I tested out my Sampler prototype by converting highlights on a printout into a digital collage and recorded a video documenting the process.

The setup

The result

Starting to enjoy the feel of this.

Experimenting with putting controls and info on the canvas - with some reciprocal scaling to make it more readable. Needs some more finesse but interesting so far.

Different keys to peel off snapshots or videos. Trying to think of the least obtrusive but clear way to show mark what is a video vs what is an image.

Been thinking about the fact that the 'peel' clone interaction goes all the way back to MacPaint.

More crop and pan experiments

Prompting to transcribe and summarize my tabletop notes. Real question is where do I put these for single source of truth - I think a database, maybe I use the s3 image key as the id? That should be unique and could come in handy, thought it may also limit uses for non-s3 images...

New on constraint.systems: Image Paint

Image pixels are copied and pasted in the direction you click and drag. An attempt to make something tactile like paint, but that "goes with the grain" of its digital nature.

Image paint experiment coming into focus.

I recorded a workspace tour https://www.youtube.com/watch?v=kRhAWA8zBa0. Featuring computers, cameras, and lots of storage bins.

Starting to add layers to the scrape experiment.

I got something more like a displacement effect working, but I don't like the feel of the kind of smooth circle erase versus the crunchiness of everything else. Think I'm going to cut it.

A nano-banana canvas experiment. Generating based on a source image and the overlapping prompts, caching the results. Like adding semantic layers to an image.

Caching by combined image and prompt works well, but doesn't fully solve the order issue of:

Not quite the effect I'm after. But enjoying the stops along the way.