Google has introduced a new concept called Lumiere - a time-space diffusion model that can convert text and images into AI-produced lifelike videos.
The motion graphics can be edited on-demand, providing user flexibility.
Developed by Google researchers, Lumiere can take a text or image input and produce a realistic video with the help of artificial intelligence.
It's designed to create “realistic, diverse, and coherent motion” using its unique “Space-Time U-Net architecture." This technology enables Lumiere to generate a video in its entirety instantly, in just a single pass of the model.
For more information on the fusion of crypto and AI, users can browse the magazine 'Crypto+AI token picks, AGI will take ‘a long time’, Galaxy AI to 100M phones: AI Eye.' For more details, visit the link available in the source.