waoowaoo AI Film Studio
A self-hosted production tool that turns novel text into storyboards, assets, voice tracks, and short-form video.
- Source repo
- waooAI/waoowaoo
- Stars
- ★ 15k
- Last updated
- 1mo ago
- License
- NOASSERTION
- Primary language
- TypeScript
- FA score
- Insufficient evidence
At a glance
- How it runs
- Works with
- Portable with changes
- Cost
- Free software; you pay for model usage
- Setup effort
- Medium · a few setup steps
- You'll need
- Typical use
- A short-drama creator wants to break a novel draft into character, scene, and plot elements before production.
- Not a fit if
- Teams needing a stable production release; this is a preview with known bugs
- Teams expecting external PRs to be merged; the core team implements changes internally
- Source review
- Insufficient evidence 8 safety controls not found
What does this agent do, and when should you use it?
waoowaoo AI Film Studio is an AI-assisted tool for producing short dramas and comic-style videos from novel text. Its documented workflow covers script analysis, character and scene image generation, storyboard creation and video compositing, plus multi-character voice synthesis. The application is built with Next.js 15 and React 19, stores data in MySQL through Prisma ORM, and uses Redis with BullMQ for queued work. It can run through Docker Compose or in a local development setup, served at http://localhost:13000 for container deployments and http://localhost:3000 for development. Adoption should account for its early beta status, frequent updates, and documented database incompatibility between versions.
The tool processes novel text through “AI script analysis” to extract characters, scenes, and plot information. It then generates consistent character and scene images, automatically creates shots/storyboards and composites them into video, with multi-character speech synthesis available for voice work. The interface is delivered by a Next.js 15 + React 19 application; MySQL is accessed through Prisma ORM, while Redis + BullMQ handle queued tasks. A full deployment starts with docker compose up -d; local development requires copying .env.example to .env, supplying an AI API Key, starting mysql redis minio, running npx prisma db push, and then running npm run dev. After startup, users configure AI-service API keys in the Settings Center before using the workflow.
- A short-drama creator wants to break a novel draft into character, scene, and plot elements before production.
- A comic-video producer needs to generate character and scene images from text, then continue into storyboard video production.
- A small film-production team wants one workflow for storyboard generation, video compositing, and multi-character voice synthesis.
- A technically capable creator with Docker Desktop wants to run the production tool locally and configure their own AI-service credentials.
- A content producer needs a Chinese or English interface and can switch languages from the upper-right UI control.
How do you install or deploy this agent?
For the quickest deployment, install Docker Desktop and run:
curl -O https://raw.githubusercontent.com/saturndec/waoowaoo/main/docker-compose.yml
docker compose up -dThen open http://localhost:13000. For local development, run:
git clone https://github.com/saturndec/waoowaoo.git
cd waoowaoo
cp .env.example .envBefore npm install, edit .env and add an AI API Key. Then run npm install, docker compose up mysql redis minio -d, npx prisma db push, and npm run dev. The development server is available at http://localhost:3000.
How do you use this agent?
Open the applicable local URL after startup. In the Settings Center, configure official AI-service API keys using the included guidance; the README says third-party OpenAI Compatible formats are not yet complete. Submit novel text for AI script analysis, then proceed through character and scene image generation, storyboard video creation, and multi-character voice synthesis. Container startup initializes the database automatically. In local development, npx prisma db push is mandatory before starting the app or the tasks table will be missing.
What are this agent's strengths and limitations?
- It documents a continuous production path from novel-text analysis through storyboards, video compositing, and multi-character voice synthesis.
- Docker Compose provides a prebuilt-image deployment route that does not require cloning the repository first.
- Its implementation stack is explicit: Next.js 15, React 19, MySQL, Prisma ORM, Redis, BullMQ, and Tailwind CSS v4.
- It offers both a container deployment path and a debuggable local-development workflow with explicit database initialization.
- The project is explicitly described as an early beta with known bugs and incomplete areas.
- Database versions are incompatible; the documented upgrade procedure runs docker compose down -v, creating a migration and data-loss risk.
- An AI-service API key is required before content generation, and official provider APIs are currently recommended.
- Third-party OpenAI Compatible support is described as incomplete, so compatible-endpoint integrations may require further work or later releases.
How does this agent compare with similar options?
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| waoowaoo AI Film Studio This agent | Insufficient evidence | Self-hosted serviceFree + model costs | ★ 15k | 1mo ago | TypeScript | — |
| OpenMontage Drama Studio | 47 · Major gaps | Self-hosted serviceFree + model costs | ★ 22 | 2d ago | Python | — |
| ArcReel Video Creation Workspace | 52 · Major gaps | Self-hosted serviceFree + model costs | ★ 6.2k | today | Python | OpenAI API · Claude API |
| MicroDrama AI Generator | 43 · Major gaps | Web appFree + model costs | ★ 568 | 3mo ago | Python | — |
How does FollowAgents rate this agent?
Why each dimension lost points
Insufficient evidence: no permission model, user confirmation mechanism, data flow transparency, sensitive data handling policy, dependency security audit, external effects description, rollback mechanism, or source attribution. All trust criteria lack evidence, hence 0.
Insufficient evidence: no self-consistency statement, dependency availability guarantee, or failure message design. Test files exist but no execution results, and static review cannot verify reliability. Hence 0.
Insufficient evidence: no clear target audience and scenarios, no capability boundaries, no trigger precision description, no environment fit explanation. Hence 0.
Insufficient evidence: unclear information architecture, install notes present but unverified, naming stability not stated, no examples/FAQ, no known limitations, license is CC BY-NC-SA 4.0 (not a software license), no versioning/changelog, no maintenance responsibility. Hence 0.
Insufficient evidence: no evidence of output usability, marginal value, or cost-benefit. Hence 0.
Insufficient evidence: claims lack traceability, no cross-source corroboration, facts and inferences not separated. Hence 0.
- Not found in source: least-privilege scopingGrant only what the task needs: a dedicated account or read-only token, scoped to specific directories and repos.
- Not found in source: confirmation before actingTurn on (or add) a confirmation step before it acts, and try it in a sandbox or test environment before real data.
- Not found in source: data-flow disclosureWatch which external services it contacts (proxy or firewall logs) and keep sensitive data out until you know where it goes.
- Not found in source: sensitive-data handlingUse dedicated, low-privilege, revocable API keys — never production credentials — and keep secrets out of logs.
- Not found in source: dependency securityPin versions and run a dependency audit (npm audit, pip-audit) before installing; prefer running it in a container.
- Not found in source: disclosed external effectsEstablish which external systems it writes to, sends to or changes, and verify with test accounts or repos before production.
- Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
- Not found in source: verifiable attributionInstall from the official repo or registry and check the publisher and URL to avoid look-alike packages.
- Repository lacks security documentation and permission model; audit before deployment.
- License is CC BY-NC-SA 4.0, not an open-source software license, may restrict commercial use.
- Test files exist but no execution results; static review cannot verify their effectiveness.
Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
Release notes excerpt
v0.5.0-beta.1 — Self-hosted preview This is a pre-release for local, self-hosted use. It is a substantial update from v0.4.x; use a new installation directory and new Compose project for evaluation. Do not point this release at an existing database without a reviewed migration and backups. What's new - A project canvas for images, videos, references, folders, and an integrated Assistant. - Direct reference uploads and project-media selection in image/video drafts. - Model-bound frame ratios, durations, reference roles and limits, and advanced generation settings. …View on GitHub ↗ -
v0.4.1 v0.4.1 update
Release notes excerpt
v0.4.1 Release Notes 优化道具确认与筛选逻辑，减少将场景内普通物件误判为关键道具的情况 接入 Wan 2.7 视频模型，补充对应能力声明、策略约束与测试覆盖 持续打磨资产相关 UI / UX，优化编辑、导入、卡片比例、生成中状态与交互一致性 补齐道具 AI 修改描述链路，统一资产中心与项目内的修改入口与任务处理 调整资产中心图片策略，移除全局图片文字标识，收口全局母图与项目参考图边界 继续增强测试与工程约束，降低资产链路与模型能力变更带来的回归风险 核心更新 道具筛选逻辑优化 本次重点收紧了道具识别标准，避免把餐具、酒杯、办公设备、房间陈设这类场景内普通物件误识别为道具资产。新的规则更强调“跨场景持续存在”“有明确文本证据”“具有唯一性或持续性”，整体提取结果会更保守，但也更符合真正的关键道具定义。 道具 AI 修改能力补齐 新增并打通了道具的 AI 修改描述能力，覆盖资产中心与项目内资产两条链路。现在角色、场景、道具三类资产在描述修改能力上更统一，道具不再是缺失能力的例外项。 资产编辑与导入体验优化 对多个高频资产界面进行了细化调整，包括 AI 修改入口位置、按钮样式统一、导入弹窗视觉收敛、导入卡片预览比例统一、无图占位图标调整、生成中状态的固定比例占位等。整体目标是减少跳跃感、坍缩感和不一致交互，让资产编辑体验更稳。 资产中心图片策略调整 …View on GitHub ↗ -
v0.4.0 v0.4.0 update
Release notes excerpt
最近比较忙所以基本没怎么更新 现在开始会恢复快速更新节奏！尽情期待！后续会有更大的更新！！我的目标依然是 the best in the world！ 重构分析工作流架构，提升长链路任务稳定性与恢复能力 重做首页与工作区入口体验，优化从启动创作到进入工作流的路径 引入 Props 资产体系，统一资产库与资产中心的能力边界 增强视频生成能力，扩展新一代模型接入与结果可控性 增加 AI Story Expand 等创作辅助能力，降低内容启动门槛 持续打磨 UI / UX，改善弹窗、编辑、卡片、面板与流程反馈体验 强化测试框架与工程守卫，降低高风险改动带来的回归概率 收口历史无效模式与旧架构，继续推进系统统一与复杂度压缩 核心更新 工作流稳定性升级 本次对分析链路与运行时执行机制进行了较大幅度调整，重点提升了 StoryToScript、ScriptToStoryboard 以及相关任务流在失败、取消、重试、恢复等场景下的稳定性与一致性。整体目标是让复杂创作流程更可控、更易恢复，也更方便定位问题。 首页与创作入口升级 新增首页与更清晰的创作启动入口，改善用户首次进入产品时的理解成本与操作路径。相较此前更偏“直接进入工作区”的方式，现在整体入口逻辑更完整，启动创作、创建项目与继续现有工作流的体验都更加顺畅。 资产体系升级 …View on GitHub ↗