Lightricks, creator of mobile photo-editing apps, is jumping on the ai-generated art wave, using new“Text-to-image” generators in its apps, including Photoleap and Motionleap, known for their photo-editing capabilities, the latter is an application that animates a still photograph to make it look like it is in motion. Starting today, users can now create ai-generated images from text prompts to share with their friends and social media fans.
The new feature is the latest AI development from Lightricks, whose flagship Facetune app is used by many Instagram models to retouch selfies and alter waist lines. The israeli-based start-up is known for using artificial intelligence to power a range of creative expression tools. Other products include applications like Videoleap, Filtertune, Beatleap, Artleap, Lightleap, and Boosted.
With its new“Text to image” feature, Lightricks’s technology will help users create art not just by editing photos or videos, but by harnessing the power of artificial intelligence. Recently, TikTok introduced a similar feature in its mobile application to create video backgrounds.
To use the new feature, click“Generate AI image” at the top of the application, a text box will appear, for you to enter any of your wildest dreams (within reason, since the application does not allow NSFW content) . You can also start with pre-written hints such as “A purple Fox, by Vincent van Gogh” or “Singing poodle K pop album covers”.
After creating an AI image, users can access editing and animation tools. Tools provided by Photoleap include layering, filters, quick art, cropping tools, and more. Motion Leap has animation tools, 3D motion tools, and overlay and other effects.
In contrast, other AI artwork applications, such as Wombo’s Dream, do not allow users to edit photos.
The company explains that the underlying artificial intelligence integrated into Lightricks’s app is based on stable diffusion’s open-source release of DALL-E 2, a recently unveiled system similar to the DALL-E 2.
To use the new feature, a user is prompted for a picture from one million publicly available web site on the Internet.
“Text to image” is free to use, users can download their own need to create AI images. Lightricks says that users have access to every image created with the generator. If you sign up for professional membership, you can download up to 100“Higher quality” files per month. Subscription fees range from $4.99 per month for an annual plan to $9.99 per month for a monthly plan.
“In terms of content creation, AI technology has proven its powerful capabilities,” Lightricks CEO and co-founder Zeev Farbman said in a statement. “Implementing the ‘text to image’ feature directly in our app, opens up an entire realm of possibilities for our users, “This new tool supports our mission to help users enjoy the magic of creating content and inspire a new generation of content creators.”.
Artificial intelligence-generated art, if used in an ethical manner, can be a great tool for artists who have no artistic ability to actually create their ideas.
Here’s an example we came up with when we tested this feature ourselves.
Notice how Nicole Kidman’s face has been altered to look frankly horrible. This was done to avoid copyright claims. According to Lightricks, its terms of use do not allow copyright infringement. Human-owned photos of celebrities from the Internet can be copyrighted, but ai-created art can not. Celebrity“Portraits” are not copyrighted.
Unlike more advanced systems like DALL-E and Google Imagen, Lightricks’s basic text-to-image generator doesn’t produce realistic results, similar to the blurry background created by Tiktok’s new AI green screen feature.
NSFW materials are a risk to the AI art-generation system, but Lightricks uses Google’s Cloud Vision API to prevent users from requesting NSFW content. When we tested the image-to-text feature on Photoleap, some of the text prompts turned out to be mostly nude, distorted images of women’s heads, but nothing explicit that could be considered pornographic.