AI startup Decart has unveiled Lucy 2.0, a real-time video transformation model capable of modifying live video streams at 30 frames per second in 1080p resolution with near-zero latency. The system enables character swaps, product placements, clothing changes, and full environment transformations — all controlled via text prompts and reference images while the video is still running.
According to Decart, Lucy 2.0 does not rely on depth maps or 3D models. Instead, physical behavior emerges purely from learned patterns in video data. A new technique called “Smart History Augmentation” prevents visual quality from degrading over time, allowing the model to operate stably for hours, the startup claims. The system runs on AWS Trainium3 chips. A public demo is available at lucy.decart.ai.
AI Analyst & Technology Researcher
AI researcher and industry analyst covering decentralized infrastructure, AI systems, and emerging technology markets. Focused on data-driven analysis, long-term trends, and real-world adoption of artificial intelligence.