Google Unveils Imagen Video: A Text-to-Video AI Generator

Google’s latest AI generator creates HD videos from text prompts

Google today announced Imagen Video. This text-to video AI mode can produce 1280×768 videos with 24 frames per seconds from a written input. It’s still in the research phase but, five months after Google Imagen, its development shows how quickly video synthesis models are evolving.

Google’s research paper states that Imagen Video has several stylistic capabilities, including the ability to generate videos based off of famous paintings (Vincent van Gogh for example), create 3D rotating objects, while maintaining object structure, or render text in different animation styles. Google hopes that video synthesis models for general use will \”significantly reduce the difficulty in creating high-quality content.\”