Flux Depth Pro

flux-depth-pro

Flux Depth Pro Model generates advanced depth estimations, enabling 3D effects and enhanced image realism.

Partner Model

Fast Inference

REST API

Try in Console API Docs Examples

Model Information

Response Time~19 sec

StatusActive

Version

0.0.1

Updated10 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-depth-pro",
            "version": "0.0.1",
            "input": {
  "seed": null,
  "steps": "50",
  "prompt": "your prompt here",
  "guidance": "10",
  "control_image": "your_file.image/jpeg",
  "output_format": "jpg",
  "safety_tolerance": "2",
  "prompt_upsampling": false
}
        }
    )
    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: ~19 seconds
Rate limit: 60 requests/minute
Concurrent requests: 10 maximum
Use long-polling to check prediction status until completion

Overview

Flux Depth Pro is designed for advanced image generation and manipulation tasks. It leverages control images, guidance settings, and upsampling capabilities to produce highly detailed and customized outputs. Its flexibility allows for both creative experimentation and precise outputs tailored to specific requirements.

Technical Specifications

Input Types: Supports a variety of input parameters including text prompts, control images, and detailed sliders for settings like guidance and steps.

Output Flexibility: Offers adjustable output formats and quality to suit diverse use cases.

Advanced Features: Safety tolerance ensures outputs are screened appropriately, while upsampling enhances fine details in generated images.

Key Considerations

Guidance vs. Creativity: High guidance values steer the output closer to the prompt, but may limit creative freedom. Lower values allow for more artistic interpretations.

Control Images: Using control images can help maintain consistency but may reduce the model’s creativity.

Steps: Increasing steps enhances image quality but can slow down processing time. Find a balance based on your priorities.

Safety Tolerance: Adjust this based on your content needs. Lower tolerance may flag outputs more strictly.

Legal Information

By using this model, you agree to:

Black Forest Labs API agreement
Black Forest Labs Terms of Service

Tips & Tricks

Seed Control: Use the same seed value for reproducibility. Experiment with different seeds to explore diverse outputs.

Steps and Guidance Tuning: Start with medium settings (e.g., steps: 20, guidance: 7) and adjust incrementally based on the results.

Control Image Usage: Use high-resolution and relevant control images to guide the model effectively. Blurry or unrelated images can negatively impact the result.

Prompt Structuring: Keep prompts clear and concise. Adding descriptors like “vivid,” “realistic,” or “high contrast” can significantly influence the outcome.

Safety Adjustments: Lower the safety tolerance for experimental work; increase it for professional or public-facing projects.

Capabilities

Visual Art Creation: Generate unique, artistic visuals based on detailed prompts.

Concept Visualization: Bring ideas to life for storyboards, prototypes, and creative projects.

Photo Enhancement and Editing: Use control images to refine and enhance photos with specific styles.

Creative Exploration: Experiment with different settings to produce imaginative and abstract results.

Professional Design: Tailor outputs for use in marketing, branding, and digital content creation.

What can I use for?

Image Generation: Create unique and detailed visuals based on textual prompts.

Style Transfer: Guide outputs using control images to adopt specific styles or structures.

Creative Projects: Experiment with abstract and imaginative ideas for artwork, design, and more.

Professional Applications: Use precise settings for tailored outputs in fields like marketing, design, and entertainment.

Things to be aware of

Artistic Interpretations: Experiment with abstract prompts like “a surreal dreamscape with vibrant colors.”
Photo Refinement: Input a control image to refine or enhance an existing photograph.
Style Combinations: Blend multiple styles by referencing distinct control images and prompts.
Concept Prototypes: Generate visual drafts for presentations, storyboards, or creative brainstorming.
Guidance Exploration: Compare outputs at different guidance values (e.g., 5, 10, 20) to understand how this impacts results.