Hi HN, I'm a computer systems engineering student in Mexico who switched from film school. I built CineGraphs because my filmmaker friends and I kept hitting the same wall—we'd have a vague idea for a film but no structured way to explore where it could go. Every AI writing tool we tried output generic, formulaic slop. I didn't want to build another ChatGPT wrapper, so I went a different route. The idea is simple: you input a rough concept, and the tool generates branching narrative paths visualized as a graph. You can then sculpt those branches into a structured screenplay format and export to Fountain for use in professional screenwriting software. For the training data, I spent a month curating 100 films I consider high-quality cinema—Godard, Kurosawa, Brakhage, and others. I built a 1000+ line extraction pipeline using Qwen3-VL to pull narrative structure, characters, and themes from each film with subtitles enabled. From those extractions I generated a 10K example dataset and fine-tuned Qwen2.5-7B-Instruct with a LoRA optimized for probabilistic story branching. The graph visualization is built with React Flow. We've been using it ourselves to break through second-act problems and explore narrative directions we wouldn't have considered otherwise. The branching format forces you to think in possibilities rather than committing too early. You can try it at https://cinegraphs.ai/ — the free tier gives you 3 projects. Would love feedback on the generation quality and whether the graph interface feels intuitive for your workflow.

Can I ask, did you pull all this from subtitles and scripts?

Quite frankly, the corpus of film criticism might be a better source. Analysis of context, interpretation, intent, result, success, failure, contention might be more useful to shape a story than the literal story itself. It's asking too much of current gen LLMs to be able to synthesize motif at a higher abstraction. In my experience they get stuck on specific examples and crudely stitching pastiche together, instead of working in the blank empty space between thoughts and ideas.

I also am unsure that "describe your opening scene" is the best place to start. I may have a story that has a tangible beginning, middle, end, and want to fix certain elements along the way. "This must happen to start act 3" so the story coherently steers correctly towards goals.

would be nice to see sample conversation shared publicly to understand what it exactly generates. It could be even good for your SEO if you share couple of them