Google Releases Free AI Art Generator That ‘Outperforms’ Popular Paid Rivals
By Mikelle Leow, 20 Aug 2024
Images via Google
Google is brushing up against the competition with Imagen 3, a free-to-use artificial intelligence image generator it says is its most powerful yet. As outlined in a research paper, the new model yields works that rival those of the top players in the AI art space. Imagen 3 is now available to all in the United States.
Imagen 3 is built on a latent diffusion model, allowing it to generate high-quality images from text prompts with newfound precision. The tool is said to outperform other state-of-the-art image generators—including the paid Midjourney and DALL-E 3 apps, according to PetaPixel—with an astute ability to handle complex prompts, as well as capture nuanced details like specific camera angles, compositions, and lighting that would challenge other AI models.
Prompt: “Shot in the style of DSLR camera with the polarizing filter. A photo of two hot air balloons floating over the unique rock formations in Cappadocia, Turkey. The colors and patterns on these balloons contrast beautifully against the earthy tones of the landscape below. This shot captures the sense of adventure that comes with enjoying such an experience.” Image via Google
Prompt: “A close up of a sleek wolf perched regally in front of gray background, in a high-resolution photograph with detailed fine details, isolated on a plain stock photo with color grading in the style of a hyper-realistic style.” Image via Google
Prompt: “A photo of a man with short hair and beard smiling at the camera. The background is blurry and it shows trees and buildings in light colors.” Image via Google
Prompt: “View from above of beautiful river canyon with trees, showcasing its stunning natural beauty with green mountains and blue waters. The photo captures the vastness of nature's creation in the style of its creation.” Image via Google
A key improvement in Imagen 3 is its enhanced understanding of user input, leading to sharper details and fewer distracting visual artifacts. This means users no longer need to be AI prompt engineers to get satisfying results. It delivers when it comes to creating small details, from the wrinkles on a person’s hand, to intricate textures, like those on a knitted stuffed animal.
Prompt: “Photographic portrait of a real life dragon resting peacefully in a zoo, curled up next to its pet sheep. Cinematic movie still, high quality DSLR photo.” Image via Google
Prompt: “A close-up photo of an origami bird soaring through a cityscape, in a flock with others of different colors and patterns, casting intricate shadows on the buildings below.” Image via Google
Prompt: “A view of a person’s hand holding a eucalyptus sprig - a macro DSLR image highlighting the balance of human and nature.” Image via Google
Imagen 3’s adaptability extends across a wide range of styles and formats, including realistic landscapes and whimsical claymation scenes.
Prompt: “Elephant amigurumi walking in savanna, a professional photograph, blurry background.” Image via Google
Prompt: “Claymation scene. A medium wide shot of an elderly woman. She is wearing flowing clothing. She is standing in a lush garden watering the plants with an orange watering can.” Image via Google
Prompt: “A large, colorful bouquet of flowers in an old blue glass vase on the table. In front is one beautiful peony flower surrounded by various other blossoms like roses, lilies, daisies, orchids, fruits, berries, green leaves. The background is dark gray. Oil painting in the style of the Dutch Golden Age.” Image via Google
Prompt: “A view of a person’s hand as they hold a little clay figurine of a bird in their hand and sculpt it with a modeling tool in their other hand. You can see the sculptor’s scarf. Their hands are covered in clay dust. a macro DSLR image highlighting the texture and craftsmanship.” Image via Google
On top of that, the tool brings advanced text rendering capabilities.
Prompt: “A single comic book panel of a boy and his father on a grassy hill, staring at the sunset. A speech bubble points from the boy's mouth and says: The sun will rise again. Muted, late 1990s coloring style.” Image via Google
Prompt: “A photograph of a stately library entrance with the words ‘Central Library’ carved into the stone.” Image via Google
The tech giant is also tightening the reins on what Imagen 3 can generate. In response to past controversies, the company has implemented stricter safeguards to prevent the creation of offensive or illegal content. Further, Imagen 3 will not generate images of public figures or weapon-related visuals.
In the coming months, Google will build Imagen 2’s more sophisticated features, like inpaiting and outpainting, into the newer Imagen 3.
For now, Imagen 3 is available through Google’s ImageFX tool and Vertex AI for all users residing in the US, with broader accessibility across its other offerings, such as the Gemini text generator, Workspace, and Ads, expected soon.
Prompt: “A weathered, wooden mech robot covered in flowering vines stands peacefully in a field of tall wildflowers, with a small bluebird resting on its outstretched hand. Digital cartoon, with warm colors and soft lines. A large cliff with a waterfall looms behind.” Image via Google
[via Android Central, VentureBeat, PetaPixel, images via Google]