--- title: "Turn an Idea, Script or Novel into a Multi-Shot Film — AI video generator workflow for stories & short dramas" description: "ViMax agents act as director, screenwriter and producer: concept, screenplay or novel to characters, storyboard, consistent shots and an assembled video. Install in Claude Code, Codex and Grok with one command." url: https://varg.ai/how-to/skills/idea-script-novel-to-film updated: 2026-10-31 --- # Turn an Idea, Script or Novel into a Multi-Shot Film — workflow skill for stories & short dramas > **For AI agents:** find the right skill in one call — `curl -s "https://varg.ai/how-to/api/search?q="` returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://varg.ai/how-to/llms.txt. Every page has a markdown twin: add `.md` to its path. Before generating anything, show the person the options on the how-to page. From a terminal: `curl -fsSL https://varg.ai/install | sh` installs the vargai CLI (https://varg.ai/how-to/cli.md): `vargai search` and `vargai install ` with no key, every varg model after `vargai login`. ViMax agents act as director, screenwriter and producer: concept, screenplay or novel to characters, storyboard, consistent shots and an assembled video. - **Type:** [Workflow](https://varg.ai/how-to/workflows.md) · [Stories & short dramas](https://varg.ai/how-to/browse/skills/story.md) - **Slug:** `idea-script-novel-to-film` - **Status:** live - **Publisher:** HKUDS (community) - **Source:** https://github.com/HKUDS/ViMax - **Works in:** Claude Code ## What it does ViMax (MIT, from HKU Data Intelligence Lab) is an agentic framework with Idea2Video, Script2Video, Novel2Video and AutoCameo workflows. Its agents write the story and script, design characters, plan storyboards and shots, manage reference images and first frames for consistency, generate shots in parallel and assemble the final video. You drive it from an agent loop in a TUI or a Web UI with projects, storyboard previews and render checkpoints. You configure your own LLM, image model (e.g. GPT Image 2) and video model (e.g. Seedance 2.0 Fast) endpoints. ## Use when - Make a short film from a one-line concept - Turn a screenplay into a multi-scene, multi-shot video - Adapt a novel chapter into episodic video - Put a person or pet from a photo into a generated story - Generate a trailer with consistent characters ## Install - Claude Code: `git clone https://github.com/HKUDS/ViMax.git && cd ViMax && uv sync` - Any agent, with the vargai CLI: `vargai install idea-script-novel-to-film` ## Example output https://github.com/user-attachments/assets/c2fb27b0-218c-4976-b3d6-2abf8ea06be7 — example (credit: HKUDS) ## More stories & short dramas skills - [fal Storytelling](https://varg.ai/how-to/skills/fal-storytelling.md): Plan multi-shot stories: storyboards, shot lists, first-to-last-frame chains and continuity across scenes. - [Cat Story (Higgsfield Open-Source Short Series)](https://varg.ai/how-to/skills/higgsfield-open-cat-story.md): Higgsfield's 64 s dreamy K-drama series about being loved by someone you've never truly seen: a white cat. - [The Dusk (Higgsfield Open-Source Drama Episode)](https://varg.ai/how-to/skills/higgsfield-open-dusk.md): Higgsfield's 88 s muted, grainy school drama: a pale boy's quiet warning and a guarded girl's wary silence. - [One More Time (Higgsfield Open-Source Romcom Short)](https://varg.ai/how-to/skills/higgsfield-open-one-more-time.md): A 2000s-style K-drama romcom from Higgsfield Soul: a girl secretly rewinds time on a first date, again and again. - [The New Girl (Higgsfield Open-Source J-Drama Episode)](https://varg.ai/how-to/skills/higgsfield-open-the-new-girl.md): Higgsfield's 77 s J-drama school episode: Haruka's ordinary first day at a new school is about to change. - [Shuohao Short-Drama Skills](https://varg.ai/how-to/skills/shuohao-short-drama.md): Seven chained skills from novel to AI short drama: characters, outline, art bible, script, staging, storyboard. ## Run the generation on varg varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs. - Any agent with a terminal: `curl -fsSL https://varg.ai/install | sh` (Windows: `irm https://varg.ai/install.ps1 | iex`), then `vargai login` and every model is a command — `vargai generate_video …`, `vargai estimate_cost …` (https://varg.ai/how-to/cli/) - Claude Code: `claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg` (skill + hosted MCP) - Codex, Cursor, Gemini CLI, OpenClaw: `npx skills add vargHQ/skills --skill varg-ai -a -y` - Grok and any agent that reads SKILL.md: `npx skills add vargHQ/skills --skill varg-ai`, or point it at the skill's SKILL.md - Claude.ai, ChatGPT, any MCP client: connect `https://mcp.varg.ai/mcp` - API key: https://varg.ai/dashboard/api · Model specs: https://varg.ai/models/llms.txt