Google Brings Native AI Image Editing to the Gemini App | PCMag
Google has announced that it is introducing AI image editing directly to the Gemini app, allowing users to upload images and provide text prompts to make changes such as altering backgrounds, replacing objects, or adding elements. This new feature eliminates the need for traditional photo editing software.
AI Image Editing in Gemini
According to a (source), Gemini's AI image editor can perform various tasks like changing backgrounds, replacing objects, and adding elements based on user inputs. Additionally, users can combine text and personalized images using Gemini's multi-modal capabilities.
Availability and Languages
Google has begun the gradual rollout of Gemini's photo editing capabilities, with availability expanding to over 45 languages and most countries in the coming weeks.
SynthID Digital Watermark
All images modified using Gemini will feature an invisible SynthID digital watermark. This technology, developed by Google, aids in detecting AI-generated images. Google is considering implementing this watermark on all images produced by Gemini, not just edited ones.
Comparison with OpenAI
OpenAI also utilizes watermarks on images generated by its GPT-4o model. The company embeds ChatGPT's image outputs with C2PA metadata to facilitate identification by AI image detectors. ChatGPT's native image generation capabilities were recently introduced, resulting in a significant number of generated images in its first week of release.
Studio Ghibli-inspired images created by ChatGPT users gained popularity on social media, despite some outputs being perceived as unsettling.
