ChatGPT is set to get better with a new text-to-video generator – as noted by Microsoft Germany’s CTO in an event this week.
He cited the launch of GPT-4 – coming next week – as the base for this new support. This new language model from OpenAI would let ChatGPT users create images and videos from simple text input and since the technology is integrated into Bing Search, Microsoft users too can take advantage of this.
ChatGPT’s Text-to-Video Generation
As if the current form of ChatGPT isn’t enough, the generative AI tool is getting better with the addition of text-to-video support soon. This was revealed by Andreas Braun, the CTO of Microsoft Germany, at the AI in Focus — Digital Kickoff event.
The new support is coming in the form of GPT-4, a next-gen language model made by OpenAI for the improvement of ChatGPT. To the unknown, the Generative Pre-trained Transformer (GPT) is a language model that powers the ChatGPT.
The current mode for ChatGPT – GPT-3 and GPT-3.5 are limited to text output only. So upgrading it to the next level (GPT-4) would add the ability of text-to-video to ChatGPT and apps that are relying on it.
Talking to a German news outlet named Heise, Braun said “We will introduce GPT-4 next week; there we will have multimodal models that will offer completely different possibilities — for example, videos.”
Well, this technology isn’t new, as we have the examples of Make-A-Video from Meta and ImagenVideo from Google doing the same(text-to-video generation) – but they’re still in the research stage and unavailable to the public – putting ChatGPT ahead of them.
OpenAI’s ChatGPT has amassed 100 million active users in the second month of it’s operation – and also benefitting the services relying on it as well. With it’s worldwide adoption, ChatGPT’s upcoming text-to-video generation will garner even more popularity.
Other Trending News:- News