🧵 Photos → Creative Code using Gemini I built... an experiment that turns photos into interactive p5xjs sketches using Gemini 2.0 Flash. Unlike UI generators, this creates code that mimics the *behavior* of what's in the image - like smoke swirling or ripples spreading. Check out this sunset + smoke simulationshow more

gemini 3 is unbelievable it can create an app... that turns image into 3D interactive The Matrix scene, adjust particle amount, color, density interact with particles using mouse or hands created with text prompts, no code neededshow more

🧵 Go from nature to code with Gemini 2.5... Pro 🍃 Each of these were created with the same prompt: Transform this image into a code-based representation of its natural behavior. Original input image on the left. Gemini output on the right.show more

I built a multimodal AI medical image diagnosis agent... using Gemini 2.0 This AI Agent can: • Analyze medical scans • Detect abnormalities • Search the web • Generate patient-friendly reports 100% Opensource Code with step-by-step tutorial.show more

Built a cool 3D physics receipt using Gemini. Grab... the code below ⤵️show more

Go from design to Compose UI code with Gemini!... ⬆️ Upload image of app UI screen ↪️ Use the prompt in the blog ↪️ Copy output into Android Studioshow more

With the launch of Nano Banana Pro, we're also... rolling out the ability for Gemini users to check whether an image was generated with or edited by Google AI using SynthID, our digital watermarking technology. Now you can upload any image into the Gemini app and ask "Is this AI-generated?" Gemini then scans the image for the imperceptible SynthID watermarks that are embedded into all Google AI-generated images - including those by Nano Banana Pro! Learn more about Google’s efforts to increase AI transparency:show more

We built the Wild Week Athens site in 1.5... weeks using mainly AI and no-code tools. AI doesn’t make designers obsolete. It shifts the weight to taste, creative instinct and understanding craft. Here's how this experiment came together 🧵show more

Create a short film like this in just 1... minute with GPT Image 2.0 + Seedance 2.0. GPT Image 2.0 can naturally combine multiple photos into one single image, while Seedance 2.0 can use that image as a reference to automatically separate the scenes, generate a coherent video sequence, and add suitable background music. This workflow greatly improves the overall creative efficiency. When using this method, simply provide the merged image as a reference for Seedance 2.0 and briefly describe each scene with a simple prompt. This can significantly increase the success rate of the final video. All of the above was created on GPT Image Prompt: Seedance Prompt:show more

See Gemini 2.0's creative coding abilities! Watch how it... can mimic an object's behavior in this demo by Trudy Painter ↓show more

This is the progression of a "3D Flappy Bird"... game I made using Gemini 2.5 Pro and Sonnet 3.7. Wrote 0 lines of code and have 0 experience with games or graphics. Vibe-coded over 1 hour with a tool that integrates with vanilla VS Code (no special editor or proprietary fork).show more

bye bye UI designers... I made this design in... 2 days, 12 hours a day without drawing a single thing in figma or writing any code vibing Gemini Flash 3, all in 2 days.show more

I built this mobile app with ONE PROMPT using... Gemini 3.0 💀show more

Gemini 2.0 Flash Experimental is accessible in Google AI... Studio ✅Change your Model to Gemini 2.0 Flash Experimental under Preview ✅Upload/generate an image ✅And just prompt to change your image I used Pikaframes for transition between keyframesshow more

🎨 Rapidly prototype interactive 3D concepts with Gemini. Learn... how to use Gemini in the Canvas web app to build 3D environments and interactive models using WebXR APIs. Start building → Explore more examples below 🧵show more

I noticed that in Runway’s Seedance 2.0 model, we... can actually reference photos that include human faces. I have no idea how they managed to overcome this. By the way, there’s no information here about whether they’re using the fast version of Seedance 2.0 or the higher/pro model. I wish they had specified that too.show more

✍️tldraw is using Gemini 3 Flash to power its... natural language computer, tldraw computer. Networks of components on an infinite canvas each use Gemini to process data and generate content that flows into other components. These flows are faster, smarter, and more reliable with Gemini 3 Flash.show more

Google is silently rolling out an updated Gemini experience... for its mobile apps ahead of Google I/O. Its updated UI for Gemini Live features an interactive "bar" or a dynamic island that reacts to your taps and can wave back. It should get loads of superpowers soon 👀show more

Ah yeah, just me trying to vibe code something... new every day :D That 3D Rubik’s Cube you see there is built from scratch (custom math-based physics engine) using Three.js with GSAP animations and totally vibe coded in Google AI Studio using Gemini 3 Pro AI. Live: Code:show more

Gemini 3 can do 3D interactive website in a... few mins it detects hand gestures using your camera and interact.. this is crazy no need to know code, just simple texts tutorial and prompts belowshow more

I built an o1 alternative, that is: 1) Fully... transparent, visually trackable 2) Infinitely recursive 3) Self-healing, with tests at every step 4) Capable of using a Python interpreter It performs shockingly well, check it out! 🧵Code + performance on popular reasoning problemsshow more