Mysterious AI Image Generator More Powerful Than Midjourney Breaks Cover

3 weeks ago 7
A young woman with a backpack is smiling and taking a photograph with a DSLR camera outdoors. She's wearing a gray hoodie and has her hair tied up in a bun. The background is a blurred landscape.Example from Recraft V3.

A mysterious AI image generator that beats all other models in benchmark tests has revealed itself. Initially known as “red_panda”, it is actually called Recraft.

Earlier this week, talk of a powerful AI image generator topping the Artificial Analysis’ Text-to-Image Model Leaderboard — a ranking platform that compares leading text-to-image models based on human preference — had people wondering who or what was behind the model known only as red_panda.

PetaPixel almost reported on it but didn’t due to lack of information. Now Recraft AI, a London-based AI design platform headed by Anna Veronika Dorogush, has claimed responsibility for red_panda. “Nice to meet you!” The company writes on X. “We are red_panda, but for friends just Recraft.”

 A woman walking alone on a dimly lit, rain-soaked street at night, wearing a coat and boots.The ‘Hard Flash’ style, left, and ‘Photorealism’ style, right.

At the start of the year, it was reported that Recraft had raised $12 million from venture capital investors.

“Introducing Recraft V3 — a revolutionary AI model that thinks in design language. It delivers unprecedented quality in text generation, outperforming models from Midjourney, OpenAI, and others,” Recraft writes on X.

“It’s more than an image generator, it’s a powerful tool with enhanced text placement, style control, and the highest quality standards in the industry.”

Recraft says it has “set a new standard for excellence in image generation” and that it is the only model that can generate long texts on an image. It also stresses that Recraft is built for graphic designers and has the ability for users to “control text size and placement to create detailed, professional-quality visuals” which it says is “perfect for branding, marketing, and complex graphic layouts.”

A person stands holding a large sign that reads, "Photography will forever be the greatest art form. Nothing can change my mind." They appear to be outdoors near a building.Racecraft says it has the longest text generation capabilities of any model.

It also allows users to use different styles as an input. If a brand or company wants to create a set of homogenous images in a particular style then users can “refine the style candidate until it matches the exact look and feel needed.”

Recraft V3 has a background removal tool, a Generative Fill-like tool, an outpainting tool, a mockup tool, a vectorize tool, an upscaler tool, as well of course as a comprehensive AI image generator that is available in different styles including “photorealism”, “studio photo”, “HDR”, “Hard flash”, and “black and white”.

In its experiments, PetaPixel found recraft to be reasonably dexterous — even placing fingers in the right place of an image of a photographer holding a camera.

A woman wearing a cap and scarf is outdoors, smiling while taking a photo with a digital camera. She has a backpack on and is standing in a natural landscape with blurred hills in the background.‘A female photographer holding her camera up.’
A confident woman in a business suit stands in focus, smiling, with two blurred colleagues in the background, all in professional attire, in an office setting with warm lighting.‘A headshot of a young professional.’
Two children play hockey on a frozen pond, wearing helmets and skates. One is ready to shoot a puck towards the net, while the other guards it. Snow-covered trees and a few distant skaters are in the background, capturing a winter scene.‘Kids playing hockey on a pond.’

There is a free version where users get 50 free credits daily. Then there are Basic ($10), Advanced ($27), and Pro ($48) packages. You can use Recraft now by visiting its website and there is also an app on iOS and Android.

Read Entire Article