Google Bard Adds Free Image Generation Feature

Google Bard, the AI chatbot that lets you collaborate with generative AI, has recently added a new feature that allows users to create images for free using text prompts. The feature uses Google’s Imagen 2 model and Gemini Pro to produce photorealistic outputs in various styles and formats.

Users can access the image generation feature by visiting the Bard website and typing “create an image” or “generate an image”, followed by a description of what they want to see. For example, one can type “create an image of a cat wearing a hat” and get several options to choose from. Users can also click the “tune” button to fine-tune the image by changing the seed number.

The image generation feature is similar to the one offered by ChatGPT, another popular AI chatbot. However, Google Bard has some advantages over ChatGPT, such as faster speed, higher resolution, and more style options. Google Bard also embeds a digital watermark called SynthID into the pixels of the generated images, to help identify them as AI-created.

Google Bard is an experimental tool that was launched in March 2023 as a direct interface to an LLM, a large language model trained on billions of words. Users can chat with Bard and ask it to perform various tasks, such as writing, brainstorming, researching, and more. Bard is designed to complement Google Search, as users can easily visit Search to check Bard’s responses or explore sources across the web.

The image generation feature is currently available only in English, but Google plans to add more languages in the future. Users can sign up to try Bard for free with their Google account, or upgrade to a premium plan for more features and benefits. To learn more about Bard and how to create images with it, users can visit the Bard Help page.