Google has launched the most colorful feature yet: image generation. So whether you want to mock up a futuristic car or just need an image of a Yeti wearing sunglasses—if you can think it, Bard can create it. Have fun exploring!
Generate Images with Bard
Create totally unique images with Bard. Enter a few words to bring your imagination to life, generate more options, and download the ones you like.
Here are some sample prompts used to create the images above. What will you dream up?
- Create an image of a majestic oil painting of a dinosaur king and queen wearing red French royal gowns.
- Create an image of an alien octopus floating through a portal reading a newspaper.
- Create a picture of puppies in a basket.
Prompt Engineering 101: Paint a Picture with Words
You can unleash your creativity with Bard using either long or short prompts—it all depends on what you want to create. Here’s how to know how much to write.
Have a specific image in mind? Adding vivid details to your prompt can help Bard recreate what’s in your imagination. A short paragraph is the sweet spot, so it’s nicely detailed without becoming overwhelming.
I KNOW WHAT I WANT | SAMPLE PROMPT
Generate a photorealistic image of an adorable hedgehog, its fur neatly combed, riding a rocket ship, zooming across a vibrant sky full of stars, leaving a trail of shimmering stardust behind.
Not sure what kind of image you want? Not a problem. Write just the basics, then let Bard take it for a creative spin. Bard will add dimensions to your prompt and you’ll see a range of images to choose from.
I’M OPEN TO IDEAS | SAMPLE PROMPT
Generate an image of a hedgehog traveling through space.
Behind the Scenes at Bard with Andrew Goodman, the Product Manager – Bard’s image generation:
Q: “How descriptive do I need to be when I ask Bard to generate an image?”
A: “It helps to be more descriptive, but you can start image generation with just a few words. When a user enters a prompt to generate images, Bard actually expands on the user’s prompt with additional descriptions to create more detailed images. If you want to see more options, you can always edit the prompt yourself or generate more options.”
Q: “How is Bard approaching watermarking images generated by AI?”
A: “Using a technology called SynthID, all unique images generated on Bard will have embedded watermarking to indicate that it was created by AI. The watermark is directly added into the pixels of an AI-generated image, meaning it’s imperceptible to the human eye but it can still be detectable with SynthID. It’s important that we approach the creation of images with AI responsibly.”
