Show HN: An app that logs your meal's calories from a photo

Posted by behzodhalil 2 days ago

Comments

Comment by levi840714 2 days ago

What do you do about portion size, and the calories a photo can't see like oil or dressing? Those are the parts that have always made me distrust the number these apps spit out. Curious how you're handling it. Only looked at the landing page so far.

Comment by adammarples 2 days ago

I'm going to safely assume that everything is hallucinated

Comment by behzodhalil 2 days ago

Fair prior. That's exactly why every number is editable - I treat the model as a quick draft, not a source of truth.

Comment by behzodhalil 2 days ago

Yeah, this is exactly the part I distrusted in other apps too.

So I didn't try to fake it. The model guesses the portion, then you adjust the grams with a slider and the macros rescale live - same "you can always correct it" idea from the post.

Oil and dressing the camera just can't see. That's the honest gap: right now it doesn't add them, so if you know it was cooked in oil, you nudge it up. Rather be approximate and honest than confidently wrong.

Where do the numbers feel most off for you? That's the edge case I want.

Comment by astaka 2 days ago

Some other similar apps do the same thing but it's hard to provdie right and accruate inforation just based on photos by using LLM & OCR. any special design you did in this app?

Comment by behzodhalil 2 days ago

No OCR actually - just a vision model doing the recognition, one prompt, JSON out (Qwen3.6-27B on Groq).

I didn't chase some clever accuracy trick, because like you said, a photo alone can only get you so far. The design bet was different: make it fast and make every number editable, so the friction stays low and you fix the guess instead of trusting it.

It nails simple plates and gets confused by messy/mixed ones — that's the part I'm still working on.

Comment by sifarhub_com 2 days ago

the app looks same or similar to fitness apps. As myself I found the apps difficult in managing while doing exercises because you have to constantly do this in phone. I prefer not to .So build something where it would not require manual efforts or minimum manual effort.

Comment by behzodhalil 2 days ago

Fair - I hate touching the phone between sets too. Right now the app keeps it minimal: photo for meals, quick-tap for workouts. But "zero effort while exercising" is the direction. What would work best for you - logging the whole workout once at the end, or voice/watch input mid-session? Asking because this decides what I build next.

Comment by sifarhub_com 1 day ago

watch would be great because it would have notification about rest time is over and when to start next exercise . Voice would not be possible because of lots of noses in gyn.fitness centre.

Comment by interfeco 2 days ago

looks like even the apple logo in the appstore button is vibecoded.

Comment by behzodhalil 2 days ago

Ha, that one's on me, not the AI - I made it in Canva myself. Apparently I vibecode by hand too.

Comment by xingped 2 days ago

sigh will you nerds please stop trying to make this app idea happen, it doesn't work.

Comment by behzodhalil 1 day ago

Maybe the idea doesn't work. Maybe no one has executed it well enough yet.

Comment by xingped 1 day ago

The problem is that A. A photo has no depth information to tell you the actual size of something, B. A photo cannot tell you what is behind something else so you can't see what's hidden, and C. Most importantly, when you're done cooking, a lot of ingredients in a food are "invisible" such as milk, butter, sugar, etc. and no camera or fancy AI can tell you what was used to make a food.

There is no "no one has executed it well enough" here. Every single attempt at this app idea has these exact same limitations. This not the same as a bird or plant identification app.

So many people have tried this exact same app. Good job making something, but I'm trying to save you a lot of wasted effort.

Comment by kingleopold 2 days ago

another BS apps after 100 made the same thing. maybe 1000 made before

Comment by kotaKat 2 days ago

What was the phrase in the Apple developer guidelines?

"Certain kinds of apps, such as dating, flashlight, sound effects, wallpaper, simple timers, and fortune telling, are well established on the App Store and we will not accept new submissions unless they offer a meaningfully different or improved experience"

Arguably, this isn't a meaningfully different or improved experience (it's the same boring thing as every other photo-as-calorie-counter-that-never-works-right, unless you count them adding monetization through a 'premium' subscription as a meaningfully different experience), so Apple should have just tossed it from the platform.

Comment by behzodhalil 2 days ago

you're right that it's never accurate. neither are we though - people under-report their own intake by 20–40% in actual studies. the photo just has to beat "didn't log anything", and it does.

Comment by behzodhalil 2 days ago

Crowded means unsolved, not worthless

Comment by behzodhalil 2 days ago

Hi, HN I kept giving up on calorie tracking because trying in every meal was too much work. So I tried building something where I just take a photo and it estimates what’s on the plate. It’s honestly not perfect - it does well with simple meals and gets confused by messy or mixed plates, so you can always correct it. But for me it lowered the friction enough that I actually kept logging.

Under the hood it’s a vision model for the food recognition, wrapped in Kotlin Multiplatform (iOS and Android) with a small Ktor backed.

I’d love feedback - especially where the recognition fails for you, so I can see the real edge cases. Thanks for checking it out.