With the announcement of the Xiaomi 14 and 14 Pro, Xiaomi also announced its replacement for the MIUI called HyperOS. One of the intriguing features of the OS is to use generative AI to stitch your photo with photos of famous locations with your Xiaomi phone.
The way it works is that the tool takes some images of you to generate a model of the person in the photo. With the data, it then can generate and create new photos using the generated data, and images from other locations.
Xiaomi showed sample photos during the Xiaomi 14 launch event. The model first took photos of herself to generate the data that the AI could use later on. In the subsequent images, the model is now on a mountaintop, wearing different clothes, and even seen posing in front of the Eiffel Tower.
Xiaomi also showed an example of generative AI used to fill in data to create a larger image based on a current sample image. The picture of the boy and the dog was originally only focused on the two subjects, but with AI, more information was added around the subjects, making the image larger.
This is quite impressive, and it is way more than Google’s new generative AI photo features, which was launched with the Pixel 8 Pro. With Google’s tools, the photos are either edited post-photo taking with Magic Eraser to take out unwanted elements in the photo, or with Best Take, a few images are taken in rapid succession and the best parts of the photo are spliced into one end photo. Imagine removing a blinking eye with an open eye in the photo.
With Xiaomi, it is actually creating new photos with non-existent information. The question is then – are the photos truly of you going on vacation, or it is just a mind trick played by AI?
[SOURCE]