Input
Configure model parameters
Output
View generated results
Result
Preview, share or download your results with a single click.
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 requestsimport timeAPI_KEY = "YOUR_API_KEY" # Replace with your API keyHEADERS = {"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": "real-esrgan-a100","version": "0.0.1","input": {"image": "your_file.image/jpeg","scale": 4,"face_enhance": false},"webhook_url": ""})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 resultelif 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 predictionprediction_id = create_prediction()print(f"Prediction created: {prediction_id}")# Get resultresult = 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: ~62 seconds
- Rate limit: 60 requests/minute
- Concurrent requests: 10 maximum
- Use long-polling to check prediction status until completion
Overview
Real-ESRGAN (Enhanced Super-Resolution Generative Adversarial Networks) uses advanced deep learning techniques to upscale low-resolution images. It not only improves the resolution but also restores details, textures, and sharpness, making it ideal for professional photographers, graphic designers, and everyday users.
Technical Specifications
Model Architecture:
- Based on ESRGAN (Enhanced Super-Resolution GAN).
- Trained on large datasets of diverse images for generalization.
Input Requirements:
- Formats: JPEG, PNG, TIFF.
- Recommended Resolution: Up to 720p for optimal performance on the 4x upscale model.
- Max File Size: 20 MB.
Output:
- Formats: JPEG, PNG, TIFF.
- Maximum Resolution: Supports 8K output with no visible loss of quality.
Key Considerations
Artifacts in Low-Quality Images:
- Overly compressed or noisy images may introduce artifacts during upscaling.
Output Consistency:
- Results may vary for complex or heavily edited images.
Tips & Tricks
Maximize Detail Restoration:
- Use the scale 4 model for images requiring the most detail recovery.
Image Cropping:
- Crop images into smaller sections for faster processing of high-res files.
Enable the "Face Enhance" feature for better facial details in portraits.
Capabilities
Super-Resolution Upscaling:
- Enhance images by up to 4x their original resolution without losing quality.
Detail Restoration:
- Rebuild lost textures and sharpen edges for a natural look.
What can I use for?
Photography Enhancement:
- Perfect for improving resolution and details in professional or personal photos.
Graphic Design:
- Enhance assets like icons, logos, or textures for high-res displays.
Video Frame Upscaling:
- Use upscaled images as keyframes in video editing or restoration projects.
Art Preservation:
- Restore and upscale digital or scanned artworks.
E-Commerce and Marketing:
- Improve product images for websites or advertisements.
Restoring old or low-resolution photos.
Enhancing image quality for professional use.
Upscaling images for printing or large-format displays.
Improving facial details in portrait photography.
Things to be aware of
Upscale Old Photos:
- Revive family photos by enhancing resolution and restoring lost details.
Improve Social Media Images:
- Transform compressed images into sharp, professional-looking visuals.
Enhance Game Textures:
- Use for modding or improving in-game textures in older titles.
Create Print-Ready Images:
- Prepare low-res digital images for high-quality printing.
Test on Unique Styles:
- Try upscaling cartoon, anime, or stylized images to explore model versatility.
Restoration: Upload a vintage photo and upscale it using a scale of 2x.
Face Enhancement: Enable the face_enhance option for high-quality portraits.
Creative Editing: Experiment with different scale values to achieve desired effects.
Limitations
Texture Consistency:
- Fine textures like grass or water may occasionally look unnatural after enhancement.
Output Format: PNG
Related AI Models
You can seamlessly integrate advanced AI capabilities into your applications without the hassle of managing complex infrastructure.
GPT-1 Image Edit
OpenAI Image Edit lets you modify images by removing, adding, or changing parts. It uses AI to fill in the selected area naturally.
Action Figure Generator
Action Figure Generator turns images into new versions by selecting from ready-made templates, streamlining creative image generation.
Eachlabs Face Swap
Swap faces between images effortlessly! Integrate your app with the Faceswap model by Eachlabs for smooth and seamless transformations.
Flux Kontext Pro Multi Image
An experimental model with FLUX Kontext Pro that can combine two input images