Google has introduced AI-powered photo-editing features in Gemini. You can now ask the chatbot to change the background of an image, add new elements, enhance photo clarity and quality, and perform many other edits by using text prompts. These features are also available in the free version.
Gemini Gets Photo Editing Functionality
The photo-editing features are powered by the Gemini 2.0 Flash model, a fast and effective LLM that can generate images and media. Initially, image editng features were only available in the Google AI Studio, but now have been expanded to Gemini. You can use this feature on any Android, iOS, or computer from the official Gemini client.
Once you upload the image, you can describe your desired editing request using text prompt. For example, you can change the background of the subject, replace the sky, add a sports car in your portrait photo, etc. Google has also implemented safety features in the tool that block and prevent users from potentially harmful requests involving deepfakes, adult content, and more.
All the images edited using Gemini AI will include a SynthID digital watermark. It adds hidden elements to your image, using which Google can detect that the photo was edited using AI. This makes it easier to track the source of image which is important if a certain altered image goes viral for the wrong use. This measure also prevents misuse of the technology.
The image editing features in Gemini will start rolling out to all users globally starting today. The rollout is happening in batches, so it could take a while before you can use it.
It is worth noting that Gemini had support for limited image generation features in its early days. However, the company halted the functionality due to large number of complaints of inconsistencies. The new Gemini 2.0 Flash model appears to have fixed the problems, and Google can now finally compete with OpenAI’s ChatGPT, which recently got popular for its image editing features with the Ghibli-style anime edit trend.
