Fine-tuned Qwen2.5-7B on 100 films for probabilistic story graphs
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 sculpt those branches into a structured screenplay format and export to…
In plain words
CineGraphs is a screenwriting tool that uses a fine-tuned AI model trained on 100 films to help writers explore narrative possibilities. Users input a film concept, and the tool generates branching story paths displayed as an interactive graph. Writers can then refine these branches into structured screenplay format and export to Fountain for use in professional screenwriting software. Designed for filmmakers seeking alternatives to generic AI writing tools, it emphasizes cinematic storytelling structure over formulaic output.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
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 sculpt those branches into a structured screenplay format and export to Fountain for use in professional screenwriting software. Most AI writing tools are trained on generic internet text, which is why they output generic results. I wanted something that understood actual cinematic storytelling—not plot summaries or Wikipedia synopses, but the actual structural DNA of films. So I spent a month curating 100 films I consider high-quality cinema. Not just popular films, but works with distinctive narrative structures: Godard's jump cuts and essay-film digressions, Kurosawa's parallel character arcs, Brakhage's non-linear visual poetry, Tarkovsky's slow-burn temporal structures. The selection was deliberately eclectic because I wanted the model to learn that "story" can mean many things. Getting useful training data from films is harder than it sounds. I built a 1000+ line Python pipeline using Qwen3-VL to analyze each film with subtitles enabled. The pipeline extracts scene-level narrative beats, character relationships and how they evolve, thematic threads, and dialogue patterns. The tricky part was getting Qwen3-VL to understand cinematic structure rather than just summarizing plot. I had to iterate on the prompts extensively to get it to identify things like "this scene functions as a mirror to the opening" or "this character's arc inverts the protagonist's." That took weeks and I'm still not fully satisfied with it, but it's good enough to produce useful training data. From those extractions I generated a 10K example dataset of prompt-to-branching-narrative pairs, then fine-tuned Qwen2.5-7B-Instruct with a LoRA optimized for probabilistic story branching. The LoRA handles the graph generation—exploring possible narrative directions—while the full 7B model generates the actual technical screenplay format when you export. I chose the 7B model because I wanted something that could run affordably at scale while still being capable enough for nuanced generation. The whole thing is served on a single 4090 GPU using vLLM. The frontend uses React Flow for the graph visualization. The key insight was that screenwriting is fundamentally about making choices—what if the character goes left instead of right?—but most writing tools force you into a linear document too early. The graph structure lets you explore multiple paths before committing, which matches how writers actually think in early development. The biggest surprise was how much the film selection mattered. Early versions trained on more mainstream films produced much more formulaic outputs. Adding experimental and international cinema dramatically improved the variety and interestingness of the generations. The model seemed to learn that narrative structure is a design space, not a formula. We've been using it ourselves to break through second-act problems—when you know where you want to end up but can't figure out how to get there. The branching format forces you to think in possibilities rather than committing too early. You can try it at https://cinegraphs.ai/ — no signup required to test it out. You get a full project with up to 50 branches without registering, though you'll need to create an account to save it. Registered users get 3 free projects. I'd love feedback on whether the generation quality feels meaningfully different from generic AI tools, and whether the graph interface adds value or just friction.
Does a similar job
all alternatives →
- IMI made a tiny book using a pen-plotter and AI2025 · muffinman.io · ▲150
Hey HN, I want to share a personal project: I made a tiny pen-plotted book for my wife. I did everything myself—drawings (with some help from Midjourney), plotting, cutting, and binding. I even used a 3D printer to make a helper tool. It's absolutely over-engineered, but I enjoyed it a lot. Multi-disciplinary projects, especially those with a physical output, are a lot of fun for me. The post covers the process in detail, but if you're interested in anything specific, let me know. Cheers!
- IAIllustrative – AI pipeline that turns books into graphic novelsMar 2026 · arv.in · ▲5
I like the idea of taking one thing and turning it into another—very much inspired by NotebookLM and wondered what it might take to generate full graphic novels, with consistent characters, narrative flow, story arc, etc. Developed a 7-pass scripting enrichment system (beat analysis, adaptation filtering, character deep dives) before generating any images. Dual backend: Google Gemini for scripting (2M context window) and either Gemini or OpenAI for image generation with 3-tier model fallback (comparing the performance of both). It's not great. Would love feedback on the pipeline.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
