Show HN: Turn casual photos into professional headshots with AI
9 hours ago (portraify.app)
A while back I needed an ID photo for something urgent. The only way to get one was to find a photo studio, book a time, and wait around for it to be printed, and just one set cost about $13 (converted from my local currency). With how far AI has come, I felt like this should be easier and cheaper by now.
So, I built Portraify. It turns 1–3 casual photos into professional headshots, and also does US passport photos and 1-inch / 2-inch ID photos.
The thing I cared most about was likeness. A headshot or an ID photo is only useful if it actually looks like you, otherwise there's no point. So the AI is tuned to reproduce the real you, no beautifying, no de-aging. It also checks your input photos before generating (lighting, sharpness, face visibility), so you don't waste a generation on a photo that was never going to work.
I know people care a lot about uploading their face to some random AI tool, so to be clear: input photos are processed in memory and discarded after generation. They're never persisted or used for training. Generated portraits are stored so you can re-download them.
One thing to know before you try: it needs a signup (no card) and you get 3 free generations. Let me know if there's anything that could be improved, or anything that doesn't work well in real-world use.
Happy to answer any questions.
The idea is good, but why limit it to a professional headshot?
With approximately the same amount of effort / compute the portrait can be put into a large number of circumstances where people enjoy being portrayed: backpacking in a forest, a night in opera, on a deck of a cruise ship with ocean around, any tourist attraction in the background, etc.
Thanks, that's a good idea, but we're keeping scope narrow for now. It’s tuned for "must look official" rather than "looks cool." We might revisit it later.
I guess everyone can start a business, but this is such a thin LLM wrapper? how do you justify the cost?
[dead]
Fake Passport photo service? I dunno hey. I feel like there's a government department somewhere that just sat bolt upright.
Yup. There have been weekly “headshot AI” generator Show HNs for practically a year at this point.
A non‑insignificant portion of them claim to be suitable for passport photos. Touching up a passport photo in any way (Photoshop or AI) is a brilliant way to get yourself denied a U.S. passport.
From the travel.state.gov [1] rules:
- Submit the original, unedited photo without filters or digital changes.
[1] - https://travel.state.gov/en/passports/apply/help/photos.html
You're right, and appreciate you flagging it. The photo is AI-regenerated, not a crop of the original, not something to submit for an actual passport. Just shipped a disclaimer on that format saying exactly that. Thank you!
I don't know what the policies are around faking/'shopping/enhancing photos for US Passport use, but I do know that there is no "official Passport Photo" service. Generally they will expect you to take and print your own snaps, and attach them on your application. There are a lot of rules around the type and format of photographs that are accepted for this purpose. However, the US Postal Service will take photographs, as an additional service for in-store passport applicants.
I had a strange case for my passport renewal, where they were asking for an updated photo, and I got nicely dressed for my photo and the USPS clerk took it for me, but for some reason the Passport Office rejected it, on quite vague criteria. Then I resubmitted the whole thing verbatim, and it was accepted on the second go. I feel like they just wanted to add some friction to the process.
ummm you know gemini can do this no problem - why would anyone pay for this?
exhibit A i just posted this for lols https://www.linkedin.com/posts/mike-james-3323a245_not-in-a-...
Yeah, agreed, you can get photos out of gemini. But getting one properly sized and not wasting a generation on a bad input photo, that's the annoying part this tool handles for you.
Thank you for the share/post, but I will never these use these void-bloody dark deafening noise of sorrow as LLM/"AI"-generated, sloppery slop... that is based on stolen actual effort and love of now defaced, unknown artists, people, who believed in their art, their message... and now sold and even further damaged each fraction of a second by LLM vendors/enthusiasts, as you, that service...
Not only that, but you, that service, will definitely use the photos, the input/data sent you, to train these sorrowful models though unknown and undisclosed algorithms even deeper and further, spreading bits of someones' lives and effort neglecting privacy and copyright as these do not exist and never existed... inhumanly.
No. Never. I believe in human work, that has a value to cherish, and learn from.
You? You do you.
Why does this read like you've had several strokes in the midst of typing it?