Users of Google Bard’s free version, Google’s AI chatbot rival to ChatGPT, can now utilize a new feature akin to ChatGPT: generating AI images. Last week, Google introduced the capacity to create images in Google Bard, facilitating the process of instructing the chatbot about what you desire to visualize. The system leverages Gemini Pro and Google Imagen 2 to generate images, balancing quality and speed. Google claims that Bard is expected to yield “photorealistic outputs” each time it’s used, although my experience reveals varying quality. The process of creating images in Google Bard is straightforward. To create an image, visit Bard’s website and type “make a photo” or “make a photo,” then specify the photo you wish to see.
Credit: Google / Joshua Hawkins The outcomes might vary, typical of any AI system, and understanding how to guide the chatbot to yield your preferred details takes a bit of time. However, with some patience, satisfactory results can be achieved. Google’s Imagen 2 system stands out amongst other image categories we’ve encountered, like Midjourney. The advantage of creating images in Google Bard is the availability of swift editing options, which can be downloaded and adjusted quickly. It’s important to note that while the quality of the images created through Google Bard may not be at the level of human creations, they are tagged with a digital signature by SynthID, indicating that they were generated by AI.
