This project is a browser-based experience where users either open a web link directly or scan a QR code that launches the experience on their mobile device. After capturing a photo through the web camera interface, the image is processed in real time and transformed into an AI-generated output. The system connects live camera input to a generative model pipeline via API integration, creating a seamless camera-to-AI workflow within a web environment.
I designed and implemented the full processing architecture handling image capture, client-side preprocessing, API request management, asynchronous response handling, and rendering the generated result back to the user. The transformation is powered through the Replicate API, where the captured image is processed by a generative model to apply a themed visual style dynamically.
This project demonstrates my ability to integrate external AI inference services into interactive web systems, manage latency and user experience during model processing, and build structured, end-to-end generative pipelines. It was independently developed for portfolio purposes and is not affiliated with any official brand collaboration.