Tech Desk 
Jul 29, 2024
Image generation is one of the core tenets of any AI bot. One of the most fascinating abilities of AI is to generate images using text prompts, a capability almost every AI already has up its sleeves.
Google’s Gemini is no different in this regard, but it does lack an essential capability, as it can use weak images once generated but that is set to change.
In the latest bets version of the Google app (v.15.29.34), new tools have been introduced to allow for images to be tweaked. This will surely upgrade the Gemini experience, it's annoying to get an image that’s just lacking in one department.
In this case, Gemini would have the user generate a whole new image rather than have them tweak an aspect and that’s incredibly exhausting, luckily the suffering won’t last.
Read more: Google Gemini gets massive speed upgrade with fast 1.5 Flash
This fine-tuning can go two ways. First, a simple language prompt will do just fine in having Gemini take up the matter. Second, users can use their fingers or a stylus to highlight a section of the image and then describe the needed alterations.
It’s a bit of a bummer to know that there’s nothing besides evidence to suggest the coming of these features, Google’s probba;y yet to do a bit of polishing, nonetheless, the prospect is exciting.
How to use Gemini mobile app
This is how you can use the Gemini mobile app, according to Google:
- Open the Gemini app, or
- Activate Gemini by touch (such as long pressing the power button or swiping up from the corner of your screen).
On Android mobile devices where you use Google Assistant, if your device is eligible, you can get started with Gemini if you:
- Get a notification from Google Assistant to switch to Gemini, or
- Download the Gemini app from the Google Play Store.
