Flux 1.1 Pro

flux-1.1-pro

Faster, better FLUX Pro. Text-to-image model with excellent image quality, prompt adherence, and output diversity.

Partner Model

Fast Inference

REST API

Try in Console API Docs Examples

Model Information

Response Time~8 sec

StatusActive

Version

0.0.1

Updated8 days ago

API Reference

View Full Documentation

Prerequisites

Create an API Key from the Eachlabs Console
Install the required dependencies for your chosen language (e.g., requests for Python)

API Integration Steps

1. Create a Prediction

Send a POST request to create a new prediction. This will return a prediction ID that you'll use to check the result. The request should include your model inputs and API key.

import requests
import time

API_KEY = "YOUR_API_KEY"  # Replace with your API key
HEADERS = {
    "X-API-Key": API_KEY,
    "Content-Type": "application/json"
}

def create_prediction():
    response = requests.post(
        "https://api.eachlabs.ai/v1/prediction/",
        headers=HEADERS,
        json={
            "model": "flux-1.1-pro",
            "version": "0.0.1",
            "input": {
  "prompt_upsampling": false,
  "seed": null,
  "width": null,
  "height": null,
  "prompt": "your prompt here",
  "aspect_ratio": "1:1",
  "output_format": "jpg",
  "output_quality": "80",
  "safety_tolerance": "2",
  "image_prompt": "your_file.jpeg"
}
        }
    )
    prediction = response.json()
    
    if prediction["status"] != "success":
        raise Exception(f"Prediction failed: {prediction}")
    
    return prediction["predictionID"]

2. Get Prediction Result

Poll the prediction endpoint with the prediction ID until the result is ready. The API uses long-polling, so you'll need to repeatedly check until you receive a success status.

def get_prediction(prediction_id):
    while True:
        result = requests.get(
            f"https://api.eachlabs.ai/v1/prediction/{prediction_id}",
            headers=HEADERS
        ).json()
        
        if result["status"] == "success":
            return result
        elif result["status"] == "error":
            raise Exception(f"Prediction failed: {result}")
        
        time.sleep(1)  # Wait before polling again

3. Complete Example

Here's a complete example that puts it all together, including error handling and result processing. This shows how to create a prediction and wait for the result in a production environment.

try:
    # Create prediction
    prediction_id = create_prediction()
    print(f"Prediction created: {prediction_id}")
    
    # Get result
    result = get_prediction(prediction_id)
    print(f"Output URL: {result['output']}")
    print(f"Processing time: {result['metrics']['predict_time']}s")
except Exception as e:
    print(f"Error: {e}")

Additional Information

The API uses a two-step process: create prediction and poll for results
Response time: ~8 seconds
Rate limit: 60 requests/minute
Concurrent requests: 10 maximum
Use long-polling to check prediction status until completion

Overview

FLUX 1.1 Pro is Black Forest Labs' most advanced and efficient text-to-image model, providing superior speed and image quality while maintaining excellent prompt adherence and output diversity.

Technical Specifications

Model Architecture: FLUX1.1 [pro] is built on a state-of-the-art hybrid architecture, combining multimodal capabilities and parallel diffusion transformer blocks, ensuring exceptional performance. The model operates with 12 billion parameters, offering unparalleled depth and nuance.

Training Innovations: The model employs a cutting-edge training approach called flow matching. This methodology generalizes traditional diffusion processes, enabling FLUX1.1 [pro] to generate images with superior detail, coherence, and creativity.

Performance Metrics: Achieving industry-leading benchmarks, FLUX1.1 [pro] has earned the highest Elo score on the Artificial Analysis image evaluation platform, reflecting its dominance in speed, image quality, and prompt alignment.

Enhanced Speed: FLUX1.1 [pro] is optimized for rapid image generation, delivering outputs six times faster than its predecessor. This improvement makes it suitable for both real-time applications and high-volume batch processing.

Output Quality: The model supports ultra high-resolution image generation, producing visuals up to 2K resolution while maintaining excellent adherence to user prompts and fine details.

Key Considerations

Ethical Use: Ensure that generated images comply with ethical guidelines and do not infringe upon copyright or promote harmful content.

Licensing: By using FLUX1.1 [pro], users agree to the Black Forest Labs API agreement and Terms of Service.

Six times faster generation than its predecessor FLUX.1 Pro

Based on a hybrid architecture of multimodal and parallel diffusion transformer blocks

Scaled to 12B parameters

Built on flow matching, a general method for training generative models

Incorporates rotary positional embeddings and parallel attention layers

Legal Information

By using this model, you agree to:

Black Forest Labs API agreement
Black Forest Labs Terms of Service

Tips & Tricks

Prompt Engineering: Experiment with varying prompt structures to achieve diverse and high-quality outputs.

Batch Processing: Leverage the model's efficiency to process multiple image generations in parallel, enhancing workflow productivity.

Use simple one-word prompts for more natural-looking results

Try using 'IMG' followed by four numbers and 'CR2' to simulate Canon camera files

Add file extensions to prompts for more realistic outputs

Avoid complex prompts that may result in overly perfect images

Capabilities

Rapid Generation: Delivers images six times faster than previous versions, enhancing real-time application feasibility.

High-Resolution Outputs: Supports ultra high-resolution image generation up to 2K, maintaining prompt fidelity.

Improved hardware efficiency

Superior text prompt compliance

Enhanced output diversity

What can I use for?

Digital Art Creation: Generate high-quality images for artistic projects, concept art, and visual storytelling.

Content Generation: Produce engaging visuals for marketing materials, social media, and multimedia presentations.

Prototyping and Design: Utilize rapid image generation for product design mockups, architectural visualizations, and creative brainstorming.

Professional photography generation

Concept art development

Stock photo alternatives

Things to be aware of

Style Exploration: Experiment with prompts that specify different artistic styles, such as "a surrealist painting of a cityscape at dawn."

Scene Composition: Create complex scenes by detailing elements and their interactions, like "a futuristic marketplace bustling with diverse alien species."

Abstract Concepts: Test the model's interpretative capabilities with abstract prompts, such as "the essence of tranquility depicted in shades of blue."

Generate realistic photos using the 'IMG_XXXX_CR2' format

Create professional product photography with simple one-word prompts

Generate images with varying levels of prompt complexity

Try portrait photography with natural lighting and poses

Experiment with landscape photography in different conditions

Create realistic stock photo alternatives

Generate concept art with different artistic styles

Test the model's capabilities with architectural visualization

Compare results between simple and complex prompts

Limitations

Input Constraints: While the model excels with well-crafted text prompts, ambiguous or poorly defined prompts may lead to less satisfactory results.

Output Variability: Despite improved prompt adherence, some generated images may not fully capture complex or highly detailed scene descriptions.

Resource Requirements: High-resolution image generation may demand substantial computational resources, potentially impacting performance on lower-end hardware.

Some complex prompts may result in overly polished images

Performance may vary based on prompt complexity

Output Format: PNG, JPG

Related AI Models

Fooocus

fooocus-api

Text to Image

Ideogram V2

ideogram-v2

Text to Image

Recraft 20B

recraft-20b

Text to Image

Photon

photon

Text to Image