Ever saved a bookmark thinking "I'll definitely come back to this"... and then never found it again?
Same. That's exactly why I built WeBook.
WeBook is a free Chrome extension that organizes your bookmarks FOR you:
AI automatically sorts every bookmark into the right folder
Adds 3 smart tags so you can actually find things later
Saves your open tabs as groups you can restore anytime
Finds duplicate bookmarks and dead links
One-click backup and restore
No more messy bookmark bars. No more "247 unsorted bookmarks." Just save a page and WeBook handles the rest.
It's completely FREE on the Chrome Web Store
https://www.webook.website/
I built this as a student project and I'd love your feedback - try it and tell me what you think!
1
7
AA Ferro Lanka — Precision Stirrup Fabrication
🔗 Live app: https://aaferrolanka.base44.app/
The business
A family CNC steel workshop in Piliyandala, Sri Lanka. They bend custom reinforcement stirrups — the steel rings inside every concrete column and beam. A WG-12 CNC bender, accurate to ±1mm, capable of 1,200 stirrups an hour.
Real business. Real machine. Real customers. Zero digital presence.
Proof - Google Map (https://www.google.com/maps/place/AA+Ferro+Lanka/@6.7963424,79.9076194,18z/data=!4m6!3m5!1s0x3ae2450a97c35061:0x36e19b48819ddc44!8m2!3d6.7961547!4d79.9089943!16s%2Fg%2F11nr2jh0n8?authuser=0&entry=tts&g_ep=EgoyMDI2MDcwOC4wIPu8ASoASAFQAw%3D%3D&skid=4354c7ed-4209-4b9a-8333-d492beda682c)
BEFORE
Orders taken by phone. Dimensions written on scrap paper.
Every quote calculated by hand, on every call — steel weight, cutting length, price per kg.
No record of who paid a deposit and who didn't.
Customers ringing all day to ask "is it ready?"
Steel running out mid-job, discovered at the machine.
Offcut waste on every single bar — never once measured.
AFTER
A live, mobile-responsive platform that runs the entire business — quoting, ordering, payments, production, delivery, and the owner's daily operations — with WhatsApp as the interface, because that's where he actually is.
THE PRODUCT
Public site Home · Products · Our Story & Team · Workshop Gallery · Track Order · Support · Get Quote · Customer testimonials from real partner stores
The configurator — quote in one second, not one phone call
Shape: rectangular, square, round, custom
Rebar size: 6mm / 8mm / 10mm / 12mm — each showing live stock in kg
Dimensions + quantity
Returns exact cutting length, weight per stirrup, total material weight, price per kg, total price and 50% deposit — calculated from today's live steel rate, read from the database, never hardcoded
Stock is checked before the price is quoted. An out-of-stock size is hard-blocked. The workshop cannot sell steel it doesn't have.
No account required to get a price.
The collection network 21 real hardware stores pulled from Google Places across the delivery corridor, sorted by distance from the customer's site — plus collection at the workshop. Any hardware store can self-register as a partner and become a collection point.
Owner Control Room (secret route — not /admin, linked from nowhere)
KPI cards: total orders, awaiting deposit, in production, deposits collected, avg rating
Order pipeline: Pending → Confirmed → In Production → Ready → Delivered, advanced with one tap — and every tap messages the customer automatically
Live steel price + stock editing with visual stock bars — change the rate, and every quote on the public site is new one second later
Full WhatsApp activity log — every message the system ever sent
Lead pipeline: New → Contacted → Quoted → Won → Lost
Hardware business verification (Verify / Unverify)
Hardware store dashboard Its own incoming orders, its own stock, its own price, its own margin, its own QR scanner. 21 drop-off points become 21 sales channels.
Steel supplier dashboard Restocks and re-prices the workshop directly — and cannot see one customer, one phone number, one message. That's row-level security, not a hidden button.
Customer portal My Orders + Track Order. Order ID, items, total, deposit status, live production status. Nobody has to phone and ask.
QR delivery verification Every bundle carries a QR tag. The store scans it. Delivery confirmed.
THE AUTOMATIONS — 17 live
On order creation
Owner alert — WhatsApp + email in seconds, with full spec, deposit and bank slip
Customer confirmation — order number + exact deposit due
Stock deduction — steel deducted from inventory automatically
Low-stock alert — the owner is warned before the machine stops
Order sanity check — catches a typo before steel is cut. 2500 instead of 250 is 500 stirrups of scrap. It freezes the order. Nobody starts the machine until a human approves.
Steel Waste Optimizer — see below. This is the one.
Scheduled
7. Deposit chaser — 09:30 daily. Chases three times, then escalates to the owner to call. Recovers revenue that used to just vanish.
8. Morning briefing — 08:00 daily: new orders, money owed, what's on the machine, what steel to buy
9. Production batching — groups the day's jobs by rebar size, so the machine is threaded once, not ten times
10. Steel purchase plan — tells the owner exactly what to buy, before he runs short
11. Weekly summary — Monday: orders, revenue, steel used
12. Post-delivery follow-up — 3 days after delivery. 5 stars route to Google. 1 star routes privately to the owner — before it becomes a public review.
On status change
13. Status updates — Confirmed / In Production / Ready. Kills every "is it ready?" phone call.
14. Ready-for-collection — store name, address, Google Maps pin, balance due
15. Honest ready dates — a real date from the real production queue, with an automatic warning the moment it slips
Inbound
16. Instant lead capture — every enquiry auto-replied before it goes cold
17. QR delivery confirmation — bundle scanned at the store, order closed
Reliability: nothing ever fires twice. Every automation is locked behind an idempotency flag on the order itself. A retry cannot spam a customer. A re-run cannot deduct the same steel twice. And with zero API keys configured, nothing breaks — every message queues as a one-tap wa.me (http://wa.me) link. Value on day one, with no setup.
THREE AI AGENTS ON WHATSAPP
Customer Assistant — quotes today's real price from live stock, at midnight on a Sunday. Photograph an engineer's drawing and it reads the stirrup off the page. It can take an order. It can never mark one paid.
Manager Agent — the owner's control room, in a chat window. "How much am I owed?" "What's on the machine?" "Make 8mm 290." He speaks; the website changes. It can move a price. It cannot move an order — that permission does not exist.
Production Planner — the CNC cut-list optimizer. Groups jobs by diameter, calculates bars to load, stirrups per bar, offcut per bar, and warns when the steel runs short before the machine starts
BONUS CRITERIA
✅ Live and published · ✅ Mobile-responsive · ✅ Real business, actively using it · ✅ Before/after documented · ✅ AI Superagent implemented (×3) · ✅ Automation demonstrably drives business outcomes (deposit recovery + LKR 8,144 material saving) · ✅ Real Google Places data, real partner store network
Built entirely on Base44.
2
8
217
✨ Aftercare
The hospital discharge summary, redesigned into a calm, patient-first recovery companion.
Good healthcare information can save lives. Good information design helps people understand it.
🔗 Project Links
🎨 Wonder Design File: https://app.wonder.so/isumenuka/files/019f31a3-8c46-7707-b8d1-9bb74298da0b
💻 React Export / GitHub: https://github.com/isumenuka/Aftercare
🩺 The Challenge
Every day, millions of patients leave hospitals with discharge instructions that are difficult to read, filled with medical jargon, and presented in dense blocks of text.
Patients are often tired, anxious, in pain, or under medication when they receive this information. Unfortunately, this is exactly when understanding it matters most.
This isn't simply a healthcare problem.
It's an information design problem.
📚 Research Validation
📄 Engel et al. (2009)
Annals of Emergency Medicine
Key Finding
78% of emergency department patients demonstrated deficient comprehension in at least one aspect of their care or discharge instructions, and most believed they understood everything correctly.
This reveals a dangerous gap between what patients think they understand and what they actually understand.
Research Paper
https://consensus.app/papers/details/78ce400adebd51cfa38953d47bbc82f7/
📄 Sahhar et al. (2025)
The American Journal of Medicine
Researchers found that:
• 81% of standard English discharge instructions exceed the recommended sixth-grade reading level.
• Multilingual discharge instructions remain limited, reducing accessibility for many patients.
Together, these studies demonstrate that improving information design can directly improve patient safety.
💡 The Solution
Aftercare
A mobile experience that transforms a hospital discharge summary into a clear, personalized recovery companion.
Simply scan the discharge document and receive an interface designed around what patients actually need.
Instead of pages filled with confusing medical language, patients receive simple guidance that answers:
✅ What happened?
✅ What should I do today?
✅ Which medications should I take?
✅ What symptoms should I watch for?
✅ When should I contact my doctor?
✅ When should I visit the emergency room?
📱 Core Screens
📄 Scan Discharge Summary
Capture the printed discharge document and instantly convert it into structured, readable information.
❤️ Recovery Today
A simple daily dashboard showing recovery progress, today's tasks, hydration, activity, appointments, and care reminders.
💊 Medication Reminder
An interactive medication timeline explaining:
• What to take
• When to take it
• Why you're taking it
• Missed dose reminders
🚨 Warning Signs
Important symptoms are grouped into clear actions.
🟢 Continue recovery
🟡 Contact your healthcare provider
🔴 Visit the emergency room immediately
No medical jargon.
Just clear actions.
🎨 Design Language
The interface was designed to feel calm, reassuring, and easy to read.
• Deep near-black background
• Soft ambient magenta, pink, and blue shader lighting
• Bento-style information cards
• Large accessible typography
• Ghost-style LCD numerals
• High-contrast layout
• Warm pastel recovery cards
• Yellow highlights for urgent information
Every visual decision helps reduce stress instead of creating it.
⚙️ Built Entirely in Wonder
The entire experience was designed inside Wonder.
Workflow
✨ Wonder Chat generated the initial component system.
✨ Wonder Shader tools created the ambient backgrounds.
✨ Wonder components built the reusable interface.
✨ Wonder MCP connected Claude to structure the discharge data.
✨ The finished design was exported directly to React and Tailwind CSS.
This demonstrates a complete Design → AI → Code workflow.
🛠 Technology Stack
• Wonder
• Wonder Chat
• Wonder Shader Generation
• Wonder MCP
• Claude
• React
• Tailwind CSS
🔌 API Stack
Free APIs
• HL7 SMART on FHIR Sandbox
• NIH RxNorm / RxNav
• MedlinePlus Connect
❤️ Why It Matters
Healthcare already has the right information.
Patients simply receive it in the wrong format.
Aftercare demonstrates how thoughtful interface design, accessibility, and AI-powered workflows can make recovery instructions understandable, actionable, and reassuring.
Better information design is patient safety.
✨ Designed in Wonder.
🏥 Built for the day patients go home.
1
102
Meet BLOOP. 🐟
One little maintenance robot. A sealed glass fishbowl where its head should be. And one real fish inside: its face, its heart, the whole reason it exists.
The idea: the robot never changes. Not a single bolt. The only thing that ever changes is the fish in the dome. Swap the resident and you get a whole new member of the same family, an infinite, instantly-recognizable cast from one design.
One robot. Infinite residents. Zero identity crises.
BLOOP is the mascot of a fictional ocean-guardian fleet, keeping reefs and trenches clean so every little resident can thrive. It's named after the real, unexplained deep-sea sound the ocean once made.
I didn't just draw a mascot. I built its whole world. Walk through it here:
🔗 https://bloop.isumenuka.me/
Recraft project link - https://www.recraft.ai/project/3d8401f5-0828-4248-9bc2-dece4fb7e130
The site holds every application, each one proof that BLOOP stays unmistakably itself across formats:
🎣 Sticker Pack · 🖼️ Poster · 🧢 Merch · 📱 Social Posts
All made in Recraft Studio. Full images in the comments 👇
Built for the Mascot Challenge with @recraftai
2
3
212
Ladle
Rescue your neighborhood's surplus food and pay a meal forward - a hyperlocal map where leftovers find a hungry neighbor in minutes, not a landfill.
Ladle is a hyperlocal food-rescue marketplace that turns the surplus food sitting in your kitchen - the half-tray of lasagna, the bagels you over-bought, the garden tomatoes you'll never finish - into a meal for a neighbor, before it spoils.
Instead of scrolling endless listings, you point your phone at the food and Ladle's on-device camera recognizes what it is and drafts the listing for you. It drops onto a live neighborhood map with a freshness countdown, and anyone nearby can claim it for free or for a few dollars. With one tap you can also "pay it forward" - funding a suspended plate that someone facing food insecurity can claim anonymously, with dignity.
The result is a faster, warmer way to move food from people who have too much to people who have too little - block by block, in real time.
The Problem
The United States throws away 30–40% of its food while tens of millions of people go hungry. The two problems sit side by side, unconnected.
Existing apps mostly rescue business surplus (cafés, bakeries, grocers). The everyday surplus in millions of home kitchens - and the neighbor two doors down who could use a meal - is almost entirely unserved, because listing food is tedious and there's no dignified way to give directly to a person in need.
Ladle explores a different question:
What if surplus food could move peer-to-peer, in real time, as easily as taking a photo - and what if giving a meal felt as good as getting one?
By combining on-device food recognition, a live hyperlocal map, and a pay-it-forward "suspended plate" mechanic, Ladle removes the friction that kills food-sharing and channels the urgency of "use it before it spoils" into a pro-social act.
Links
Live Project: https://ladle-84447.bubbleapps.io (https://ladle-84447.bubbleapps.io/version-test/)
Category
Marketplace - a peer-to-peer platform for giving, claiming, and paying forward surplus food.
Process
Ladle combines AI-assisted no-code development, on-device computer vision, and real-time geolocation, built on Bubble.io (http://Bubble.io) and Claude.
Development Workflow
The entire foundation was generated from a single Bubble AI prompt - pages, database schema, workflows, authentication, and seed data - then refined by hand. I used Bubble AI to scaffold the marketplace, then took the wheel: embedding the camera food-detection model, and designing the suspended-plate flow and the community impact dashboard.
Food Detection (on-device camera)
When a giver adds a photo of their surplus food, Ladle runs an image classifier entirely in the browser — no server, no API key, no quota — and auto-fills the listing with the detected food.
It uses TensorFlow.js with the MobileNet model (1,000 ImageNet classes, many of them foods — bagel, French loaf, pretzel, pizza, banana, lemon, and more), loaded in Bubble's native HTML element and bridged back into the app with the Toolbox plugin (Run JavaScript + JavaScript-to-Bubble). The detected label pre-fills the food name, and the giver can edit it before posting — turning a tedious listing into a single tap. (COCO-SSD is also supported for object-style detection of common foods like pizza, banana, and donut.)
APIs & Integrations
TensorFlow.js — MobileNet / COCO-SSD — on-device food image recognition, no API key — github.com/tensorflow/tfjs-models
Plugin — Toolbox (Mishav) bridges the in-browser CV model to Bubble.
Research & Problem Validation
Ladle's problem is real, measured, and unsolved in the peer-reviewed literature:
Conrad, Z. (2020). Daily cost of consumer food wasted, inedible, and consumed in the United States, 2001–2016. Nutrition Journal, 19(1):35. — Across 39,758 adults (NHANES), about 27% of daily per-capita food spending goes to food that is ultimately wasted (~$1,300/year per household), pointing to the consumer level as the highest-leverage place to intervene. https://doi.org/10.1186/s12937-020-00552-w (https://doi.org/10.1186/s12937-020-00552-w) nih (https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7168972/)
von Massow, M., et al. (2019). Valuing the Multiple Impacts of Household Food Waste. Frontiers in Nutrition, 6:143. — A detailed household audit quantifying the economic, nutritional, and environmental cost of avoidable household food waste. https://doi.org/10.3389/fnut.2019.00143 (https://doi.org/10.3389/fnut.2019.00143)
Principato, L., Mattia, G., Di Leo, A., & Pratesi, C. A. (2021). The household wasteful behaviour framework: A systematic review of consumer food waste. Industrial Marketing Management, 93, 641–649. — A systematic review confirming that roughly one-third of the food produced globally is lost or wasted along the supply chain, with household waste driven mainly by everyday food-related behavior. https://www.sciencedirect.com/science/article/abs/pii/S0019850119308600 ScienceDirect (https://www.sciencedirect.com/science/article/abs/pii/S0019850119308600)
Dunn, E. W., Aknin, L. B., & Norton, M. I. (2008). Spending Money on Others Promotes Happiness. Science, 319(5870), 1687–1688. — The behavioral engine behind the suspended-plate feature: spending money on others promotes greater happiness than spending it on oneself. https://doi.org/10.1126/science.1150952 (https://doi.org/10.1126/science.1150952) Science (https://www.science.org/doi/10.1126/science.1150952)
Context: USDA estimates U.S. food loss and waste in the hundreds of billions of dollars annually, while ~47 million people lived in food-insecure households in 2023 (USDA ERS) — the exact gap Ladle is built to close.
Sources & Imagery
Demo food photography is sourced from Unsplash (a unique image per listing). Nutrition data is provided by Open Food Facts.
Tech Stack
Bubble.io (http://Bubble.io) · Bubble AI · Claude · TensorFlow.js · MobileNet / COCO-SSD · Toolbox plugin · Mapbox · OpenStreetMap Nominatim · Open Food Facts · Unsplash
2
118
Did you know a tornado formed the year you were born?
Not a real one. A data one.
Type your birth year. Watch the storm react - the speed, the color, the rage of it - all driven by the exact CO₂ levels recorded that year.
🌪️Live Site - https://thedatatornado.figma.site
🎨Figma Make - https://www.figma.com/make/onDJsdMQ3PQV2B8xkSzHKn/TheDataTornado (https://www.figma.com/make/onDJsdMQ3PQV2B8xkSzHKn/TheDataTornado?t=AdZGoKLchp7v8avG-1)
📋FigJam Board - https://www.figma.com/board/2P5FGzsc6faOl2a2JK2GDo/TheDataTornado (https://www.figma.com/board/2P5FGzsc6faOl2a2JK2GDo/TheDataTornado?node-id=0-1&t=fECFM44dgxDR2x3C-1)
💻GitHub Repo - https://github.com/isumenuka/Thedatatornado
🔬 The Problem
Climate change is the most documented crisis in human history. Scientists have been collecting data for over 65 years. But most people feel nothing when they see the numbers - because a wall of data doesn't make you care. That is a design problem. The Data Tornado is my answer.
⚙️ How It Was Built
I started in FigJam - mapping the full app structure, severity color system (Stable → Elevated → Critical → Extreme), and the 65-year climate timeline before touching any build tool.
In Figma Make, I loaded my complete design guidelines first - colors, fonts, spacing rules - so every generated output matched my vision from the first prompt. That one step eliminated hours of corrections.
The MCP connector was the most critical technical piece: a custom live pipeline to NOAA's servers, pulling real CO₂ and temperature readings automatically every time someone opens the app. No downloading. No pasting. Always live.
The hero background video was generated entirely in Figma Weave - I set a start frame and end frame, and Weave generated the full atmospheric storm footage between them. The Figma Agent handled precision edits throughout -clicking directly on individual elements, repositioning buttons, aligning sections, without touching anything else.
Supabase powers the share cards, news gallery, and live data caching. GitHub handles deployment.
🛠️ Tools Used
→ FigJam: full app structure, severity system & data flow diagrams
→ Figma Make: prompt-to-code app with custom NOAA MCP connector
→ Figma MCP: live pipeline direct to NOAA's climate API
→ Figma Weave: AI video generation for the hero storm background
→ Figma Agent: precision element-level UI edits throughout the build
→ Supabase: backend for share cards, news & data caching
→ GitHub: deployment and version control
✨ Key Feature - Birth Year Telemetry
Enter your birth year. The app instantly generates your personal climate log -the exact CO₂ concentration the year you arrived in the world, your temperature anomaly then vs. now, your severity level at birth vs. today. It stops being a global statistic. It becomes yours.
Most people go quiet when they see their own number.
78
126
6.5K
SimpleRent - Contra Submission Post
Google Stitch Challenge Entry
PROJECT LINK
https://stitch.withgoogle.com/projects/14459373944360524996
(https://stitch.withgoogle.com/projects/14459373944360524996)WEBAPP LINK
https://simple-rent-contra.vercel.app (https://simple-rent-contra.vercel.app/)
PROJECT TITLE
SimpleRent - Student Rental Platform for Sri Lanka
Every year, university students in Sri Lanka leave their hometowns to study in Colombo. They arrive with no local knowledge and no housing plan. No platform was built specifically for them.
SimpleRent is a student-first rental interface that solves two linked problems in one product: find a safe rental near your campus or find a compatible roommate to share the cost.
Google Maps-centered property search, NIC verification flow, roommate board, landlord dashboard, multi-step onboarding, messaging interface, and more - entirely designed and iterated inside Google Stitch.
HOW I USED STITCH
Before generating a single screen, I designed my own logo - a map pin housing a rooftop icon - and imported it into Stitch to generate a design.md (http://design.md) brand file. Stitch scanned the logo and produced a complete design system: color palette, typography, card radius, shadow depth, and spacing. Every screen inherited that system automatically from the start.
Each of the 18 screens was then streamed live to the canvas - letting me review and plan refinements on one screen while the next was still being generated.
Once screens were on the canvas, I used Stitch's in-place AI edit feature to refine specific elements without regenerating anything. I clicked directly on a footer, typed a prompt, and only the footer changed. Same for card layouts, button colors, and badge styling - precise, targeted iteration on exactly the element I chose.
For motion, I used Stitch's native HTML canvas to build the NIC verification animation: the ID card shakes first as a visual cue, then flips smoothly on double-click. Property cards lift and shadow on hover. Because Stitch renders native HTML by default, every animation played in real time directly on the canvas as I built it.
For the code pipeline, I used Stitch's MCP connection to import Antigravity. Antigravity handled the code-side refinements - the logic and structure that go beyond what a visual canvas touches. Stitch for design. Antigravity for code. A full design-to-code pipeline, linked through MCP.
FEEDBACK ON STITCH
The real-time streaming canvas changed how I design. You stop waiting for a result and start collaborating with it - refining the previous screen while the next one is still being generated. That shift alone made the process feel genuinely different from any other tool I have used.
The in-place edit feature removed the biggest frustration of AI design tools: the fear of regenerating something good just to fix something small. Clicking directly on an element and prompting only that element to change is the kind of control that makes iteration feel safe.
The MCP integration with Antigravity was the unexpected part. It bridges the gap between a design prototype and a real codebase in a way I did not expect from a design tool.
Stitch did not just speed up how I work. It improved the ideas I had while I was working.
4
15
825
🌍 Introducing my ElevenCreative Template — a fully automated country-based video generation workflow!
Pick a country. Add your location. Drop in two faces (male + female). Hit run.
From there, EVERYTHING is auto-generated:
🎵 Country-matched background music
🗣️ Welcome narration spoken in the local language
💃 Culturally matched poses and expressions
🎬 Smooth video transitions — start to finish
No editing. No dubbing. No multi-tool juggling. One pipeline, one click, one complete video.
This template chains image generation, lip-sync, TTS, and music models inside ElevenCreative Flows — replacing a workflow that would normally take hours across multiple tools and platforms.
🔗 Try the template here → https://elevenlabs.io/app/templates/JLcakgDoamRbKLgR78q7
@ElevenCreative #ElevenCreative
1
8
569
THE LAST NODE — A Complete AI-Generated Graphic Novel
Built entirely on Melius
What I Built:
365 nodes on one Melius canvas
20 story pages across 5 chapters
57+ individually generated panels
3 full-page cinematic splash panels
Complete front and back cover
Character sheets, environment sheets, prop sheets — all locked for consistency
How I Built It:
I used Melius chat to automatically generate the node structure from my story idea. Then I wired character reference nodes, environment reference nodes, and prop nodes into every single image generation node — so Kael's face, his red jacket, and Cipher's green LED stayed consistent across all 57 panels. Every page runs through its own chain: prompt node → Nano Banana Pro art generation → overlay → assembly. All nodes ran without a single crash or freeze.
Read the full graphic novel:
🔗 https://melius.isumenuka.me/
Explore the full Melius canvas:
🔗 https://app.melius.com/projects/34dbc88b-ddef-411b-98f4-3a63f19527dc/canvas/1aca8142-094c-4e8c-8bfd-55a5911bf83a
Demo video and workflow screenshots attached above.
1
13
559
🎙️ I just built an AI Podcast Video Workflow on @Morphic
that turns ONE image into a full cinematic podcast video automatically.
Here's what it does:
✅ Generates your podcast scene
✅ Creates cinematic B-roll cutaways
✅ Lip-syncs your character to your voice
✅ Alternates camera angles automatically
✅ Adds background music & sound effects
No camera. No studio. No editing skills.
Just one image. One script. One click. 🚀
Try it yourself 👇
https://www.morphic.com/en/workflows/019d963f-181f-76c4-ac88-ff0beae68ec7/podcast-face-reborn
#MorphicWorkflowChallenge @Morphic
4
16
707
Stop chasing your dog with a party hat! 🐶🎂
The Story:
Every pet owner knows the struggle - you want that perfect birthday photo, but your pet won’t sit still, balloons keep popping, and the cake disappears before you even take the shot. This is exactly why I built the Pet Birthday Photoshoot Generator in FLORA.
The Workflow:
This technique transforms a complex creative process into a single click. It automatically generates studio-quality birthday photos using multiple camera angles - dramatic low shots, clean eye-level portraits, and aesthetic top-down flat lays - while maintaining consistent themes, lighting, and composition.
Smart Pet Analysis:
When you upload your pet image, the system intelligently analyzes key details such as:
Fur color and patterns
Pet size and proportions
Eye color
Breed/type characteristics
Overall appearance and vibe
Based on this analysis, it automatically generates perfectly matched:
Birthday cake design (color, size, style)
Party hat and accessories
Neck bands / bows
Background themes and decorations
Everything is customized to fit your pet naturally—so every photo looks realistic, styled, and professionally shot.
Try it yourself:
🔗 https://app.flora.ai/techniques/pet-birthday-photoshoot-generator
Built with @FLORA 🌸
#FLORATechnique
11
30
2.4K
NailHealth AI uses Google's Health AI Developer Foundations (HAI-DEF) models to detect serious diseases through nail signs captured via smartphone camera. The app provides instant clinical explanations and disease predictions.
1
172
This project aims to develop an integrated web application that leverages machine learning models to provide early, multi-disease risk assessment for Non-Communicable Diseases (NCDs). The system focuses on four major NCDs
0
159
MindRoots is an interactive, voice-driven web application powered by Google's Gemini 2.5 Flash Native Audio Preview and the new Gemini Multimodal Live API. It leverages advanced conversational AI to act as a responsive, real-time agent that can see, hear, and speak with users, dynamically maintaining affective dialog and providing mental frameworks/belief trees.
0
129