ByteDance with Eachlabs
ByteDance's new video model, OmniHuman, is available on Eachlabs →
Eachlabs | AI Workflows for app builders

Ideogram V2 Turbo

ideogram-v2-turbo

A fast image model with state of the art inpainting, prompt comprehension and text rendering

Fast Inference
REST API
Try in ConsoleAPI DocsExamples

Model Information

Response Time~12 sec
StatusActive
Version
0.0.1
Updated9 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": "ideogram-v2-turbo",
            "version": "0.0.1",
            "input": {
  "mask": "your_file.image/jpeg",
  "seed": null,
  "image": "your_file.image/jpeg",
  "prompt": "your prompt here",
  "resolution": "None",
  "style_type": "None",
  "aspect_ratio": "1:1",
  "negative_prompt": "your negative prompt here",
  "magic_prompt_option": "Auto"
}
        }
    )
    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: ~12 seconds
  • Rate limit: 60 requests/minute
  • Concurrent requests: 10 maximum
  • Use long-polling to check prediction status until completion

Overview

Ideogram V2 Turbo is an advanced model designed for generating and manipulating images based on various input parameters. By adjusting different inputs, users can create images that meet specific creative and technical requirements. Whether you're looking to generate a detailed artistic image, adjust resolution, or customize the style, Ideogram V2 Turbo offers flexibility and precision to meet your needs.

Technical Specifications

Ideogram V2 Turbo is designed for rapid image generation, focusing on ideation and creative outputs.

Ideogram V2 Turbo is capable of understanding and rendering detailed prompts and negative prompts.

It supports inpainting capabilities, allowing for modifications or enhancements to specific areas of an image.

Advanced text rendering features enable seamless integration of text within generated visuals.

Ideogram V2 Turbo generates outputs quickly, typically within 7 to 12 seconds per image.

Key Considerations

Resolution and Aspect Ratio: High resolution and wide aspect ratios (e.g., 16:9) can be resource-intensive. Consider balancing image quality and efficiency based on your needs and available resources.

Magic Prompt: If magic_prompt_option is set to on, it automatically fine-tunes the generated image. For specific creative control, set this to off.

Image Masking: When using an image or mask, make sure the mask is aligned with the areas of the image you want to alter. It can help create more specific results.

Tips & Tricks

  • Effective Use of Aspect Ratio:
    • For a balanced image, use 1:1.
    • For wide landscapes, choose 16:9 or 3:1.
    • For vertical images, try 9:16 or 3:4.
  • Resolution:
    • Use 512x1536 for long vertical images or 1024x1024 for detailed square images.
    • Select 1536x512 or 1536x640 for highly detailed wide-format images.
  • Seed:
    • Set a seed value if you need reproducibility for the same prompt.
    • If you desire random variations in the result, leave the seed undefined.
  • Style Types:
    • Realistic style provides life-like images suitable for photorealism.
    • Use 3D Render for computer-generated imagery or stylized 3D representations.
    • Anime gives a cartoonish, yet detailed art style.
  • Image Input:
    • Upload an image that aligns with your desired output. For example, uploading an image of a landscape will allow the model to generate a similar scene based on your prompt.
    • Masking: If you need to preserve certain regions of the image while generating new areas, upload a mask image that marks areas to alter or preserve.
  • Magic Prompt Option:
    • Use auto for the model to optimize the output with minimal input adjustments.
    • Set on to fully optimize based on the prompt.
    • Set off for more manual control over the image generation.

Capabilities

Versatile Image Generation: Ideogram V2 Turbo is capable of generating a variety of image styles and formats, from realistic depictions to artistic renderings.

Customizability: With input options for aspect ratio, resolution, and style, users have fine-grained control over their generated images.

Image Modification: When used with an input image and mask, the model can modify specific areas while leaving the rest intact.

What can I use for?

Art Creation: Ideal for digital artists looking to generate new artwork or modify existing ones.

Design: Useful for graphic designers needing custom images or backgrounds for their projects.

Concept Visualization: Perfect for visualizing concepts in various artistic styles, including realistic, 3D renderings, and anime.

Content Generation: Generate images for blogs, social media posts, and other content-based platforms.

Things to be aware of

Experiment with different aspect_ratios to see how the image composition changes.

Adjust the resolution based on the final use case — high resolution for print, lower resolution for web use.

Use style_type to explore various art styles and discover unique variations of your prompts.

Upload your own image with a mask to modify certain parts, like changing the background or adjusting specific features.

Limitations

Resolution Constraints: High resolution may not always be available depending on computational limitations or time constraints.

Complex Prompts: If the prompt is too vague or overly complex, it might result in unexpected or inconsistent outputs.

Style Restrictions: Some specific art styles may not be as accurately rendered in certain resolution settings.


Output Format: PNG

Related AI Models

stable-diffusion-3.5-medium

Stable Diffusion 3.5 Medium

stable-diffusion-3-5-medium

Text to Image
flux-1.1-pro

Flux 1.1 Pro

flux-1-1-pro

Text to Image
flux-dev

Flux Dev

flux-dev

Text to Image
sana

Sana by Nvidia

sana

Text to Image