What's New in v6.0.0

What's New

Manual Mode (Human-in-the-Loop Checkpoints)

Manual Mode pauses your pipeline at the checkpoints you choose, so you can confirm, modify, or regenerate each intermediate artifact before continuing — "auto for vibe, manual for precise output."

• Checkpoint pausing — the pipeline stops at a checkpoint after the artifacts are produced, waits for your action, and continues from the last confirmed stage.
• Fine-grained pause points (creative) — up to 10 stages: image analysis, story, script & narration, character reference, end-frame prompts, end-frame generation, videos, audio, subtitle, and final composite.
• Standard pause points (manuscript / poetry / anchor) — 6 stages: scenes, references, videos, audio, subtitle, and final.
• Pre-filled default pause points — filled in automatically per task type at creation (editable; unchecked checkpoints pass through automatically).
• Not supported — simple (single-shot) video and simple image tasks only show the artifact list on completion.

Four Ways to Refine Artifacts

At each paused checkpoint you can pick any of these ways to handle the current artifacts:

• 🤖 AI-assisted editing — describe your change (e.g. "make scene 2 more cinematic") and the built-in model rewrites the artifact; review the diff before applying.
• ✏️ Edit locally — copy the artifact path and edit the file directly (JSON / SRT / images / videos), then click "modified, continue".
• 🤝 External Agent — copy a ready-made collaboration prompt and hand the artifact to a more capable local Agent (e.g. opencode / CodeBuddy CLI / ffmpeg / PIL), then fill the result back in.
• 💻 Online editing — edit text artifacts (script / narration / subtitles) in an in-page dialog with side-by-side comparison against the original.

Artifact-Level Dependency Graph (Rerun Only What Changed)

After any modification, the system computes affected downstream artifacts precisely and reruns only those — the rest are kept untouched:

• Edit narration → reruns audio / subtitle / final only.
• Edit scene descriptions → reruns reference images / videos / final only.
• A "before-modification" prompt lists exactly which artifacts will be regenerated vs. retained.

Switch Between Auto and Manual Anytime

• Switch an auto task to manual while running — it pauses at the next safe checkpoint.
• Switch a manual task back to auto while paused — pause points are cleared and it runs straight to completion.

Other Features & Improvements

• Dedicated task progress page — a focused, full-page progress view with step timeline and live status.
• Task detail page — opens in a new tab with official-site links and support guidance.
• Project card pinning — pin a task card to the top of the list; artifact previews auto-expand.
• "Continue without changes" button at every pause point — skip review on any channel.
• Bilingual startup scripts — prompts adapt to the system locale.
• Full 22-language i18n — missing translations completed, plus a new language-completeness checker used as a release regression gate and a language switcher in the task progress header.

Refactoring & Optimizations

• Unified checkpoint mechanism across pipelines — the same MultiScenePipeline checkpoint system now powers creative, manuscript, poetry, and anchor tasks, with per-type artifact matrices.
• Standalone artifact dependency graph — core/dependency_graph.py is a pure, declarative edge-table module (product-level + parameter-level) shared by impact prediction, approve handling, and frontend highlighting; fully unit-tested.
• Standardized artifact manifests — per-checkpoint checkpoint.json lists and task-directory MANIFEST.md make every intermediate artifact discoverable, readable, and refillable.
• Resume skips completed scene-building steps — avoids duplicate LLM calls when Creative / Anchor / Poetry tasks resume.

Bug Fixes

• Fixed an un-clickable "open edit window" button caused by checkpoint artifact field-name mismatch.
• Fixed multi-PID port-in-use hints so the kill command is emitted as a single copyable line.
• Progress control-flow fixes — pause UI cleared immediately after resume, and queued/running tasks now show real-time progress messages.
• Character reference image generation moved into the references stage for correct ordering.
• Manual-mode UI polish — visible disabled states, artifact filter compatibility, auto-collapse of earlier stages, and resume for inactive unfinished tasks.

Learn more about Manual Mode: Manual Mode Guide and the in-repo docs/public/manual_mode_guide.md.

Quick Start (npm)

npx free-short-video

Or install globally:

npm install -g free-short-video
free-short-video

Requires Python 3.10+ and ffmpeg.

🎬 Agnes Video Generator — Completely Free AI Video Generator

🌏 Mirror Notice / 镜像说明 This project is also mirrored on Gitee for faster access in mainland China. The GitHub repository is the primary home of this project — issues, PRs, and stars are managed there. 本项目在国内 Gitee 设有镜像仓库，便于国内访问加速；GitHub 为项目主仓库，Issue / PR / Star 均在 GitHub 提交。

Completely free AI video generator — Built on Agnes AI's free models, no subscription, no high-end GPU, no usage limits. Type in a text idea and automatically generate multi-scene AI videos with narration and subtitles. Supports text-to-video, image-to-video, keyframes animation, digital anchor, and more. All AI compute runs in the cloud — a regular laptop is all you need. Try it online →

"The solution is not to suppress AI, but to make it a more equitable capability, so that everyone knows how to create more with AI. This is a very important vision for our company — to make world-class AI belong to everyone. What we can do may be insignificant, but this vision is very long-term and enduring."

— Bruce Yang, Founder of Agnes AI

🌐 Official Website | 📝 Blog (中文) | 📝 Blog (English)

🖥️ Try it now — no install needed: Visit video.lichuanyang.top and experience Simple Video mode directly in your browser. Just enter a prompt and generate a free AI video instantly.

🚀 Two Ways to Use — Both Completely Free

| Project | Run Where | Features | Link | |---------|-----------|----------|------| | Agnes Video Generator (this project) | Download & run locally | More powerful — TTS narration, auto subtitles, digital anchor, image-to-video, keyframes animation, manuscript-to-video, checkpoint resume & more | GitHub | | FreeShortVideoStudio | Fully online, in the browser | Lightweight, zero install — no setup at all, features under active construction | video.lichuanyang.top/studio · GitHub |

⭐ Support & Contribute

If you find this project useful, please star the GitHub repository ⭐ — your support helps more people discover this free and open-source AI video generator.

Bug reports and feature suggestions are welcome via GitHub Issues.

💝 Support the Developer

Agnes Video Generator is and will always remain completely free and open-source. There will be no paid plans, no premium features, and no subscription services — now or in the future.

If you find this project helpful, here are a few ways to support its continued development:

• ⭐ Star on GitHub — Star the repository to help others discover this project.
• 🌐 Whitelist the official website — Turn off your ad blocker on video.lichuanyang.top and click on an ad if something catches your eye. A small gesture that makes a real difference.
• 📢 Share your creations — Post videos made with Agnes Video Generator on social media (Douyin, YouTube, Xiaohongshu, etc.) and tag the project. More exposure means more users, more feedback, and a better tool for everyone.

🎥 Demo

1. Creative Video — No Narration

A dark-twist fairytale — The Frog Prince, 5 scenes, keyframes chaining, fully auto-generated.

2. Creative Video — With TTS Narration

Same Frog Prince story, now with AI-generated TTS narration and auto subtitles.

3. Manuscript Video — Text-to-Video

Paste a long article or script → auto-split into segments → AI video per segment → unified TTS narration + subtitles → final video.

Click to watch on Douyin

Why Agnes Video Generator?

Making AI videos today has an absurdly high barrier. Overseas services like Runway and Pika charge monthly subscriptions of tens of dollars. Domestic platforms like Jimeng and Keling charge by the second once their free quotas run out. Want to run open-source models locally? A GPU capable of video generation easily costs over ten thousand RMB. For most people who want to try AI video creation, the door is essentially closed.

We believe what Bruce Yang said — AI should be a more equitable capability. World-class AI should belong to everyone, not just those who can afford the bill.

To be honest, Agnes's video model isn't perfect yet. The generated frames are sometimes unstable, and complex actions occasionally deform. But it is completely free with no usage limits, and it iterates fast. We choose to grow with it rather than wait for a "perfect" commercial solution. If you share this mindset, then this project is for you — all you need is a free Agnes AI API key and an ordinary computer that can run Python to start creating AI videos at zero cost.

Comparison: Agnes vs. Commercial AI Video Tools

| Feature | Agnes Video Generator | Runway Gen-3 | Pika 2.0 | OpenAI Sora | Kling 1.6 | |---------|:---:|:---:|:---:|:---:|:---:| | Price | Free | $15–$95/month | $10–$95/month | $20+/month (limited) | Free quota, then pay-per-second | | Open Source | ✅ Yes (MIT) | ❌ No | ❌ No | ❌ No | ❌ No | | Self-Hosted | ✅ Yes | ❌ No | ❌ No | ❌ No | ❌ No | | Max Video Length | 20s per clip, unlimited scenes | 10s per clip | 10s per clip | 20s per clip | 10s per clip | | Multi-Scene Pipeline | ✅ Built-in (Creative/Manuscript) | ❌ Manual editing | ❌ Manual editing | ❌ Manual editing | ❌ Manual editing | | AI Narration (TTS) | ✅ Free, built-in | ❌ Third-party | ❌ Third-party | ❌ Not available | ❌ Not available | | Auto Subtitles | ✅ Word-level SRT | ❌ Not available | ❌ Not available | ❌ Not available | ❌ Not available | | Digital Anchor | ✅ Built-in | ❌ No | ❌ No | ❌ No | ❌ No | | Resolution Options | 9:16 / 16:9 / 1:1 | Multiple | Multiple | Multiple | Multiple | | Image-to-Video | ✅ Yes | ✅ Yes | ✅ Yes | ✅ Image inputs | ✅ Yes | | Keyframes Animation | ✅ Yes | ✅ Yes | ✅ Yes | ❌ Not available | ❌ Not available | | Local GPU Required | ❌ No (cloud API) | ❌ No (cloud) | ❌ No (cloud) | ❌ No (cloud) | ❌ No (cloud) | | Watermark | No watermark | Built-in watermark | Built-in watermark | C2PA metadata | Built-in watermark | | Usage Limit | No limit (16 req/min rate limit) | Billed by compute | Billed by generation | Billed by generation | Billed by generation |

📚 Documentation

• Features — Creation modes, the completely free AI model chain, AI narration & smart subtitles, flexible creative controls, production-grade reliability, and the multilingual Web UI.
• Getting Started — Install and deploy in 4 ways: Manual (start.sh), Docker, npm (npx free-short-video), or AI-Agent assisted.
• Usage Guide — Configure your API key, pick a video mode, resume from checkpoints, the three chaining modes, and logs & output layout.
• Architecture — Project structure and tech stack.
• API Reference — Full REST + WebSocket endpoint list.
• FAQ — Frequently asked questions.
• About & License — Acknowledgments and the MIT license.

Keywords: free AI video generator, AI video generation tool, text to video AI, free AI video maker, AI video creator, open source video generator, Agnes AI, text-to-video, image-to-video, keyframes video, AI narration, auto subtitles, multi-scene video, zero cost AI video, no subscription AI video tool, digital anchor, self-hosted AI video generator, open source alternative to Runway