#Vision
4 posts- 3 min
Harder to read than a card — a table splits into two lines
A receipt's line items run name on the left, amount on the right. To the human eye, it's clearly one row. But text recognition sometimes returned that name and amount as separate fragments. What looked like one row split into two — and that "table" was the part of this app I struggled with most.
- 4 min
The iPhone turns a face into a drawing — Vision finds it, Apple Intelligence draws it
Last time I wrote that STIL.TOON redraws a face rather than erasing it. So how does it find the face, and how does it draw it? Vision finds it; Apple Intelligence draws it. And the first place I tripped was calling the tool the way I assumed it worked, instead of the way it actually did.
- 3 min
Past the AI cutoff line — making it run on every iPhone
Reading a scanned card and sorting it into name, company, and the rest — that part runs on Apple Intelligence. But that AI only works on newer iPhones. At first I thought, "then make it an app for supported devices only." But cutting along that line left too many people out. So I decided to deliver the same experience to the side where the AI doesn't run.
- 4 min
The background that doubled — cutting out a face with only Apple's public APIs
Turning a face into a drawing — that part worked. The problem was putting the drawing back onto the photo: only the face swapped, the background and clothes left as they were. It didn't come easily. The background doubled, I hit two dead ends, and still cut my way through with only Apple's public APIs — the record of one day.