Google has announced major improvements to its AI platform, Bard. The tech giant said that Bard can now use Gemini Pro, Google’s latest multimodal artificial intelligence model, across all the languages and territories where it is currently available.
This is a major advancement in Bard’s capabilities, as Gemini Pro offers advanced understanding, thinking, summarizing, and coding capabilities in multiple languages.
Bard previously only integrated Gemini Pro in Bard for English.
The most interesting feature introduced is Bard’s newfound ability to create images. This feature is powered by Google’s latest Imagen 2 model.
It is available in English in most countries around the world and is free.
By entering a description into Bard’s text box, users can quickly bring their idea to life.
Custom visuals are generated with high-quality photorealistic outputs, and Bard embeds digitally identifiable watermarks to ensure authenticity.
Here is how you can use Google Image Generation:
- Open Google Bard
- Sign in to or make a Google Account
- Enter an image generation prompt
As ever with making extraordinary prompts for simulated intelligence, our top tip is to be pretty much as unambiguous as could be expected. We’d likewise propose beginning your brief by indicating you believe Versifier should make a picture.
Here are some examples of prompt from google that you can try on AI platform bard
- Generate an image of a futuristic car driving through an old mountain road surrounded by nature
- Create an image of a dog riding a surfboard
- Create images of a jungle with a river in a splashy watercolor style
+ There are no comments
Add yours