Stable Dıffusion 3.5 Large Turbo

stable-diffusion-3.5-large-turbo

A fast and efficient model for generating high-quality images using diffusion techniques.

Fast Inference

REST API

Try in Console API Docs Examples

Model Information

Response Time~2 sec

StatusActive

Version

0.0.1

Updated7 days ago

Live Demo

Average runtime: ~2 seconds

Input

Configure model parameters

Prompt Strength

Prompt strength (or denoising strength) when using image to image. 1.0 corresponds to full destruction of information in image.

0.85

Prompt

Text prompt for image generation

An impasto horse

aspect_ratio

An enumeration.

Cfg

The guidance scale tells the model how similar the output should be to the prompt.

Image

Input image for image to image mode. The aspect ratio of your output will match this image.

File upload is currently disabled

JPEGPNGJPGWEBP

output_format

An enumeration.

Output

View generated results

Result

Preview, share or download your results with a single click.

Each execution costs $0.044 With $1 you can run this model about 22 times.

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": "stable-diffusion-3.5-large-turbo",
            "version": "0.0.1",
            "input": {
  "cfg": "1",
  "seed": null,
  "image": "your_file.image/jpeg",
  "steps": "4",
  "prompt": "your prompt here",
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "output_quality": "90",
  "prompt_strength": "0.85"
}
        }
    )
    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: ~2 seconds
Rate limit: 60 requests/minute
Concurrent requests: 10 maximum
Use long-polling to check prediction status until completion

Overview

Stable Dıffusion 3.5 Large Turbo is designed to generate highly realistic and detailed outputs based on input prompts and specific configurations. It excels at creating content with fine detail, offering flexible control over style, quality, and aspect ratio. Whether you're using it for artistic projects, professional designs, or exploratory purposes, the model adapts to a variety of creative needs.

Technical Specifications

prompt: Text input describing the desired output.
image: Optional image input for conditional generation.
cfg: Controls adherence to the prompt. Higher values yield results closer to the prompt but might reduce creativity.
steps: Defines the number of processing iterations. Higher steps improve quality but require more time.
prompt_strength: Determines how strongly the prompt influences the output.
aspect_ratio: Specifies the output dimensions..
output_quality: Adjusts the quality of the generated output.
seed: Ensures reproducibility.

Key Considerations

Outputs depend heavily on the clarity and specificity of the prompt.
Processing time increases with higher steps and quality settings.
Ensure prompt strength is optimized to prevent overpowering input images.
The model's outputs are only as good as the initial configurations and inputs provided.

Legal Information

By using this model, you agree to:

Stability AI API agreement
Stability AI Terms of Service

Tips & Tricks

Prompt Design: Craft clear and descriptive prompts for the best results. Adding context, style preferences, or specific details can significantly enhance output quality.
Aspect Ratio: Choose an aspect ratio that complements the subject or output goal. For example, use 16:9 for wide scenes and 1:1 for square designs.
Seed: Fix the seed value for consistent outputs across multiple runs. Useful for reproducing specific designs.
Steps: Higher steps generally improve image quality, but processing time increases. Use moderate values for quick iterations and higher values for final renders.
Prompt Strength: Balance prompt strength to ensure the input image and the textual prompt contribute effectively. Higher strength gives more weight to the prompt, while lower strength retains the original image details.
Output Quality: Adjust output_quality for the intended use. High quality is ideal for professional work, while medium quality saves processing time for drafts.
Use cfg values between 7-10 for a good balance of creativity and prompt alignment.

Capabilities

Generates high-quality images based on textual or combined text-image inputs.
Supports various aspect ratios and resolutions for versatile use cases.
Allows fine-tuning of quality, format, and style.

What can I use for?

Artistic creations: Illustrations, concept art, and posters.
Professional design: Product mockups, marketing materials, and branding.
Visual storytelling: Storyboards, visual novels, or animations.

Things to be aware of

Artistic Exploration: Combine an input image with a descriptive prompt for unique styles.
Recreation: Use the same seed and prompt with varying steps to find the best outcome.
Thematic Creations: Experiment with prompts that evoke specific emotions or themes.
Aspect Ratios: Create outputs optimized for social media by selecting 1:1 or 4:5 ratios.