Aug 19, 2024 By Matt Growcoot
Google has released an updated version of its AI image generator to everyone in the U.S. via the company’s AI Test Kitchen service.
Google Imagen 3 was first announced in May during the company’s I/O keynote but it was only rolled out last week after Google published a research paper on it.
Imagen 3 works like most other AI image generators: Users type in a prompt and wait for about 30 seconds until the pictures begin to appear. Google says the model “is preferred over other state-of-the-art models at the time of evaluation.”
In PetaPixel’s tests, Imagen 3 does appear to be a quality text-to-image model that rivals Midjourney or OpenAI’s DALL-E. What’s more, Imagen 3 is currently free-to-use unlike the aforementioned.
“Imagen 3 is our highest quality text-to-image model, capable of generating images with even better detail, richer lighting and fewer distracting artifacts than our previous models,” Google says.
“We’ve significantly improved Imagen 3’s ability to understand prompts, which helps the models generate a wide range of visual styles and capture small details from longer prompts.”
There is little word on the data used to train Imagen 3. In the paper, Google says “The Imagen 3 model was trained on a large dataset comprising images, text, and associated annotations.” It is extremely likely that the dataset contains scores of copyrighted photos.
As well as generating images, Google gives the option of editing the images using the now common inpainting technique. This method allows the user to select a part of the image and type in the change they would like to see.
Unlike Elon Musk’s Grok AI image generator, Google has placed restrictions on Imagen 3. PetaPixel was unable to generate an image of “Kamala Harris and Donald Trump holding hands” or “A Californian landscape in the style of Ansel Adams.”
However, as is well-documented, there are workarounds. For example, by asking Imagen 3 to “Make a dramatic black and white photo taken in 1942 of the Grand Teton National Park in Wyoming” the user will receive back an image similar to that of Ansel Adams’ work.
The Verge got around copyright restrictions on famous cartoon characters by asking for “an image of a cartoonish blue hedgehog running in a field” and receiving a picture of Sonic the Hedgehog.
Earlier this year, Google landed in hot water after its AI image generator on Gemini was accussed of overcorrecting for biases and essentially “erasing white people.” It led Google to remove the image generator entirely.
Story from Petapixel.com
Matt Growcoot
Matt Growcoot spent ten years as a news photographer in the UK, carrying out assignments for the Guardian, the Daily Mail, the Telegraph, and many others. Aside from shooting breaking news and Premier League soccer, he began to write as well, getting bylines as well as photo credits. Matt has since produced photography-focused books for Penguin Random House and dabbled with video too, with his story-led camera work seen on the BBC, ABC, and NHK.
💬 What Do You Think?
Share your thoughts on this story with the TechNews ED community in the General Discussion.
👉 Join the Discussion ✅ Register Free
Its like you read my mind You appear to know so much about this like you wrote the book in it or something I think that you can do with a few pics to drive the message home a little bit but other than that this is fantastic blog A great read Ill certainly be back
Tech to Trick I very delighted to find this internet site on bing, just what I was searching for as well saved to fav
allegheny county real estate Hi there to all, for the reason that I am genuinely keen of reading this website’s post to be updated on a regular basis. It carries pleasant stuff.