City beneath the surface

City beneath the surface - DrawGPT
una ciudad subterranea
Bot
I hope they have good ventilation down here!

Javascript Code

                        // City beneath the surface
ctx.fillStyle = "#000000"; // Setting background color to black
ctx.fillRect(0, 0, 512, 512); // Drawing a black rectangle to fill the canvas

// Creating buildings
ctx.fillStyle = "#333333"; // Setting building color to dark gray
ctx.fillRect(100, 150, 50, 200); // Drawing a tall building
ctx.fillRect(200, 100, 100, 250); // Drawing a wider building
ctx.fillRect(350, 200, 75, 150); // Drawing a shorter building
ctx.fillRect(430, 50, 50, 300); // Drawing a skinny building

// Creating windows
ctx.fillStyle = "#ffffff"; // Setting window color to white
for (let i = 115; i < 150; i += 25) {
for (let j = 165; j < 345; j += 25) {
ctx.fillRect(j, i, 10, 10); // Drawing windows on the tall building
}
}
for (let i = 120; i < 300; i += 25) {
for (let j = 215; j < 285; j += 25) {
ctx.fillRect(j, i, 10, 10); // Drawing windows on the wider building
}
}
for (let i = 225; i < 325; i += 25) {
for (let j = 375; j < 425; j += 25) {
ctx.fillRect(j, i, 10, 10); // Drawing windows on the shorter building
}
}
for (let i = 75; i < 325; i += 25) {
for (let j = 445; j < 495; j += 25) {
ctx.fillRect(j, i, 10, 10); // Drawing windows on the skinny building
}
}

// Creating streetlights
ctx.fillStyle = "#ffcc33"; // Setting streetlight color to yellow
ctx.fillRect(120, 380, 10, 50); // Drawing the first streetlight
ctx.fillRect(280, 380, 10, 50); // Drawing the second streetlight
ctx.fillRect(385, 280, 10, 50); // Drawing the third streetlight
ctx.fillRect(450, 380, 10, 50); // Drawing the fourth streetlight

// Creating stairs
ctx.fillStyle = "#666666"; // Setting stair color to dark gray
ctx.fillRect(50, 450, 50, 10); // Drawing the first stair
ctx.fillRect(40, 460, 70, 10); // Drawing the second stair
ctx.fillRect(30, 470, 90, 10); // Drawing the third stair

// Creating the entrance
ctx.fillStyle = "#cc9966"; // Setting entrance color to brown
ctx.fillRect(250, 400, 50, 50); // Drawing the entrance

// Creating the sign
ctx.fillStyle = "#ffffff"; // Setting sign color to white
ctx.fillRect(265, 370, 20, 20); // Drawing the sign
ctx.fillStyle = "#000000"; // Setting text color to black
ctx.font = "12px Arial"; // Setting font size and type
ctx.fillText("Entrance", 255, 385); // Adding text to the sign

// Adding shadows
ctx.fillStyle = "rgba(0, 0, 0, 0.5)"; // Setting shadow color to transparent black
ctx.fillRect(110, 360, 40, 10); // Adding a shadow to the first streetlight
ctx.fillRect(270, 360, 40, 10); // Adding a shadow to the second streetlight
ctx.fillRect(375, 260, 40, 10); // Adding a shadow to the third streetlight
ctx.fillRect(440, 360, 40, 10); // Adding a shadow to the fourth streetlight
ctx.fillRect(110, 460, 80, 10); // Adding a shadow to the stairs
ctx.fillRect(240, 410, 70, 10); // Adding a shadow to the entrance

// Adding highlights
ctx.fillStyle = "rgba(255, 255, 255, 0.5)"; // Setting highlight color to transparent white
ctx.fillRect(110, 350, 40, 10); // Adding a highlight to the first streetlight
ctx.fillRect(270, 350, 40, 10); // Adding a highlight to the second streetlight
ctx.fillRect(375, 250, 40, 10); // Adding a highlight to the third streetlight
ctx.fillRect(440, 350, 40, 10); // Adding a highlight to the fourth streetlight
ctx.fillRect(120, 440, 70, 10); // Adding a highlight to the stairs
ctx.fillRect(240, 400, 70, 10); // Adding a highlight to the entrance

// Adding some flora
ctx.fillStyle = "#33cc33"; // Setting flower color to green
ctx.beginPath(); // Starting a new path
ctx.arc(80, 170, 10, 0, 2 * Math.PI); // Drawing a circle for the flower
ctx.fill(); // Filling in the circle
ctx.fillStyle = "#ffccff"; // Setting petal color to pink
ctx.beginPath(); // Starting a new path
ctx.arc(80, 170, 5, 0, 2 * Math.PI); // Drawing a circle for the petal
ctx.fill(); // Filling in the circle
ctx.rotate(45 * Math.PI / 180); // Rotating the canvas by 45 degrees
ctx.beginPath(); // Starting a new path
ctx.arc(140, -10, 10, 0, 2 * Math.PI); // Drawing a circle for the flower
ctx.fill(); // Filling in the circle
ctx.fillStyle = "#ffff66"; // Setting petal color to yellow
ctx.beginPath(); // Starting a new path
ctx.arc(140, -10, 5, 0, 2 * Math.PI); // Drawing a circle for the petal
ctx.fill(); // Filling in the circle

// Adding a happy mole person
ctx.fillStyle = "#996633"; // Setting mole person color to brown
ctx.beginPath(); // Starting a new path
ctx.arc(350, 450, 30, 0, 2 * Math.PI); // Drawing a circle for the body
ctx.fill(); // Filling in the circle
ctx.beginPath(); // Starting a new path
ctx.arc(350, 420, 20, 0, Math.PI); // Drawing a half circle for the head
ctx.fill(); // Filling in the half circle
ctx.beginPath(); // Starting a new path
ctx.arc(340, 410, 5, 0, 2 * Math.PI); // Drawing a circle for the left eye
ctx.fill(); // Filling in the circle
ctx.beginPath(); // Starting a new path
ctx.arc(360, 410, 5, 0, 2 * Math.PI); // Drawing a circle for the right eye
ctx.fill(); // Filling in the circle
ctx.beginPath(); // Starting a new path
ctx.arc(350, 430, 10, 0, Math.PI, true); // Drawing a half circle for the mouth
ctx.stroke(); // Drawing the half circle

// Adding a happy bird person
ctx.fillStyle = "#0099cc"; // Setting bird person color to blue
ctx.beginPath(); // Starting a new path
ctx.arc(450, 120, 30, 0, 2 * Math.PI); // Drawing a circle for the body
ctx.fill(); // Filling in the circle
ctx.beginPath(); // Starting a new path
ctx.arc(450, 90, 20, 0, Math.PI); // Drawing a half circle for the head
ctx.fill(); // Filling in the half circle
ctx.beginPath(); // Starting a new path
ctx.arc(440, 80, 5, 0, 2 * Math.PI); // Drawing a circle for the left eye
ctx.fill(); // Filling in the circle
ctx.beginPath(); // Starting a new path
ctx.arc(460, 80, 5, 0, 2 * Math.PI); // Drawing a circle for the right eye
ctx.fill(); // Filling in the circle
ctx.beginPath(); // Starting a new path
ctx.moveTo(455, 95); // Moving to the starting point of the beak
ctx.lineTo(465, 100); // Drawing a line for the beak
ctx.lineTo(455, 105); // Drawing another line for the beak
ctx.closePath(); // Closing the path
ctx.fill(); // Filling in the path

// Adding a happy worm person
ctx.fillStyle = "#ff99ff"; // Setting worm person color to pink
ctx.beginPath(); // Starting a new path
ctx.arc(200, 400, 15, 0, 2 * Math.PI); // Drawing a circle for the body
ctx.fill(); // Filling in the circle
ctx.beginPath(); // Starting a new path
ctx.arc(200, 390, 10, 0, Math.PI); // Drawing a half circle for the head
ctx.fill(); // Filling in the half circle
ctx.beginPath(); // Starting a new path
ctx.arc(195, 385, 3, 0, 2 * Math.PI); // Drawing a circle for the left eye
ctx.fill(); // Filling in the circle
ctx.beginPath(); // Starting a new path
ctx.arc(205, 385, 3, 0, 2 * Math.PI); // Drawing a circle for the right eye
ctx.fill(); // Filling in the circle

// Adding a happy comment
// I hope they have good ventilation down here!

Info

Created On: June 10, 2023
Created By: @DrawGPT

AI

Model: gpt-3.5-turbo-0301
Time: 89 seconds
Prompt Tokens: 182
Completion Tokens: 2103
Total Token Cost: 2285
DrawGPT logo DrawGPT logo

Compare & Benchmark AI Models

Try the new DrawGPT Compare

  • Instantly compare the latest AI models side-by-side.
  • Top models: GPT, Gemini, Claude, Grok, SDXL.
  • From OpenAI, Google, Anthropic, xAI, Scenario.gg.
  • Generate images or text with multiple models at once.
  • See results in real time, share, and benchmark.
Try DrawGPT Compare →
DrawGPT Compare demo
DrawGPT logo DrawGPT logo

Draw, Sketch, Paint, or Doodle Instantly

This is where you can draw anything—then AI turns it into real 3D images and more!

  • Draw, sketch, paint, or doodle anything right in your browser.
  • AI transforms your creations into 3D images, vector art, and more.
  • Create images from text prompts using top AI models: DALL-E 3, Gemini, Stable Diffusion, and more.
  • No subscription required – just use tokens for each image.
  • Download as PNG, SVG, or vector graphics.
  • Perfect for logos, icons, art, textures, patterns, and game assets.
  • Type anything, get an image instantly. Commercial use allowed!
Try DrawGPT Draw →
DrawGPT Draw demo

NEW COMMUNITY AI IMAGES


These are recent AI images made by the community! These may use any AI model including DALL-E 3, Flux, Stable Diffusion, GPT-4, o1, and more and may be anything from simple animated SVGs to PNGs.

FAQ

What is DrawGPT?

DrawGPT is a an AI art generator that uses GPT-4, o1, o3, DALL-E 3, Gemini 2.0, Imagegen 3.0, Flux, Stable Diffusion, and Custom GPTs, ChatGPT, and other large language models to generate new images from text prompts.

Why Is This Different?

This does not require access to premium AI model subscriptions, it is able to be used by anyone with an internet connection and tokens. This allows everyone to get access to the very best AI art generation technology.

Artificial intelligence may create strange or unusual images. It is being used to generated images for advertising, entertainment, gaming, marketing, and fun right now!

Because Draw GPT has access to do many models we assume the model providers have followed best practices when attributing or utilizing data and images in the training data.

Yes! You can use the images for commercial purposes! And so can Draw GPT.

What Can DrawGPT Draw?

DrawGPT can draw anything you can think of and more! Just type your text prompt in to the textbox exactly like ChatGPT and see what the AI gives you! Seriously, you can get GPT to draw just about anything for you that you can type in the box.

DrawGPT creates images in PNG, SVG, and Javascript format for download and use. This is different than other AI art projects that only create images in PNG format; being able to get a scene graph via Javascript draw commands is a unique feature of this project and getting any AI art in SVG vector format is unique to DrawGPT.

Many people use this to generate quick art for simple projects, video game assets, new business logos, and more. It is also used to generate images for advertising, entertainment, gaming, marketing, creating art for ads and blog posts with AI and fun.

Want to learn more about DrawGPT, the types of possible image renders, and how to use DrawGPT in your next project as a developer?
Check out our AI image generation API!

Why Are They Weird?

DrawGPT is runs on an AI that has never actually "seen" an image as embodied AI in its life!

This method of drawing images using raw code is not a great way to draw complex images with lots of structure. It may be able to make photograph quality artwork and professional illustrations with AI but it can fail when using certain types of typography.

Is This ChatGPT?

Yes and no. Same same but different.

ChatGPT runs on the same model that this project uses, so this is like using ChatGPT to generate images, but it is a different instance of the model. This means that the AI is not precisly the same but it is the same quality AI, image generation AI, large language model, and overall AI art that ChatGPT is using and that Chat GPT can draw.

What is the difference? ChatGPT is specifically wired up to be conversational and track a conversation thread across multiple user prompts. Images in ChatGPT using DALL-E 3 are not saved to the Intenet and made available publicly.

In comparison DrawGPT does not remember things from prompt to prompt, each image is a unique image that does not reference any of the images or prompts previously supplied.

Copyright

You can do what you want it's your party.

We humbly ask that you backlink to DrawGPT if you do use our images in any promotion or commercial ways, but it is not required.

At the moment all images & Javascript code generated by this tool under the CC0 License with outrageous added term that the license can be revoked or retroactively changed at any time without warning for any image.

Yes! You can use the images for commercial purposes! And so can DrawGPT.

Images & Prompts Private

Images & prompts may be made made public.

Depending on the situation the prompts themselves are stored internally for research purposes.

Employees at OpenAI and DrawGPT have access to any prompts you submit.

DO NOT SUBMIT PERSONAL INFORMATION.