Make / AI & Graphics

Getting a specific image out of a model on purpose — prompt structure, seeds, sampling, composition, reference, fixing hands and faces.

The same person, object or world across many images — character records, reference images, seeds, what actually holds and what drifts.

Running it yourself — our CPU pipeline, your PC, Colab, Modal, bringing your own key. RAM/VRAM, times, quantisation, and what CPU-only genuinely cannot do.

Letterforms, glyphs and symbol systems in graphics — including the ancient writing systems in the Scripts tool, and getting them right rather than decorative.