Skip to content
TheChatArchiveThe Chat Archive
gpt-3.5-turbo-0613· OpenAIHugging Face Arena Human Preference 55K

Can you create python code that generates a svg image of a unicorn using swgwrite?

From a Chatbot Arena battleThe same person sent this prompt to two anonymous models at once. Compare it with Mistralmistral-medium’s answer.
  1. User

    Can you create python code that generates a svg image of a unicorn using swgwrite?

  2. Assistant

    Certainly! Here's an example of Python code that uses the svgwrite library to generate an SVG image of a unicorn:

    import svgwrite
    
    def draw_unicorn():
        dwg = svgwrite.Drawing('unicorn.svg', profile='tiny')
        
        # Draw the unicorn's body
        body = dwg.add(dwg.g())
        body.add(dwg.ellipse(center=(300, 400), r=(120, 150), fill='white', stroke='black'))
        
        # Draw the unicorn's head
        head = dwg.add(dwg.g())
        head.add(dwg.ellipse(center=(300, 270), r=(90, 100), fill='white', stroke='black'))
        
        # Draw the unicorn's horn
        horn = dwg.add(dwg.g())
        horn.add(dwg.polygon(points=[(300, 150), (320, 200), (280, 200)], fill='gold', stroke='black'))
        
        # Draw the unicorn's eyes
        eyes = dwg.add(dwg.g())
        eyes.add(dwg.circle(center=(280, 250), r=10, fill='black'))
        eyes.add(dwg.circle(center=(320, 250), r=10, fill='black'))
        
        # Draw the unicorn's mane
        mane = dwg.add(dwg.g())
        mane.add(dwg.polygon(points=[(240, 300), (280, 200), (320, 200), (360, 300)], fill='pink', stroke='black'))
        
        # Draw the unicorn's tail
        tail = dwg.add(dwg.g())
        tail.add(dwg.polyline(points=[(340, 450), (380, 500), (420, 550)], fill='none', stroke='black', stroke_width=3))
        
        dwg.save()
    
    draw_unicorn()
    

    This code creates an SVG image file named "unicorn.svg" that contains a simple representation of a unicorn. You can modify the code and add more details to the unicorn as desired.

Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.