pro
Taïel — a client Reel built with prompts only
One rule: prompts only. This is the full walkthrough of a real client Reel for Taïel, a natural skincare brand whose name means "inner song" in Mapuche tradition — built end-to-end inside Envato.
Every asset came from one toolkit: ImageEdit stripped the logo to its butterfly and cleared the label. ImageGen made her real. VideoGen landed the shot where she descends and folds back into the logo she was born from. The worlds came from Envato Stock, the track from MusicGen — approved by the client on the first take — the typeface from Envato Fonts, and the air from Envato SFX.
The machine generated. The human decided. Three calls shaped this film: the idea (bring the logo to life and let it sing), a mother's photo — I chose the children's line from her product shots, she answered with a photo of her own son, and that photo became the film's ending. That's my Human by Design moment. And the founder's own voice: I had AI voices generated and ready — I rejected them, and she recorded it herself, in her words.
Ten minutes of machine work. Eight seconds for you — and a Reel the client actually published.
Watch the walkthrough above.
On X: https://x.com/astroph0s/status/2078655194137575931
2
3
235
🦋 Back'Fly — a butterfly's life told backwards, where what looks like a fragile creature fighting a storm is revealed at the chrysalis to be a beginning, not an end, and a caterpillar's final wink lands the twist.
Built entirely in Renoise using Seedance 2.0 multi-reference for every shot — the butterfly's identity paired with environment plates driving each scene — with GPT Image 2 and Nano Banana Pro for the keyframes.
Native audio per clip, assembled on a single continuous score.
#RenoiseChallenge @Renoise
1
1
158
Pulse — Real-Time Global Seismic Activity Category: Dashboard
Pulse is a live monitor of earthquake activity worldwide. Open it and the planet is already breathing — every recent quake rendered as an incandescent heatmap, streamed live from USGS. Drag the timeline scrubber to replay the last 30 days and watch seismic activity unfold as a film. Pulse auto-focuses on the most active zone, then opens a full analytical panel: how active the region is versus its baseline, cumulative energy released measured against Hiroshima, and a depth cross-section that reveals the tectonic plate diving beneath the surface — the dimension a flat map can't show, and the one that determines whether a quake is deadly or harmless.
An educational slider reframes each zone's geology from plain language for anyone to technical depth for an expert — the same phenomenon, two audiences, no jargon left behind. Logged-in users save regions to track.
Built on Bubble AI. A single prompt to Bubble's AI builder generated the foundation — data structure, page layout, navigation, and auth. On top of that base I built the live WebGL map (MapLibre + deck.gl (http://deck.gl)), real-time USGS integration, the client-side analytics engine (energy, anomaly, depth distribution), and the bespoke 2D depth cross-section that detects subduction directly from the data.
Pulse is informational, not an official emergency source. Data: USGS.
Live app: https://pulse-20833.bubbleapps.io/version-test/
1
4
522
OmniLearn — be the hero of your own story, literally
OmniLearn is a body-controlled learning game for kids aged 4–7. A child stands in
front of any webcam, gets scanned, and becomes a soft-voxel 3D avatar of themselves
that they control with their body — no controller, no keyboard. They solve
educational challenges by MOVING: catching falling leaves to count (the golden ones
worth three), and crossing "Vowel River" by grabbing the animals whose names say the
long-A sound.
THE PROBLEM
Kids this age learn by moving, not by reading — but most educational software sits
them down to tap a screen. OmniLearn flips that, and it speaks to the child so they
can play before they can read. It runs on what's already at home: a laptop webcam, no
special hardware.
BUILT ENTIRELY IN FIGMA
The app lives inside Figma Make — screens, flow, and game logic.
Every soft-voxel creature, world, and the avatar were designed in Figma Weave as a reusable asset workflow.
The engine — MediaPipe pose tracking (33 body landmarks, in a web worker) and a three.js avatar that mirrors the child in real time — I wrote and wired into the Make project's code by hand. Soft-voxel was a deliberate choice: rigid rounded chunks make the rig trivial and never deform.
Voice lines are pre-generated TTS; everything else is synthesized SFX.
THE VISION
This demo is one polished journey — but OmniLearn is built to teach ANY subject. The
same body-as-controller engine works for math, language, history, science, logic. In
the full product, worlds and challenges are generated ON DEMAND and adapted to the
exact age and level requested — today's worlds are hand-built, tomorrow's are
infinite. Every child gets a curriculum that meets them where they are.
PRIVACY
100% on-device. The child's camera feed never leaves the browser — nothing uploaded,
nothing stored.
LINKS
Live demo: https://meta-rover-70928932.figma.site/
(https://meta-rover-70928932.figma.site/)Community file: https://www.figma.com/community/file/1649688792758544694/omnilearn-body-controlled-learning-game
(https://www.figma.com/community/file/1649688792758544694/omnilearn-body-controlled-learning-game)Social post: https://x.com/astroph0s/status/2067859955781128419
#ConfigMakeathon
3
242