Farewell Photoshop? Google’s new AI lets you edit images by asking
1 min read
Summary
Google has made its new Gemini 2.0 Flash AI image generation model available to all users of its AI studio, which integrates text and image processing in one AI model.
The model is capable of removing watermarks from images, adding objects, changing lighting and modifying scenery, among other effects.
It can also edit images during chatbot conversations, all in one system without needing a diffusion-based AI model.
However, the model is not without its limitations, with outputs still being of varying quality depending on the image in question.
The model was trained on a large dataset of images and text, and its image intelligence occupies the same neural network space as its knowledge of world concepts from text sources.
