Ideogram V2

ideogram-v2

Ideogram V2 is an model with state of the art inpainting, prompt comprehension and text rendering

Fast Inference

REST API

Try in Console API Docs Examples

Model Information

Response Time~20 sec

StatusActive

Version

0.0.1

Updated9 days ago

Live Demo

Average runtime: ~20 seconds

Input

Configure model parameters

Negative Prompt

Things you do not want to see in the generated image.

Enter your negative prompt

Prompt

Text prompt for image generation

An illustration of a blue running shoe with the text "Run AI with an API" written on the shoe. The shoe is placed on a blue background. The text is white and bold. The overall image has a modern and techy vibe.

aspect_ratio

An enumeration.

resolution

An enumeration.

Image

An image file to use for inpainting.

File upload is currently disabled

JPEGPNGJPGWEBP

style_type

An enumeration.

Output

View generated results

Result

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

Each execution costs $0.088 With $1 you can run this model about 11 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": "ideogram-v2",
            "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: ~20 seconds
Rate limit: 60 requests/minute
Concurrent requests: 10 maximum
Use long-polling to check prediction status until completion

Overview

Ideogram V2 is a model designed for generating high-quality images based on user-defined prompts. Ideogram V2 supports a wide range of customization options, allowing users to fine-tune the visual output according to their specific requirements. It provides flexibility in defining styles, resolutions, and aspect ratios to meet diverse creative needs.

Technical Specifications

Advanced Architecture: Ideogram V2 utilizes a transformer-based architecture optimized for image generation, ensuring consistent and high-quality results.

Style Versatility: Seamlessly transitions between diverse styles such as realism, anime, and 3D renders.

Fine-Tuning Capability: Accepts a wide range of input parameters, allowing precise control over the generated output.

Reproducibility: Supports deterministic results through seed values, enabling users to recreate or slightly vary outputs as needed.

Efficiency: Designed for optimized resource usage, balancing high-quality results with reasonable processing times.

Dynamic Composition: Handles various resolutions and aspect ratios to suit different formats, from wide landscapes to vertical portraits.

Key Considerations

Ensure the prompt matches the intended theme or visual context for the best results.
High resolutions can increase generation time; choose settings that balance quality and efficiency.
Avoid overly complex prompts, as they might lead to inconsistent or unpredictable outputs.

Tips & Tricks

Input Optimization for Better Results

Prompt:
- Use concise and descriptive language to articulate the visual elements clearly.
- Example: "A serene mountain landscape at sunset with soft lighting and vibrant colors."
- Avoid ambiguous or contradictory descriptions.
Negative Prompt:
- Define elements to exclude, such as "blurry edges," or "unrealistic colors."
- This refines the model’s focus and reduces unwanted artifacts.
Aspect Ratio:
- Choose the appropriate ratio based on your target use case:
  - 1:1 for social media posts.
  - 16:9 for wide landscapes or cinematic visuals.
  - 9:16 for vertical formats like stories.
- Stick to common ratios for better compatibility with standard display formats.
Resolution:
- For detailed visuals, select resolutions like 1536x512 or higher.
- Use 512x1536 or similar for faster previews or less demanding projects.
Magic Prompt Option:
- Set to Auto for automatic prompt enhancement if unsure.
- Use On for controlled enhancement or Off for full manual control.
Style Type:
- Match the style to your desired output:
  - Realistic for lifelike images.
  - Anime for stylized and animated appearances.
  - 3D Render for sharp and well-defined renders.
- Auto is a good starting point if uncertain about style preferences.
Seed:
- Use the same seed value to replicate results for consistency.
- Randomize the seed for varied outputs.

General Tips

Start with default settings to familiarize yourself with the model’s capabilities.
Gradually tweak one input at a time to understand its impact.
Review outputs and refine inputs iteratively to achieve the best results.

Capabilities

Versatile Image Generation: Ability to create visuals across various styles and formats.

Dynamic Customization: Tailor outputs with a rich set of inputs for precise control.

Creative Potential: From realistic photography to stylized illustrations, the model adapts to diverse creative needs.

What can I use for?

Creating visually engaging content for presentations, social media, and design projects.

Experimenting with artistic styles for concept art or illustrations.

Generating unique visuals for storytelling, branding, or marketing purposes.

Things to be aware of

Explore Different Aspect Ratios:
- Use 1:1 for balanced and centered compositions, such as profile pictures or social media posts.
- Experiment with 16:9 for cinematic wide landscapes or 9:16 for vertical content like stories.
Play with Resolutions:
- Start with mid-range resolutions like 768x1024 for quick generation and preview.
- Use higher resolutions such as 1536x640 for detailed visuals when finalizing projects.
Combine Prompts and Negative Prompts:
- Define a detailed positive prompt for your main idea and refine the result using a targeted negative prompt to eliminate unwanted elements.
Experiment with Style Types:
- Set the style to Realistic for lifelike images or Anime for a playful, animated feel.
- Test 3D Render for sharp, professional-quality renders.
Use Magic Prompt Option:
- Enable Auto for automated enhancement if you're unsure about prompt details.
- Manually refine prompts with the On setting for more control.
Seed for Controlled Variation:
- Reuse the same seed value to replicate specific results.
- Change the seed to explore variations of the same concept.
Layer Inputs Creatively:
- Combine inputs like masks and custom styles to achieve complex, multi-layered visuals.