AI wants to up your selfie game

The Future. AI art platforms are graduating from cool and controversial developer tools to cool and controversial selfie filters that anyone can use. Considering how amazing the recreated selfies look by platforms like DrawAnyone and Facetune, expect mass adoption… and mass litigation by artists looking to earn royalties from the platforms’ success.

Filter update
Selfies are about to get a lot more creative, according to The Verge.

• Web tool DrawAnyone allows users to “upload some selfies, let the system process your likeness, and then pick an output style for your new portrait,” which includes preset styles like “occult,” “soldier,” “royal,” and “Studio Ghibli.”
• And a new feature in Facetune — king of selfie-editing — does a similar function, albeit with a “more cartoonish” output than DrawAnyone.

Both tools use the open-source Stable Diffusion generator to create their images, with both companies stressing that the uploaded selfies are only used to create the edited selfies.

The word behind the image
What makes Facetune’s feature, in particular, stand out is that the output shows you what exact text prompt is used to create your new selfie… and some of the prompts are wildly specific, including:

• “Intricate color portrait of me in the style of Tom Bagshaw, soft smooth skin, 8k Octane beautifully detailed render.”
• “Me as a gorgeous princess, professionally retouched, muted colors, soft lighting, realistic, smooth face, full body shot, torso, dress, perfect eyes, sharp focus on eyes, 8k, high definition, insanely detailed, intricate, elegant, art by J. Scott Campbell and Artgerm.”

As The Verge notes, the fact that Facetune points out specific artists to base their outputs on may be smoking gun evidence of how these platforms specifically mimic their style.

Prepare for that to be included in some lawsuits in the near future.