Similar to OpenAI’s Sora, Google unveiled Veo, a new AI video synthesis model that can produce HD videos from text, images or video cues. Although it hasn’t been made available for public usage yet, it can edit videos from written instructions and produce 1080p recordings longer than a minute.

According to the sources, Veo has the capacity to create video sequences up to and including 60 seconds from a single query or a sequence of prompts that construct a narrative. It can also apparently modify pre-existing videos using text instructions and retain visual consistency across frames. According to company officials, it can create intricate scenes and incorporate cinematic elements like time-lapses, aerial views and different visual styles.

A plethora of additional image synthesis and video synthesis models have emerged since the debut of DALL-E 2 in April 2022, with the goal of enabling anyone with the ability to enter a written description to produce a detailed image or video. AI picture and video producers are steadily getting stronger. Google’s Veo seems to be able to create videos in a similar way to Sora.

Moreover, Google unveiled Imagen 3, a brand-new image creator. Similar to Veo, there is a waitlist, but it is only accessible to a restricted group of creators in private preview. Imagen 3 outperforms Imagen 2 in terms of emulating various artistic styles, deciphering the text prompt’s meaning and converting text into images—an area where AI picture producers frequently stumble.

Read More : https://thecioconnect.com/