Google Bard has been out and trying to compete with Microsoft’s Bing and OpenAI’s ChatGPT for a bit now, but Google’s AI chat assistant has been missing a key feature that the other AI chat assistants have had for a while now: image generation.
Thankfully, that imbalance in the force is coming to an end. In a blog post, Google announced its latest update to Bard which, in addition to launching Gemini Pro in more languages, also enables the creation of AI-generated images for the first time.
The most notable update for Bard today is the ability to generate images through a text prompt. The feature, which is currently only available in English, is designed to “balance quality and speed, delivering high-quality, photorealistic outputs. Just type in a description — like ‘create an image of a dog riding a surfboard’ — and Bard will generate custom, wide-ranging visuals to help bring your idea to life.”
For an extra creative boost, you can now generate images in Bard in English in most countries around the world, at no cost. This new capability is powered by our updated Imagen 2 model, which is designed to balance quality and speed, delivering high-quality, photorealistic outputs. Just type in a description — like “create an image of a dog riding a surfboard” — and Bard will generate custom, wide-ranging visuals to help bring your idea to life.
The image generation feature is enabled by Google’s new Imagen 2 model, which the company says delivers its “highest-quality images yet, as well as 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.
I tried out the new image generation feature with a basic prompt, asking it to create an image of a hiker on a mountain. It popped out two images with one being more realistic and one being more artsy. Both hikers had trekking poles, even though I didn’t ask for them. That’s fine though, trekking poles are the way. It seems the feature is available widely immediately, so get creating!
In addition to image generation, the latest update also brings Gemini Pro to more languages. The company already brought Gemini Pro into Bard in English, but it is expanding the technology to over 40 more languages. Gemini Pro makes Bard “far more capable at things like understanding, summarizing, reasoning, coding, and planning.”
The Large Model Systems Organization, a leading evaluator of language models and chatbots across languages, recently shared that Bard with Gemini Pro is one of the most preferred chatbots available (with or without cost), noting that it has made a “stunning leap” forward. And blind evaluations with our third-party raters identified Bard with Gemini Pro as one of the top-performing conversational AIs, compared to leading free and paid alternatives.
As Google finally gets into image creation with Bard, Yelp is over here using AI to determine which images of food you see at restaurants. The AI is apparently going to be involved in what we see one way or another — even if it’s not creating the images itself.