Google announced its artificially intelligent (AI) movie generator called Imagen Video. It is still in the development phase, but the company says it will be capable of producing 1280×768 videos at 24 frames per second from a written prompt.
According to Google’s research paper, Imagen Video will have stylistic abilities, such as generating videos based on the work of famous artists like Vincent van Gough. It will also generate 3D rotating objects while preserving their structure and rendering text in various animation styles.
Google hopes its AI-video model can significantly decrease the difficulty of high-quality content generation. Imagen Video builds on Google’s Imagen, a text-to-image program similar to OpenAI’s DALL-E.
Read More: OpenAI’s DALL-E Is Now Available To Everyone
As Google’s research team described, Imagen Video will take a text description and generate a 16-frame, three-frames-per-second video at 24×48 pixel resolution. The system then upscales and predicts additional frames, producing a final 128-frame, 24-frames-per-second video at 720p.
Google says that Imagen Video has been trained on 14 million video-text pairs and 60 million image-text pairs, as well as the LAION image-text dataset, which was used to train Stable Diffusion.
Among the examples provided by Google are a panda chewing on bamboo, a zooming shot into a choppy sea filled with pirate ships, and an astronaut riding a horse. It is worth noting that all the results from Imagen Video are picked by Google, and as of yet, no independent testers have tried the program.
