Recraft v3 SVG

recraft-v3-svg

Recraft v3 SVG Model specializes in vector-based editing for scalable and precise designs.

Fast Inference
REST API

Model Information

Response Time~13 sec
StatusActive
Version
0.0.1
Updated8 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": "recraft-v3-svg",
"version": "0.0.1",
"input": {
"size": "1024x1024",
"style": "any",
"prompt": "your prompt here"
}
}
)
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: ~13 seconds
  • Rate limit: 60 requests/minute
  • Concurrent requests: 10 maximum
  • Use long-polling to check prediction status until completion

Overview

The Recraft V3 SVG model specializes in generating high-quality, scalable vector graphics (SVGs) based on user-provided inputs. This model is particularly valuable for creating intricate illustrations, designs, and artwork in various styles and sizes. It offers precision and flexibility, making it an ideal choice for digital artists, designers, and anyone looking to produce SVG files tailored to their creative needs.

Technical Specifications

Core Functionality: Recraft V3 SVG processes textual prompts to generate vector-based graphic outputs.

Supported Styles: Offers various artistic styles, including:

  • Engraving for detailed and textured designs.
  • Line Art for minimalist, clean graphics.
  • Line Circuit for technical or schematic aesthetics.
  • Linocut for bold, print-like designs.
  • Any for generalized results.

Size Parameters: Supports a wide range of aspect ratios and resolutions, ensuring versatility in design outputs.

Key Considerations

Input-Output Correlation: The complexity and relevance of the SVG are directly influenced by the prompt's detail level.

Performance Variability: Complex designs may require longer generation times. Plan accordingly for high-resolution outputs.

Output Adaptability: Generated outputs may require post-processing or refinement for specific use cases.

Legal Information for Recraft V3 SVG

By using this model, you agree to:

Tips & Tricks

Prompt for Recraft V3 SVG:

  • Use specific, descriptive language in prompts to guide the model effectively. For example:
    • “A detailed engraving of a forest scene at sunrise.”
    • “Minimalist line art of a modern city skyline.”

Size:

  • The model supports a variety of resolutions. Choose based on the use case:
    • 1024x1024 or 1365x1024 for standard designs.
    • 2048x1024 or larger for detailed outputs requiring high resolution.
    • For intricate details, larger aspect ratios like 1707x1024 ensure clarity.

Style:

  • Engraving: Best for designs needing texture and depth. Ideal for classical or historical themes.
  • Line Art: Perfect for minimalist and contemporary aesthetics.
  • Line Circuit: Suitable for schematics or technology-oriented projects.
  • Linocut: Great for bold, dramatic designs reminiscent of traditional printmaking.
  • Any: Use when uncertain about specific styles or for broader experimentation.

Optimization Tip for Recraft V3 SVG:

  • Start with 1024x1024 size and the Any style for general experiments. Once the output aligns with your vision, switch to a higher resolution and refine the style for the final result.

Capabilities

Scalable Outputs: Produces resolution-independent SVGs ideal for digital and print media.

Versatile Style Range: Supports diverse artistic and technical styles, catering to various creative needs.

Customizable Sizes: Offers a broad spectrum of resolutions and aspect ratios to suit specific design requirements.

What can I use for?

Graphic Design: Create scalable logos, banners, and illustrations.

Artistic Projects: Develop unique artworks in styles like linocut or engraving.

Educational Content: Generate schematics and diagrams using Line Circuit.

Web Design: Produce responsive, high-quality vector graphics for web applications.

Things to be aware of

Generate a line art illustration of a natural scene at 1280x1024 resolution for a clean and modern aesthetic with Recraft V3 SVG.

Experiment with engraving style to create a textured portrait or historical illustration.

Use 2048x1024 size for panoramic views, such as landscapes or cityscapes, in linocut style.

Design technical schematics in Line Circuit style for educational or professional use.

Limitations

Output Detail: Highly complex prompts may result in oversimplified outputs.

Style Consistency: Slight variations may occur in style application depending on the prompt.

Size Limitations: Extremely large or unconventional sizes may not perform optimally.

Output Format: SVG

Related AI Models

photon-flash

Photon Flash

photon-flash

Text to Image
recraft-20b

Recraft 20B

recraft-20b

Text to Image
fooocus-api

Fooocus

fooocus-api

Text to Image
flux-dev-lora

FLUX Dev LoRA

flux-dev-lora

Text to Image