A versatile web application that leverages advanced AI models, including Gemini Flash, DALL-E 3, and Stable Diffusion XL, to provide three main features: Chatbot Interaction, Image Captioning, and Text-to-Image Generation.
Experiments in structured perception and system-level interpretation of visual data.
An AI-powered educational backend built with FastAPI, Firestore, and Gemini 2.0. Ingests multiple file formats (PDFs, DOCX, PPTX, images, audios, and YouTube URLs) to generate personalized, active-recall study aids (summaries, flashcards, flowcharts, and adaptive quizzes) tailored to user performance.
Add a description, image, and links to the multimodal-processing topic page so that developers can more easily learn about it.
To associate your repository with the multimodal-processing topic, visit your repo's landing page and select "manage topics."