A whole lot of new people have joined, so let's have an onboarding thread. Hi, we're Prisma Labs, the company that brought you Prisma and Lensa apps, both designed for photo editing and powered by AI.

Owners of Windows OS devices, check out the link! https://t.co/IAdEMxQ0rq

If you’re in the US, type https://t.co/VgfOyca7ql in your browser to try out the web version. Stay tuned for access in other regions!

Lensa Magic Avatars are reaching far and beyond 🎉 Prisma Labs teamed up with @MicrosoftStore to bring the avatar experience to the web and Windows OS devices.

"Cherry-picking how we want to present ourselves online is not a new act. But with these portraits, we are giving everyone something more intimate: the aspirational version of ourselves."

Prisma Labs, maker of Lensa AI, says it is working to prevent accidental generation of nudes https://t.co/57OPiW43dv by @Haje

We also believe that the growing accessibility of AI-powered tools would only make man-made art in its creative excellence more valued and appreciated, since any industrialization brings more value to handcrafted works.

To sum up,AI produces unique images based on the principles derived from data, but it can't ideate and imagine things on its own. As cinema didn't kill theater and accounting software hasn't eradicated the profession, AI won't replace artists but can become a great assisting tool

As soon as the avatars are generated, the user's photos and the associated model are erased permanently from our servers. And the process would start over again for the next request.

It takes at least 10 minutes for the machine to make approx. 120 million billion (yes, it's not a typo) mathematical operations every time, meaning we have a separate model for each user, not a one-size-fits-all monstrous neural network trained to reproduce any face.

Lensa uses a copy of the Stable Diffusion model that, by default, generates a random person if one is mentioned in the prompt. To personalize the output images in each particular case, we need 10-20 pictures uploaded to re-train the copy of the model.

The AI learns to recognize the connections between the images and their descriptions, not the artworks. This way the model develops operational principles that can be applied to content generation. Hence the outputs can't be described as exact replicas of any particular artwork

Whilst both humans and AI learn about artistic styles in semi-similar ways, there are some fundamental differences: AI is capable of rapidly analyzing and learning from large sets of data, but it does not have the same level of attention and appreciation for art as a human being

Seeing plenty of thoughts online about the future of digital art in connection with AI generations, we decided to share some information on how AI generates images and why it will not replace digital artists. 🧵🧵🧵

Lensa AI climbs the App Store charts as its 'magic avatars' go viral https://t.co/POMdUnIcXv by @asilbwrites

I ain’t think I could get more young, rich & handsome, but Lensa’s Ai really accomplished the impossible 🤣

These AI photos generated by @PrismaAI are kinda crazy 😳🔥

Since we introduced our AI-generated avatars here, the hype has gone over the roof. Among the first and most voted names of whom we should do next, you named Casey Neistat. So we've braced ourselves, prepared more bandwidth on servers, and are happy to show @Casey as seen by AI

Portraits of me generated by @PrismaAI

The feature is available on iOS only and for devices with at least 4GB RAM, meaning iPhone 11 and the later devices. It is offered in a package with an annual subscription to Lensa’s photo and video editing tools and offers a 50% discount on AI-Avatars.

More so, the avatars are stored in-app in the smaller versions. They only reach the average of 1.5-2 MB when you tap “Save” and bring them to your Camera Roll.