Imagen 3

imagen-3

Google's highest quality text-to-image model, Imagen-3 is capable of generating images with detail, rich lighting and beauty

Fast Inference
REST API

Model Information

Response Time~15 sec
StatusActive
Version
0.0.1
Updated9 days ago

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": "imagen-3",
"version": "0.0.1",
"input": {
"prompt": "your prompt here",
"aspect_ratio": "1:1",
"negative_prompt": "your negative prompt here",
"safety_filter_level": "block_medium_and_above"
}
}
)
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: ~15 seconds
  • Rate limit: 60 requests/minute
  • Concurrent requests: 10 maximum
  • Use long-polling to check prediction status until completion

Overview

Imagen 3 is a text-to-image generative model developed by Google Deepmind to produce high-quality images from textual descriptions. It excels in understanding natural language prompts and generating images with enhanced detail, lighting, and reduced artifacts. The Imagen 3 supports various artistic styles, ranging from photorealism to abstract art.

Technical Specifications

  • Architecture: Imagen 3 employs a latent diffusion model, enabling efficient and high-quality image generation from text prompts.
  • Training Data: The Imagen 3 is trained on a diverse dataset comprising various image styles and subjects, enhancing its ability to generate a wide range of visuals.
  • Resolution: Capable of producing images with high resolution, capturing fine details and textures.
  • Language Understanding: Enhanced natural language processing allows for better comprehension of complex prompts, resulting in more accurate image representations.

Key Considerations

Content Sensitivity: While the Imagen 3 includes safety filters, always review generated images to ensure they meet content standards, especially in sensitive contexts.

Prompt Specificity: Overly complex or ambiguous prompts may lead to unexpected results. Strive for clarity and specificity in your descriptions.



Legal Information for Imagen 3

By using this Imagen 3, you agree to:

Tips & Tricks

Optimizing Prompts for Imagen 3:

  • Clarity: Use clear and concise language to describe the desired image.
  • Detail: Incorporate specific details such as colors, lighting, and composition to guide Imagen 3.
  • Style Specification: Mention the desired artistic style (e.g., "watercolor painting," "digital art") to influence the output.

Negative Prompt Usage:

  • Exclusion: Clearly state elements to avoid in the negative_prompt to prevent their inclusion.
  • Testing: Experiment with different negative prompts to see their impact on the generated image.

Aspect Ratio Selection:

  • Purpose Alignment: Choose an aspect ratio that fits the intended use of the image (e.g., 16:9 for widescreen displays).
  • Consistency: Maintain consistent aspect ratios when generating images for a cohesive look.

Safety Filter Configuration:

  • Contextual Adjustment: Set the safety_filter_level based on the context and audience of the images.
  • Review: Even with filters, always review images to ensure appropriateness.

Capabilities

Diverse Style Generation: Produces images across various styles, including photorealistic, illustrative, and abstract art.

High-Resolution Output: Generates detailed images suitable for professional and creative use cases.

Natural Language Comprehension: Understands and interprets detailed textual descriptions to create corresponding visuals.

What can I use for?

Creative Design: Assists artists and designers in visualizing concepts and generating inspiration.

Marketing Materials: Generates visuals for advertising, social media, and promotional content.

Educational Resources: Creates illustrative content to support learning materials and presentations.

Things to be aware of

Style Exploration: Experiment with different artistic styles by specifying them in your prompts.

Detail Variation: Adjust the level of detail in prompts to see how Imagen 3 interprets and represents various complexities.

Negative Prompt Testing: Use the negative_prompt to refine images by excluding certain elements and observe the changes.

Limitations

Complex Scenes: Imagen 3 may struggle with highly complex scenes involving numerous interacting elements.

Text Generation: Rendering legible text within images can be challenging and may not always be accurate.

Abstract Concepts: Interpreting and visualizing highly abstract or conceptual prompts may lead to unpredictable results.


Output Format: PNG

Related AI Models

ideogram-v2-turbo

Ideogram V2 Turbo

ideogram-v2-turbo

Text to Image
ideogram-v2

Ideogram V2

ideogram-v2

Text to Image
stable-diffusion-3.5-large-turbo

Stable Dıffusion 3.5 Large Turbo

stable-diffusion-3-5-large-turbo

Text to Image
recraft-v3

Recraft V3

recraft-v3

Text to Image