My Projects¶
Welcome π¶
This is a site collecting often-used strategies, as well as a central meeting place for cooperative work.
The Technology¶
The visual work here was created using ComfyUI, a node-based Stable Diffusion interface to vision models. The vision models are designed for creating images based on a text prompt, or in some cases, another image. This gives me the flexibility to build, test, revise, and refine images as part of the storytelling process.
The text is accompanied by audio files of the narration, recorded for the most part in ElevenLabs, a state-of-the-art Text-To-Speech audio file generator. The audio files are embellished by short clips of the sort of music that provided the emotional atmosphere when I wrote.
The music was created by transcribing notes from musical scores (PDFs) into MuseScore, then rendering and refining the result in Reaper, a digital audio workstation. I only use public-domain or otherwise permissible source material: the musical scores.
Large Language Models are a central part of my creative workflowβnot as a substitute for imagination, but as a demanding collaborator: useful for research, structure, revision, and turning rough language into clean, enjoyable prose.