I'm hosting a workshop with tiat.place in SF on tuesday!
we'll experiment with otherworldly visuals to create dynamic interfaces with generative art together 🖥️
interested in vibecoding, creative coding, or making things playfully?
come join our vibecode creative code jam today in SF! using @MakeGizmos or whatever tools you like 🌀🤩
last night, we hosted a demo night @southpkcommons on all things "fun."
stoked to share what @zan2434, @faionur, @elizalian, and many more are exploring on the frontier of joy:
This is an awesome fork of Gemini Co-Drawing by @trudypainter by our friend @whichlight. It's so cool to have Gemini 2.5 not only output the next predicted drawing state, but actually co-think with you about what it might draw next. ✏️🧠
What it would be like to co-think creatively with AI?
After you draw, Gemini gives suggestions on what it can add to the drawing, picks one, and automatically adds it.
Built on Gemini Co-Drawing by @trudypainter and @alexanderchen!
What it would be like to co-think creatively with AI?
After you draw, Gemini gives suggestions on what it can add to the drawing, picks one, and automatically adds it.
Built on Gemini Co-Drawing by @trudypainter and @alexanderchen!
Co-draw with Gemini 2.0 native image generation… from @alexanderchen and me
Doodling AI is a magical → it really starts to feel like Gemini is *with you in the canvas
Link: huggingface.co/spaces/Trudy/…
You can also see the list of suggestions and pick one for Gemini to draw.
After there are enough lines on the canvas, a few style features pop up too to transform the drawing as a whole. Things like color, texture, and surreal mode which is wild. Note: both these videos are 3x
I've been interested in co-creative tools with AI for a while, esp doodling with AI. It's amazing to see what we can do as the tools improve, and lots more to explore!
here's a project from a couple years ago using stable diffusion img2img and p5js x.com/whichlight/status/1633…
doodle & diffuse: collaborative drawing with AI✨
@p5xjs@StableDiffusion img2img
generate an image, doodle on it, and then generate an image from that, and then doodle on it, etc
Co-draw with Gemini 2.0 native image generation… from @alexanderchen and me
Doodling AI is a magical → it really starts to feel like Gemini is *with you in the canvas
Link: huggingface.co/spaces/Trudy/…
🧵 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 simulation
love playing with this — a canvas for prompting with text and images and easily chaining together flows. the creative fuzziness an LLM allows for makes it a delight to explore. from @tldraw :
x.com/tldraw/status/18694011…
I want to share a news storytelling provocation for 2025, coming from a toolmaker who’s been building media prototypes with LLMs over the past year.
The @NiemanLab at Harvard invited me to share a prediction for 2025, and here's what I wrote: 🧵
We’re caught in this tension. Social media pushes us toward simpler messages — bolder headlines, punchier takes, everything feels flattened. Yet at the same time, the world grows more complex, and stories must have more nuance, more context, and more perspectives.
We can move from flat to dimensional stories with the new interfaces powered by LLMs. I’ve been prototyping what this might look like:
niemanlab.org/2024/12/new-di…