Google Introduces Text-To-Video AI Following Meta’s Lead

Google-Introduces-Text-To-Video-AI-Following-Metas-Lead
Google-Introduces-Text-To-Video-AI-Following-Metas-Lead

Similar to the software that Meta Platforms Inc. unveiled last week, researchers at Google LLC’s AI lab, Google Brain, has now unveiled Imagen Video, a program that can produce high-quality videos from text.

A “text-conditional video generation system based on a cascade of video diffusion models,” according to Google, is what Imagen Video is. It claims that using a base video generation model and a series of interlaced spatial and temporal video super-resolution models, it can produce high definition videos with just a text prompt. The generator will create HD video at a frame rate of 24 fps in 1280 x 768 resolution.

Although it’s still in the development phase, it’s already a significant improvement over Google’s text-to-image generation model DALL-E, which made its debut earlier this year.

Read More: Google follows Meta in introducing text-to-video AI

For more such updates follow us on Google News TalkCMO News.