibrant street market in Morocco",
    image_size: "landscape_4_3"
  }
});

Common Parameters Reference

Image Size Options

square

square_hd

portrait_4_3

portrait_16_9

landscape_4_3

landscape_16_9

Custom Dimensions:

image_size: { width: 1920, height: 1080 }

Complete Parameter Reference

interface TextToImageInput {
  // Required
  prompt: string;

  // Image dimensions
  image_size?:
    | "square" | "square_hd"
    | "portrait_4_3" | "portrait_16_9"
    | "landscape_4_3" | "landscape_16_9"
    | { width: number; height: number };

  // Generation parameters
  num_inference_steps?: number;  // 1-50, default varies by model
  guidance_scale?: number;       // 1-20, default: 3.5 (FLUX) or 7.5 (SDXL)
  num_images?: number;           // 1-4, default: 1
  seed?: number;                 // For reproducibility

  // Output options
  output_format?: "jpeg" | "png";
  enable_safety_checker?: boolean;

  // SDXL-specific
  negative_prompt?: string;

  // FLUX 2 Pro specific
  safety_tolerance?: string;     // "1" to "6"
  raw?: boolean;                 // Disable prompt enhancement

  // LoRA specific
  loras?: Array<{
    path: string;
    scale: number;
  }>;
}

Response Structure

interface TextToImageOutput {
  images: Array<{
    url: string;
    width: number;
    height: number;
    content_type: string;
  }>;
  seed: number;
  prompt: string;
  has_nsfw_concepts?: boolean[];
  timings?: {
    inference: number;
  };
}

Model Selection Guide

fal-ai/flux-2-pro

fal-ai/flux/dev

fal-ai/flux/schnell

fal-ai/fast-sdxl

fal-ai/sdxl-turbo

fal-ai/flux-lora

fal-ai/ideogram

fal-ai/recraft-v3

fal-ai/flux-realism

Best Practices

Prompt Engineering

For FLUX models:

• Be descriptive and specific
• Include style, lighting, composition
• FLUX 2 Pro auto-enhances prompts (use

  raw: true

  to disable)
• Guidance scale 3-4 works best

For SDXL models:

• Use negative prompts
• Higher guidance (7-12) for better prompt adherence
• Include quality keywords: "high quality, detailed, 8k"

Quality vs Speed Trade-offs

// Quality priority
const quality = await fal.subscribe("fal-ai/flux-2-pro", {
  input: {
    prompt: "...",
    num_inference_steps: 28,
    guidance_scale: 3.5
  }
});

// Speed priority
const fast = await fal.subscribe("fal-ai/flux/schnell", {
  input: {
    prompt: "...",
    num_inference_steps: 4
  }
});

// Balance
const balanced = await fal.subscribe("fal-ai/flux/dev", {
  input: {
    prompt: "...",
    num_inference_steps: 20,
    guidance_scale: 3.5
  }
});

Batch Generation

// Generate multiple variations
const result = await fal.subscribe("fal-ai/flux/dev", {
  input: {
    prompt: "A beautiful landscape",
    num_images: 4,
    seed: 42  // Same seed = similar outputs
  }
});

// Access all images
result.images.forEach((img, i) => {
  console.log(`Image ${i + 1}: ${img.url}`);
});

Reproducibility

// Use seed for reproducible results
const seed = 12345;

const result1 = await fal.subscribe("fal-ai/flux/dev", {
  input: { prompt: "A cat", seed }
});

const result2 = await fal.subscribe("fal-ai/flux/dev", {
  input: { prompt: "A cat", seed }
});

// result1 and result2 will be identical