add funny comment "I bet he can play Bach in his sleep... which is great, because his fingers are always dreaming of harpsichords."
// Portrait of Mahan Esfahani, the Iranian harpsichordist
// He sits in front of a harpsichord with his fingers on the keys
// The background is a gradient from light green to dark green
// His skin is a warm tan color
// He wears a black suit with a white shirt and a black bow tie
// The harpsichord is wooden with gold detailing
// The keys are white with black sharps and flats
// A sheet of music is open on the stand
// The notes on the sheet are hyper realistic, as if floating off the page
// Mahan's expression is focused, yet relaxed
// He appears to be lost in the music
ctx.fillStyle = 'linear-gradient(to bottom, #9ACD32, #006400)'; // set background gradient
ctx.fillRect(0, 0, 512, 512); // draw background
// draw Mahan Esfahani
ctx.fillStyle = '#D2B48C'; // set skin color
ctx.beginPath();
ctx.arc(256, 256, 150, 0, 2 * Math.PI); // draw head
ctx.fill();
// draw suit
ctx.fillStyle = '#000000'; // set suit color
ctx.fillRect(156, 296, 200, 150); // draw jacket
ctx.fillRect(156, 446, 200, 20); // draw pants
// draw shirt
ctx.fillStyle = '#FFFFFF'; // set shirt color
ctx.fillRect(206, 296, 100, 100); // draw shirt
// draw bow tie
ctx.fillStyle = '#000000'; // set bow tie color
ctx.beginPath();
ctx.moveTo(256, 346); // start at center of shirt
ctx.lineTo(226, 376); // draw left side of bow tie
ctx.lineTo(256, 406); // draw bottom of bow tie
ctx.lineTo(286, 376); // draw right side of bow tie
ctx.fill();
// draw harpsichord
ctx.fillStyle = '#8B4513'; // set harpsichord color
ctx.fillRect(50, 150, 412, 100); // draw body of harpsichord
ctx.fillStyle = '#FFD700'; // set detailing color
ctx.fillRect(50, 150, 412, 20); // draw gold detailing at top of harpsichord
ctx.fillRect(50, 230, 412, 20); // draw gold detailing at bottom of harpsichord
ctx.fillRect(50, 150, 20, 100); // draw gold detailing on left side of harpsichord
ctx.fillRect(442, 150, 20, 100); // draw gold detailing on right side of harpsichord
ctx.fillStyle = '#FFFFFF'; // set key color
ctx.fillRect(80, 170, 352, 60); // draw white keys
ctx.fillStyle = '#000000'; // set black key color
ctx.fillRect(118, 170, 20, 40); // draw first set of black keys
ctx.fillRect(190, 170, 20, 40);
ctx.fillRect(262, 170, 20, 40);
ctx.fillRect(334, 170, 20, 40);
ctx.fillRect(406, 170, 20, 40);
ctx.fillRect(148, 210, 20, 40); // draw second set of black keys
ctx.fillRect(220, 210, 20, 40);
ctx.fillRect(292, 210, 20, 40);
ctx.fillRect(364, 210, 20, 40);
// draw sheet of music
ctx.fillStyle = '#FFFFFF'; // set sheet color
ctx.fillRect(100, 50, 312, 100); // draw sheet of music
ctx.fillStyle = '#000000'; // set note color
ctx.font = 'bold 24px Arial'; // set font
ctx.fillText('♩ ♪ ♫ ♬', 210, 110); // draw notes
// add title
// "Mahan Esfahani: Harpsichord Virtuoso"
// (I hope he likes it!)
// add funny comment
// "I bet he can play Bach in his sleep... which is great, because his fingers are always dreaming of harpsichords."
These are recent AI images made by the community!
DrawGPT is a an AI art generator that uses the GPT-3, GPT-4, DALL-E 3, Custom GPTs, ChatGPT, and other large language models by OpenAI to generate new images from text prompts.
The AI is able to express itself visually through words by writing code to draw and create unique images. This is the same AI powering the very popular ChatGPT large language model AI.
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.
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!
DrawGPT is runs on an AI that has never actually "seen" an image as embodied AI in its life!
GPT-3, GPT-4, ChatGPT, and DALL-E 3 only allow input from words. Even GPT-4V which uses image recogintion via AI converts the output to words for use with other AI models. That makes their understanding of the visual world extremely unusual. This AI is able to draw images just like ChatGPT can draw images.
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.
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.
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 are made public during submission.
Depending on the situation the prompts themselves are stored internally for research purposes but given that people are morons and put things in there like personal information it is unlikely DrawGPT would ever be able to release the raw prompts publicly.
Employees at OpenAI and DrawGPT have access to any prompts you submit.
DO NOT SUBMIT PERSONAL INFORMATION.
No.