CineSnap
CineSnap is an AI-powered photo-to-cinema system that transforms a set of uploaded photos into a cohesive cinematic short film by analyzing all images as a unified story, generating a narrative script, creating video cli
Core trick
Gemini analyzes all photos as one set to write a connecting script, then Veo generates a clip anchored to each photo.
Description
CineSnap is an AI-powered photo-to-cinema system that transforms a set of uploaded photos into a cohesive cinematic short film by analyzing all images as a unified story, generating a narrative script, creating video clips anchored to each photo, and assembling them with smooth transitions into a final movie. The project has strong long-term potential because it solves a real problem, people have many photos but lack easy tools to turn them into engaging stories, making it useful for travelers, content creators, families, and social media users, while fitting directly into the multimodal AI and film problem space by showcasing how models like Gemini can perform vision understanding, storytelling, and creative generation in a single end-to-end pipeline with scalable applications in creative tools, media platforms, and automated content production.
README excerpt
# 🎬 CineSnap — AI Photo-to-Cinema Pipeline > **Turn your photo album into a cinematic experience — AI writes the story between your moments.** Built for the **Gemini 3 NYC Hackathon** · Track: Gemini and Film --- ## What It Does CineSnap transforms a collection of photos into a professional cinematic short film. Upload photos → AI analyzes them as one unified story → generates a cinematic script → produces video clips from each photo → assembles everything into a seamless film with smooth transitions. **The AI doesn't just animate photos — it fills in the gaps.** If you upload 5 photos from a beach trip, Gemini analyzes the entire collection as ONE continuous narrative, finds visual bridges between images (shared colors, subjects, lighting), writes connecting beats, and Veo generates transitional footage. Your photos become anchor points in an AI-directed short film — not a slideshow of separate clips. --- ## Architecture ``` Photos → Gemini Vision (analyze) → Gemini (unified script) → Veo 3.1 (generate) → FFmpeg (assemble) → Film ``` ### 4-Stage Pipeline | Stage | Model / Tool | Progress | What Happens | |-------|-------------|----------|-------------| | **1. Analyze** | Gemini 2.5 Flash (multimodal) | 5% → 15% | All photos sent in one request → extracts mood, subjects, lighting, visual bridges → groups into unified scene | | **2. Script** | Gemini 2.5 Flash (text) | 20% → 30% | Generates 1 clip per photo with Veo prompt, camera motion, transitions, audio — all as