With its artificial intelligence tool, Microsoft can turn photos into realistic videos and even make photos sing.
Long before the advent of generative artificial intelligence making songs sing for photos, animations started to be made. Microsoft’s artificial intelligence tool now turns photos into more realistic videos. Not only that, the tool can also make photos sing whatever they want, in any way they want: this includes songs.
Introduced by Microsoft Asia Research and VASA-1 The artificial intelligence tool called can take any photo or drawing and combine it with an existing audio file. The new artificial intelligence tool can create facial expressions and head movements. It also produces mouth movements appropriate to speech.
It is clear “for now” that the images are the work of artificial intelligence
Although in the images created by VASA-1 mouth and head movements While it looks a bit robotic, when we look closely, there are shifts in voice and lip synchronization. However, it also comes to mind that these technologies can be used to create fake images or produce deepfake videos over time. Researchers are also aware of this situation and that is why they did not share a usable demo or API. This technology alsoresponsiblyHe stated that they wanted to make sure that it would be used.
Still, researchers believe this technology can be used for good purposes. VoxCeleb2 It is stated that communication with artificial intelligence can be strengthened, new tools can be developed in the field of education and communication difficulties can be solved, thanks to the artificial intelligence tool trained with the images of 6112 celebrities with the data set called.
You can access the research and demo images published by Microsoft here.
Source :
https://www.engadget.com/microsofts-ai-tool-can-turn-photos-into-realistic-videos-of-people-talking-and-singing-070052240.html?src=rss