<!--
Generated by DrawGPT.
Free, open source, AI generated images in SVG, PNG, and HTML Canvas format.
https://drawgpt.ai
Created: 2026-01-26T14:25:23+00:00
-->
<svg viewBox="0 0 512 512" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
<title>GPU Air Duct Design</title>
<desc>A fun CAD-style drawing of a GPU air duct! Who knew cooling could be so artsy?</desc>
<metadata type="keywords">GPU, air duct, cooling, CAD, PVC</metadata>
<!-- Background (stationary) -->
<rect id="background" class="background" x="0" y="0" width="512" height="512" fill="#EEEEEE"/>
<!-- PVC Duct -->
<path id="duct-wall-1" class="duct" d="M50 100 L50 400 L250 400 L250 100 Z" fill="#D3D3D3" stroke="black" stroke-width="2"/>
<path id="duct-wall-2" class="duct" d="M250 100 L250 400 L450 400 L450 100 Z" fill="#D3D3D3" stroke="black" stroke-width="2"/>
<path id="duct-wall-3" class="duct" d="M50 100 L450 100 L450 80 L50 80 Z" fill="#D3D3D3" stroke="black" stroke-width="2"/>
<!-- GPU Backplate (Inside Duct) -->
<rect id="gpu-backplate" class="gpu" x="52" y="102" width="396" height="296" fill="#444444" stroke="black" stroke-width="2"/>
<!-- ATX Slot Opening -->
<rect id="atx-slot" class="atx" x="50" y="250" width="111" height="20" fill="#888888" stroke="black" stroke-width="1"/>
<!-- Axagon Fan -->
<circle id="fan-housing" class="fan" cx="400" cy="250" r="30" fill="#CCCCCC" stroke="black" stroke-width="2"/>
<circle id="fan-center" class="fan" cx="400" cy="250" r="5" fill="#333333"/>
<!-- Fan Blades (Animated) -->
<g id="fan-blades" class="fan">
<path d="M400 220 L410 240 L430 250 L410 260 L400 280 L390 260 L370 250 L390 240 Z" fill="#555555" stroke="black" stroke-width="1">
<animateTransform attributeName="transform" type="rotate" from="0 400 250" to="360 400 250" dur="2s" repeatCount="indefinite"/>
</path>
<path d="M400 220 L410 240 L430 250 L410 260 L400 280 L390 260 L370 250 L390 240 Z" fill="#555555" stroke="black" stroke-width="1" transform="rotate(45 400 250)">
<animateTransform attributeName="transform" type="rotate" from="45 400 250" to="405 400 250" dur="2s" repeatCount="indefinite"/>
</path>
</g>
<!-- Air Flow Arrows (Animated) -->
<path id="airflow-arrow-1" class="airflow" d="M161 260 L201 260 L191 250 L201 240 L161 240 Z" fill="lightblue">
<animate attributeName="x" values="161; 171; 181; 191; 201; 161" dur="5s" repeatCount="indefinite"/>
</path>
<path id="airflow-arrow-2" class="airflow" d="M211 260 L251 260 L241 250 L251 240 L211 240 Z" fill="lightblue">
<animate attributeName="x" values="211; 221; 231; 241; 251; 211" dur="5s" repeatCount="indefinite"/>
</path>
<path id="airflow-arrow-3" class="airflow" d="M261 260 L301 260 L291 250 L301 240 L261 240 Z" fill="lightblue">
<animate attributeName="x" values="261; 271; 281; 291; 301; 261" dur="5s" repeatCount="indefinite"/>
</path>
<path id="airflow-arrow-4" class="airflow" d="M311 260 L351 260 L341 250 L351 240 L311 240 Z" fill="lightblue">
<animate attributeName="x" values="311; 321; 331; 341; 351; 311" dur="5s" repeatCount="indefinite"/>
</path>
<path id="airflow-arrow-5" class="airflow" d="M361 260 L401 260 L391 250 L401 240 L361 240 Z" fill="lightblue">
<animate attributeName="x" values="361; 371; 381; 391; 401; 361" dur="5s" repeatCount="indefinite"/>
</path>
<!-- Dimensions -->
<line id="dimension-x" class="dimension" x1="50" y1="60" x2="450" y2="60" stroke="black" stroke-width="1"/>
<line id="dimension-x-tick-1" class="dimension" x1="50" y1="55" x2="50" y2="65" stroke="black" stroke-width="1"/>
<line id="dimension-x-tick-2" class="dimension" x1="450" y1="55" x2="450" y2="65" stroke="black" stroke-width="1"/>
<text id="dimension-x-text" class="dimension" x="250" y="50" text-anchor="middle" font-size="12">X</text>
<line id="dimension-y" class="dimension" x1="20" y1="100" x2="20" y2="400" stroke="black" stroke-width="1"/>
<line id="dimension-y-tick-1" class="dimension" x1="15" y1="100" x2="25" y2="100" stroke="black" stroke-width="1"/>
<line id="dimension-y-tick-2" class="dimension" x1="15" y1="400" x2="25" y2="400" stroke="black" stroke-width="1"/>
<text id="dimension-y-text" class="dimension" x="30" y="250" text-anchor="middle" transform="rotate(-90 30 250)" font-size="12">Y</text>
<line id="dimension-z" class="dimension" x1="460" y1="102" x2="460" y2="102" stroke="black" stroke-width="1">
<animate attributeName="y2" values="102; 104; 102" dur="2s" repeatCount="indefinite"/>
</line>
<line id="dimension-z-tick-1" class="dimension" x1="455" y1="102" x2="465" y2="102" stroke="black" stroke-width="1"/>
<line id="dimension-z-tick-2" class="dimension" x1="455" y1="102" x2="465" y2="102" stroke="black" stroke-width="1">
<animate attributeName="y2" values="102; 104; 102" dur="2s" repeatCount="indefinite"/>
</line>
<text id="dimension-z-text" class="dimension" x="470" y="106" text-anchor="middle" font-size="12">Z</text>
<line id="dimension-gap-1" class="dimension" x1="52" y1="90" x2="52" y2="102" stroke="black" stroke-width="1"/>
<line id="dimension-gap-1-tick-1" class="dimension" x1="47" y1="90" x2="57" y2="90" stroke="black" stroke-width="1"/>
<line id="dimension-gap-1-tick-2" class="dimension" x1="47" y1="102" x2="57" y2="102" stroke="black" stroke-width="1"/>
<text id="dimension-gap-1-text" class="dimension" x="40" y="96" text-anchor="middle" font-size="12">1-2mm</text>
<line id="dimension-gap-2" class="dimension" x1="430" y1="90" x2="430" y2="102" stroke="black" stroke-width="1"/>
<line id="dimension-gap-2-tick-1" class="dimension" x1="425" y1="90" x2="435" y2="90" stroke="black" stroke-width="1"/>
<line id="dimension-gap-2-tick-2" class="dimension" x1="425" y1="102" x2="435" y2="102" stroke="black" stroke-width="1"/>
<text id="dimension-gap-2-text" class="dimension" x="440" y="96" text-anchor="middle" font-size="12">5-10mm</text>
</svg>
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.
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.
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!
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 & 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.