Miedocuentista: local AI turns photo sequences into horror stories, scripts and novels

Miedocuentista is an open-source tool that runs entirely on a personal laptop and generates stories from a sequence of images. A small vision model describes each photo, which the user can edit, and a language model writes the next scene while a rolling story memory keeps characters and plot threads consistent. After the last image, a final editor pass reviews the full narrative to fix plot holes and timeline issues. The output can be a short film script, a film story, or a novel with one chapter per image, and the project is built for the Hacktoberfest Open-Source AI Challenge. Its creator plans to later connect the structured script output to open-source video and speech tools, though that step is not yet implemented.
This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)
Log in to join the discussion and vote.
Log in