About This Project
Developed a UGC video generation platform enabling AI-created content through automated storyboarding, text-to-speech, face-swapping, lip-syncing, and compositing. Designed and implemented AI-driven video pipelines using DeepFaceLab, Wav2Lip, and OpenCV for seamless facial animation and synchronization. Built an automated B-roll generation system leveraging web scraping, video understanding models (Qwen2.5-VL, Video-LLaMA), and Unreal Engine for physics-based storytelling. Optimized GPU-accelerated microservices for text-to-speech and face-swapping, achieving fast, scalable video synthesis.
Technologies Used
DeepFaceLabWav2LipOpenCVQwen2.5-VLVideo-LLaMAUnreal EnginePythonMicroservices
Project Information
- Category
- entrepreneurship
- Year
- 2023