is adding three features to its
Bard
AI chatbot, including AI image generation and support for more languages on
Gemini Pro
as well as double-check feature. Image generation by text inputs is the flagship feature among the three, and it happens to be among the ones that competitors like ChatGPT Plus and Copilot have had for some time.
Powered by Google DeepMind, Google’s advanced AI image generating tool called
Imagen 2
creates “highest-quality images yet” that Bard has to offer.
It also gets improvements in areas that text-to-image systems often struggle with, such as rendering realistic hands and human faces and keeping images free of distracting visual artifacts.
“Imagen 2 has been trained on higher-quality, image-description pairings and generates more detailed images that are better aligned with the semantics of people’s language prompts. It’s more accurate than our previous system at processing details, and it’s more capable at capturing nuance — delivering more photorealistic images across a range of styles and use cases,” Google said.
Guardrails for AI image generation
Google said that it “added technical guardrails to limit problematic outputs like violent, offensive, or sexually explicit content.” Additionally, the images generated with Imagen 2 in consumer products will be marked by SynthID, which is a tool that adds a digital watermark directly into the pixels of images generated.
Bard with Gemini Pro is coming to more languages
Google Bard with Gemini Pro large language model (LLM) is coming to all languages, including multiple Indian languages, where Bard is available.
Finally, the double-check feature is also available for Bard responses in most supported languages. To help you double-check Bard's statements, users can use the Google button to summon
Google Search
and find content that’s likely similar to or likely different from Bard’s statements.
English (US) ·