Creeza

Generate sits in the graph as a processor like any other, with Run and Done in the same Action strip every patch uses. When Apple's Image Playground finishes, the sheet closes itself instead of waiting for a click, the preview hinge places itself to suit the shape of what came back, and the Quality knob is hidden on the models that ignore it rather than pretending to matter.

A lot of it runs on your Mac with Apple's own models: no key, no account, no Creeza credits. When you want a particular look or voice, the same patch in Pro reaches out to OpenAI, Gemini, Stability or ElevenLabs, so switching provider is one connection rather than a rebuild.

Auto-confirm reads the Image Playground sheet through the same accessibility tree VoiceOver reads, and only fires when the patch's Done output is actually wired, so it never steals a click you meant to make. Provider action buttons fade in on hover or selection, so a resting patch is just its content, and the preview/inline toggle moved out of the header into the info popover where it reads as a setting rather than a mystery glyph.

Several attempts can live side by side. Keep four versions in one place, flip between them, and the layout updates around whichever one you're looking at.

No card entry, no billing portal, no per-service API keys to manage for the routes credits cover. Apple Cloud sits outside all of this: it's Apple's quota, subject to availability and entitlement, not Creeza spending.

Behind it is real infrastructure rather than a mock: a Postgres-backed service with per-host TLS, and balance totals reconciled against the database.

That description is just a value, so it can caption the image, feed the next prompt, or decide which of three layouts an asset belongs in. Point it at a folder and the same graph sorts and re-lays every file in it.

Extract pulls the words out of a screenshot or a photo, which makes real content easy to get at when all you have is a picture of it.

It runs on your Mac, so you can throw a hundred images at it without a bill, even if each one takes a moment.

Body takes the same inputs, images, video or a live Camera stream, and picks one detection mode at a time: rectangles for bodies, landmarks and available angles for faces, joints and pinch data for hands. Wire a pinch into a value, or a face position into a layout. These are detections and temporary tracks, not identity recognition. Markup goes the other way: scribble over an object and Mask uses the drawing as guidance for a clean cutout that keeps the source pixels intact (macOS 27, with an initial Apple model download). Canvas drawing is different again: pen, highlighter, shapes and arrows that annotate the graph, saved with the document but never rendered into the artboard.

When a request doesn't match anything in the library, the picker falls back to Ask Creeza: same Vision path, reasoning over what's actually on the canvas rather than a keyword guess, so it can match you to a patch, or invent a new one on the spot.

Cropping is now just resizing. Drag an image patch's corner and the output reframes to exactly what the preview shows you, on generated images and on photos you dropped in, so reframing is a drag rather than a trip to another app.

Effects chain and stack, and a chain you like becomes a component with only the knobs you care about exposed. Point it at every variant instead of repeating the same treatment by hand.

Any control can be handed to something else: a beat, a head turn, a slider, a playhead. Glitch on the downbeat, colour draining as a scene ends, a mask tightening as someone leans in.

Nothing is baked in. Change the source image weeks later and the whole treatment re-runs on it.

The crop reads its source from the patch's own preview assets rather than an input port, so it composes with whatever produced the image. Cells clip content at the cell's final frame, which is what makes the preview an honest promise of the output.

Refinement is careful about your cables. Compatible changes keep patch and port identities, values and connections; a change that would remove a connected port is previewed first and can be undone. AI designs the effect once; after that it runs locally, and no model is called when you turn a knob. Custom Metal effects render images to PNG, not a live camera or video shader pipeline, and Filter recipes don't yet execute inside CreezaKit exports.

The View was merged onto the same Consumer template every other patch uses, which is why it now resizes, reorders and reveals its chrome like its siblings: one set of behaviours instead of a bespoke copy. Colour, Fill and Corners knobs went away, because the layers themselves already control those, and a crop of phantom knob dots that were swallowing clicks on the real ones went with them.

Because every asset arrives from the graph, rearranging is cheap: nudge an image and the version behind it follows, swap the source and the composition survives.

Even Apple Maps is a layer now, not an app. The map renders in the composition and resizes like anything else, and latitude and longitude are just ports, so a language model extracting a place from text, a slider or a beat can fly the camera. It's MapKit on the same patch template as every other visual, which is why it composes instead of being a special case.

Comments sit on the canvas next to it all, and they hold pictures rather than just words, so the reasoning for a choice lives beside the choice.

Touch groups content into a region that emits Down and Tap. Scroll supports continuous, freeform and snapping movement; Collection publishes the chosen media; Tab View (Pro) switches between media and text panes. A wired selection or offset can take ownership from manual interaction. On iOS, a View with exactly one Tab Bar becomes a native tab controller and the Status Bar shows real device values; the rest of the composition keeps its authored geometry rather than reflowing. Tab View and Tab Bar are different patches.