Hi, I’m Kenan.

Two years of diffusion research. The first thing it made was a gift for my father.

Weights in one service, the interface in another, datasets in a third. Each one a login, a bill and a format. Making the thing is the smallest part of the day.

Two families of video model that genuinely differ. Rather than one panel with half its controls quietly inert, the composer is rebuilt from what the chosen model says it reads. Change the model, or change the medium on the chip inside the field — the prompt survives both.

A control that is present but ignored is worse than one that is absent — it is the interface making a promise the model will not keep. Below, the real bar in the deployed app.

Not in the trainer. A caption set that repeats itself teaches the repetition, and you find that out eight hours and a GPU bill later. So the dataset screen counts what the trainer is actually going to read.

80 of 80 carry the trigger word, 80 of 80 are captioned, median seventy words. The list on the right is every clause appearing more than once — even lighting five times, with soft five times. That is the overfitting warning, delivered before the run instead of after it.

Captions are written by a vision model as prose, not tags, because the text encoders these models use parse grammar.

The decisions that matter most leave no trace. There is no video mode to enter, no project type to choose at the start, and nothing announcing that two systems were joined — one canvas, one prompt, one gallery. Done properly it is unremarkable, which is why it has to be claimed here and nowhere in the product.

The switch lives inside the prompt field rather than in the chrome, because which one you get is a property of what you're making, not an address you navigate to. What differs between them is only the options. The canvas holds the screen either way — options sit in a bar under the picture, never a rail beside it, since a settings column costs the image 384 pixels of the one dimension it cannot get back.

Where this goes once the models are fast enough: a gesture-driven canvas for iPad. Nothing is labelled and everything is live — you touch her face to change her. What the machine invented is marked differently from what you actually said, and rerolling it costs nothing.

Speculative, and deliberately labelled as such. What makes it a design rather than a mood board is the list underneath it.

Eleven sentences, each written to kill a specific thing when the cheap fix gets proposed. If a sentence has never vetoed anything, it isn't earning its place — cut it.

The failure to guard against isn't the model, or latency, or scope. It's month four, when something doesn't fit cleanly and the cheapest fix is a panel.

Scale here isn't requests per second. It's dataset size, model size and cost per job — so the decisions that matter are about what runs where.

The work I’m proudest of here is the work nobody will notice — two systems joined so completely that no one thinks to ask when they were separate. Good design is unobtrusive — Dieter Rams. Underneath sit three words that settle the arguments, in priority order when they conflict.

The geometry responds to you. There is nothing to operate.