Mobile photo-editing app maker Lightricks launches text-to-image generator – TechCrunch

Mobile photo-editing app maker Lightricks is jumping on the AI-generated art bandwagon with its new “Text to Image” generator in its apps, including Photoleap, which is known for its photo-editing capabilities, and Motionleap, an app that can animate a photo photo to make it look like it’s in motion. Starting today, users can now create AI-generated images via text prompts to share with their friends and social media followers.

The new feature is the latest AI development for Lightricks, whose flagship Facetune app is used by many Instagram models to touch up their selfies and alter their waistlines. The Israel-based startup is known for leveraging AI technology to power a range of tools for creative expression. Its other products include apps such as Videoleap, Filtertune, Beatleap, Artleap, Lightleap and Boosted.

With the new “Text to Image” feature, Lightricks is adopting technology that will help users not only edit photos or videos, but also create art by leveraging AI capabilities. A similar feature was recently introduced in TikTok’s mobile app to create video backgrounds.

To use the new feature, click “Generate AI Image” at the top of the app and a text box will appear for you to type in whatever came from your wildest dreams (within reason, as l app does not allow NSFW content). You can also start with pre-written prompts provided, such as “a purple fox, by Van Gogh” or “poodle singing k pop album cover”.

After creating the AI ​​image, users can access editing and animation tools. Photoleap provides tools like overlay, filters, quick art, cutout tools and more. Motionleap has animation tools, a 3D motion tool, as well as overlays and other effects.

In comparison, other AI illustration apps like Dream by WOMBO do not allow users to edit photos.

Picture credits: Lightricks

The company explains that the underlying AI built into Lightricks’ applications is based on open-source code released by Stable Diffusion, a DALL-E 2-like system launched publicly recently.

To use the new feature, a user enters a prompt and the images are sourced from millions of images on the internet from publicly available websites.

“Text to Image” is free and users can upload as many of their AI image creations as they want. The user owns every image created with the generator, says Lightricks. If you sign up for a Pro subscription, you can download up to 100 “premium quality” files per month. The subscription ranges from $4.99 per month with an annual plan to $9.99 per month with a monthly plan.

“AI technology has proven its powerful capabilities in content creation. Implementing Text to Image functionality directly into our apps opens up a whole realm of possibilities for our users, giving them unlimited opportunities for creating amazing content,” said Zeev Farbman, CEO and Co-Founder of Lightricks, in a statement. . “This new tool supports our mission to help users experience the magic of creation and inspire a new generation of content creators.”

AI-generated art, when used ethically, can be a great tool for creators who lack the artistic abilities to physically create their ideas.

Here’s an example of what we found while testing the feature ourselves:

Picture credits: Lauren Forristal/Photoleap

Notice how Nicole Kidman’s face is weathered and looks downright terrifying. This is done to avoid copyright claims. According to Lightricks, its terms of use do not permit copyright infringement. A human-owned photo of an internet celebrity may be copyrightable, but not a work of art created by artificial intelligence. A celebrity’s “likeness” is not copyrighted.

Unlike the more advanced DALL-E and Google Imagen systems, Lightricks’ basic text-to-image generator does not produce photorealistic results, similar to the ambiguous backgrounds created by TikTok’s new AI green screen feature.

NSFW material is a risk with AI art generation systems, but Lightricks uses the Google Cloud Vision API to prevent users from requesting NSFW content. When we tested the image-to-text feature on Photoleap, some text prompts resulted in images of mostly nude and distorted female avatars, but nothing explicit that could be considered pornographic.

We have also typed “Vladimir Putin strip tease” for educational purposes only. Fortunately, the AI ​​generator on Photoleap saved our eyes from burns and generated an artistic image of Putin wearing a suit and tie.

So if you were looking for something light and fun, try Photoleap and Motionleap. Don’t be weird about it.

Photoleap is available only on iOS devices, while Motionleap is on iOS and Android devices. Combined, Photoleap and Motionleap have been downloaded over 170 million times.

Comments are closed.