This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
autosomal.ai
A free AI face analyzer that learns when you correct it
Upload a selfie or use your camera and autosomal.ai estimates how old you look, which gender the AI reads and which of 14 world regions your face resembles. Free, no sign-up, 16 languages. Tell it where it went wrong and the next version learns from you.
Hey Product Hunt! I'm Romon, and I built autosomal.ai.
Most face analyzers stop at a handful of broad labels, and they're weakest on exactly the people who are underrepresented in their training data. So autosomal.ai compares a face with 14 world regions, from the Horn of Africa and the Caucasus to Central Asia, the Americas and Polynesia, shows a percentage for each, and then asks: "Did we get it right?"
Every answer trains the next version. Recently, a share in Iranian Telegram groups brought in hundreds of people who corrected it, and its accuracy for Iranian faces doubled in a single day. Now I'm doing the same with other communities face AI usually gets wrong.
What's inside:
• Age and gender: MiVOLO v2 plus our own fine-tuned models
• Regions: a CLIP-based model we train ourselves, which keeps improving as people correct it
• Camera, upload or paste a photo, on phone or desktop
• 16 languages, no account, no app
• A share card to compare results with friends
It's meant for fun: a photo shows how someone looks, not their ancestry. Results by ethnic group and community come next, once the models are accurate enough.
I'd love to hear where it got you right, and especially where it didn't.
No comment highlights available yet. Please check back later!
About autosomal.ai on Product Hunt
“A free AI face analyzer that learns when you correct it”
autosomal.ai was submitted on Product Hunt and earned 0 upvotes and 1 comments, placing #330 on the daily leaderboard. Upload a selfie or use your camera and autosomal.ai estimates how old you look, which gender the AI reads and which of 14 world regions your face resembles. Free, no sign-up, 16 languages. Tell it where it went wrong and the next version learns from you.
autosomal.ai was featured in Photography (143.6k followers), Artificial Intelligence (484k followers) and Entertainment (2.1k followers) on Product Hunt. Together, these topics include over 157.8k products, making this a competitive space to launch in.
Who hunted autosomal.ai?
autosomal.ai was hunted by Romon Wafa. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how autosomal.ai stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Hey Product Hunt! I'm Romon, and I built autosomal.ai.
Most face analyzers stop at a handful of broad labels, and they're weakest on exactly the people who are underrepresented in their training data. So autosomal.ai compares a face with 14 world regions, from the Horn of Africa and the Caucasus to Central Asia, the Americas and Polynesia, shows a percentage for each, and then asks: "Did we get it right?"
Every answer trains the next version. Recently, a share in Iranian Telegram groups brought in hundreds of people who corrected it, and its accuracy for Iranian faces doubled in a single day. Now I'm doing the same with other communities face AI usually gets wrong.
What's inside:
• Age and gender: MiVOLO v2 plus our own fine-tuned models
• Regions: a CLIP-based model we train ourselves, which keeps improving as people correct it
• Camera, upload or paste a photo, on phone or desktop
• 16 languages, no account, no app
• A share card to compare results with friends
It's meant for fun: a photo shows how someone looks, not their ancestry. Results by ethnic group and community come next, once the models are accurate enough.
I'd love to hear where it got you right, and especially where it didn't.