TikTok also presented an AI text-to-image, that is a tool that allows you to create an image starting from a textual description.
TikTok also presented an AI text-to-image , that is a tool that allows you to create an image starting from a textual description. For example, you could write ‘Elvis Presley riding a T-Rex’ to get an image with this scene. And so on.
Text-to-image AI is not always very accurate and sometimes the results seem straight out of a horror story, nevertheless they have become extremely popular recently, especially thanks to the popularity of platforms such as DALL-E of Google’s spinoff DeepMind.
The AI of TikTok is part of the special effects made freely available to users and is called ‘ AI greenscreen ‘. The images thus created can be used by users as backgrounds for their videos. Exactly, like greenscreen.
The Verge, who tested the new TikTok feature, wrote that the results are not always very accurate and that it is undoubtedly a less sophisticated tool than DALL-E or other similar technologies.
Furthermore, the images produced by the AI have a rather uniform and abstract style. In short, if other tools even allow you to customize the style of the image (returning to the example above, you can also write “pastel illustration of Elvis Presley riding a T-Rex”), that of TikTok does not offer its users a huge freedom of choice and the images are all a little alike.
Also according to The Verge’s account, the software was also designed to avoid potentially unsuitable results for a young audience, such as sexual images or scenes of violence.