🎭 DreamLens – Turn Any Story Into a Mini Movie What I Built

Rohit Mane — Mon, 08 Sep 2025 12:05:52 +0000

I built DreamLens, a multimodal applet powered by Google AI Studio that transforms any idea, story, or doodle into a short animated movie.

Everyone has imagination—kids tell fantasy tales, writers create worlds, gamers describe epic battles—but most can’t turn them into visuals and sound. DreamLens solves this by using text, voice, and image understanding to automatically generate storyboards, narration, and background audio.

How I Built It

Frontend: React (simple input box + doodle/image upload + voice mic)

Backend: Python Flask on Cloud Run

AI: Gemini 2.5 Pro for multimodal input

Text + Voice processing via Gemini Live API

Image/doodle understanding via Gemini 2.5 Flash Image

Script/narration generation via Gemini text model

Deployment: Google Cloud Run

Other Tools: Tailwind (UI), Firebase (story saves), optional text-to-speech

Key Features

📝 Story-to-Movie → User types or narrates a story, Gemini generates visuals + narration.

🎤 Voice-to-Story → Kids or users can simply tell a story and see it animated.

🖼️ Doodle-to-Scene → Upload a doodle/sketch, Gemini turns it into a polished scene.

🎙️ Custom Narration Styles → Funny, dramatic, bedtime storyteller, etc.

🎶 Background Music → Automatically matched to story mood (epic, spooky, calm).

🔄 Interactive Regeneration → Users say “Add a villain,” “Make it funnier” → instantly updated.

Challenges I Faced

Synchronizing story + visuals + narration into one flow.

Handling latency in image + audio generation without breaking immersion.

Designing an interface that’s both simple for kids and powerful for creators.

What’s Next

📚 Education Mode → Teachers can create animated lessons (history, science).

🎮 Gamers Mode → Auto-generate cinematic recaps of role-playing campaigns.

📱 Mobile App → “Tell a story, watch it come alive” in seconds on phones.

🌍 Community Sharing → Users can share their AI mini-movies with friends.

Submission Category

🔹 Innovation and Creativity

🔹 Technical Implementation

🔹 User Experience

🔹 Effective Use of Multimodal Features

Team Members

Rohit Mane

LifeLens – My Multimodal Health & Wellness Companion

Rohit Mane — Sun, 07 Sep 2025 04:11:55 +0000

🚀 LifeLens – My Multimodal Health & Wellness Companion

This is a submission for the Google AI Studio Multimodal Challenge

What I Built

I built LifeLens, a personal health & wellness companion applet powered by Gemini’s multimodal intelligence.

Instead of juggling separate apps for food logging, fitness, and mood tracking, LifeLens lets you:

📸 Snap a meal photo → Get calorie & nutrition breakdown

🏋️ Upload a workout photo/selfie → Detect exercise type and duration

🎙 Record a voice note → Analyze mood, stress, or energy levels

✍️ Write a quick journal entry → Extract lifestyle insights (e.g., sleep quality, focus)

At the end of each day, Gemini compiles everything into a personalized daily health snapshot — a simple, infographic-style report that shows nutrition, activity, and mood in one place.

The goal: make health tracking frictionless and holistic, using natural inputs (photo, voice, text).

Demo

🌐 Live App (Cloud Run):

🎥 Demo Video:

🖼 Screenshots:

Meal photo → nutrition analysis

Workout photo → activity detection

Voice note → stress/mood insights

Final daily health report (infographic)

How I Used Google AI Studio

I used Google AI Studio with Gemini 2.5 to power all the multimodal intelligence in LifeLens:

Image understanding → Meal & workout detection

Audio analysis → Emotional tone & mood recognition

Text extraction → Journaling insights + summarization

Multimodal fusion → Combine all three inputs into one personalized daily report

The best part is that Gemini can process mixed inputs in a single prompt, so the final report feels contextual and cohesive rather than three disconnected analyses.

Multimodal Features

Here’s how multimodality shines in LifeLens:

📸 Food recognition – Instead of manually typing calories, just take a picture.

🏋️ Exercise recognition – Gemini detects workouts visually.

🎙 Mood detection – Voice notes capture feelings more authentically than typing.

✍️ Lifestyle journaling – Short reflections provide context Gemini can analyze.

📊 Daily Health Report – Combines everything into a single, easy-to-read summary (optionally with an AI-generated infographic).

Together, these make LifeLens a natural and engaging way to track health, lowering the barrier for consistent use.

Why It Matters

Most people abandon health apps because logging feels like work.

LifeLens makes tracking feel like living your day normally: take a picture, talk to your phone, write a sentence.

Gemini does the heavy lifting, turning it into insightful, actionable feedback.

Roadmap

If I expand this applet further, I’d add:

📱 Wearable integration (steps, heart rate, sleep)

🎮 Gamification with streaks & achievements

🌍 Multilingual support for accessibility

🤝 Community features for sharing anonymized health highlights

Team

Solo project by @rohitsmane57-glitch

DEV Community: Rohit Mane

🎭 DreamLens – Turn Any Story Into a Mini Movie What I Built

LifeLens – My Multimodal Health & Wellness Companion