People using the free version of Google Bard, Google’s chatbot competitor to ChatGPT, will now be able to take advantage of yet another ChatGPT-like feature: AI image generation.
Google has added this option to creating images in Google Bard just last week, making it incredibly straightforward to jump in and tell the chatbot exactly what you want to see. The system uses Gemini Pro and the Google Imagen 2 model to create images, which means you can expect a decent balance between quality and speed. Google says Bard should deliver “photorealistic results” every time you operate it, though in my experience the quality definitely varies.
How to create images in Google Bard
Creating images in Google Bard is the same as telling you to take an image of yourself. All you need to do is go to Bard’s website and type “create image” or “generate image” and then type the image you want to see.
Source: Google / Joshua Hawkins
The results of these prompts can vary, as with any AI generation system, and sometimes it takes a bit of configuration to find the perfect prompt for what you want the chatbot to create. But with a little patience you can usually get a decent result. Google Imagen 2 is impressive, even compared to other image generation models we’ve seen, such as Midjourney. What makes generating images in Google Bard especially nice is that it usually spits out several different style options for each prompt, which can cut down on back-and-forth time.
It is worth noting that any images generated using Google Bard will not qualify as “human-made” not only due to their quality, but also due to Google’s inclusion SynthIDwhich embeds a digital watermark into pixels to show whether an image has been generated by artificial intelligence.
