v0.31.0 · Commercial tier · Tell us what you need
From a novel
to a finished reel,
agent-driven.
Open-source AI short-drama & manga workspace · novel to reel · multi-agent orchestrated
ArcReel is an open-source AI short-drama & manga workspace. Drop in a novel, and an agent orchestrates scriptwriting, character design, storyboarding and final video synthesis — keeping characters, scenes and props visually consistent across every shot.
pipeline.reel · v0.31.0
06 stagesagent-orchestrated
01
Upload novel
Drop in the source text. Chinese or English, any length.
02
Build asset library
Agents scan the full work and index every character, scene, and prop.
03
Plan & split episodes
Progressive human-in-the-loop episode breakdown with AI-suggested cut points.
04
Generate script JSON
Normalize prose into structured scene / shot JSON — narration, drama or ad.
05
Character & storyboard frames
Reference sheets first; then every shot with cross-scene consistency.
06
Synthesize video
Image-to-video per shot, then FFmpeg-composed final reel or Jianying export.
Built for consistency across every shot.
Characters keep their faces. Props keep their shapes. Scenes keep their mood. ArcReel's agent graph treats continuity as a first-class artifact — not an afterthought.
Agent workflow
Orchestration Skill + focused Subagents
A state-aware orchestrator detects your project phase and dispatches subagents for each task. Large context (novel text, references) stays inside subagents — only distilled summaries reach the main thread.
Character DNA
Cross-shot consistency
Reference sheets are generated first; every downstream storyboard and video clip is conditioned on them. Characters, scenes, and props are tracked as persistent assets across every cut.
Queue
Async task engine
RPM-rate-limited, lease-based scheduling with independent image / video channels. Batch runs report success and failure per item, so a retry only re-renders what failed — you never pay twice for what already worked.
Versioning
Every regen is history
One-click rollback. Compare variants side by side. Nothing is ever lost.
Export
Jianying-ready drafts
Ship per-episode ZIPs into Jianying 5.x / 6+ for human finishing. FFmpeg pipeline for automated cuts.
Bring your own model stack.
One backend protocol spanning text, image and video generation, with speech output alongside. 11 generation providers and 100+ preset models built in — plus custom endpoints in a range of formats, including self-hosted Ollama and vLLM.
The table shows five of them and a subset of preset models. Full provider & model list in the docs →
Modality
Gemini
Volcengine
Grok (xAI)
OpenAI
Vidu
Image
Nano Banana 2 / Pro
Seedream 5.0 / Lite / 4.5 / 4.0
Grok Imagine Image / Pro
GPT Image 2 / 1.5 / 1 Mini
Vidu Q2 / Q1 Image
Video
Veo 3.1 · Fast · Lite
Seedance 2.0 · Fast · 1.5 Pro
Grok Imagine Video
Sora 2 · Sora 2 Pro
Vidu Q3 Turbo · Pro · 2.0
Text
Gemini 3.1 Pro / 3 Flash / 3.1 Flash Lite
Doubao Seed 2.0 / 1.8 series
Grok 4.20 / 4.1 Fast
GPT-5.5 / 5.4 / Mini / Nano
—
11
Generation providers
100+
Preset models
∞
Custom endpoints
3·2
Content types · generation modes
Tell us what you need from a commercial tier.
The open-source build is free forever. Commercial licensing beyond AGPL-3.0 is open for inquiries today, and the commercial tier grows from there — tell us what else you need.
Received · #
Thanks, friend.
We'll read it properly and get back to you at {email}. In the meantime, join the community group below to see what we're building.
Join the community.
Swap tips, show reels, troubleshoot, and shape the roadmap with other creators and devs building on ArcReel.
Get early access to the reel.
We post release notes, prompt recipes, and sneak peeks of unreleased agents in the group. Join before the next cohort closes.
- ◆Weekly model & feature digests
- ◆Direct access to core maintainers
- ◆Showcase channel for community reels
- ◆First look at new features
Feishu · Chinese-first
Scan with Feishu / Lark
Frequently asked.
Yes. ArcReel is AGPL-3.0 open source and free forever — self-host with Docker Compose on Linux, macOS or WSL2. You only pay for upstream AI provider usage (Gemini, Volcengine, OpenAI, Qwen, or your own endpoint). If AGPL-3.0 does not fit how you plan to use it, commercial licensing is open for inquiries: support@arc-reel.com.
Before any storyboard is rendered, a subagent scans the novel and builds a library of characters, scenes, and props. Reference sheets are generated first and every downstream image/video generation is conditioned on them. Continuity is designed in, not a prompt hack.
Eleven generation providers ship out of the box — Gemini (AI Studio and Vertex), Volcengine Ark, Grok (xAI), OpenAI, Vidu, Qwen DashScope, MiniMax, Kling, Agnes and more — with 100+ preset models across text, image and video generation plus speech output. The orchestration layer adds another 11 preset agent providers to choose from. You can also add custom endpoints: ArcReel speaks a range of endpoint formats, including self-hosted Ollama and vLLM, and auto-discovers the available models. Full list in the docs: https://docs.arc-reel.com/en/guide/providers
Yes. Per-episode drafts export as a ZIP compatible with Jianying desktop 5.x and 6+ (the mainland China edition). Import, fine-tune the cut, add music, done. CapCut is Jianying's international sibling but uses a different draft data structure — only Jianying is supported today.
A POSIX-like environment: Linux, macOS, or Windows with WSL2 / Docker Desktop. A few low-level dependencies are POSIX-only, so native Windows isn't supported yet.
The open-source build is the whole product — nothing is held back from it. What is concrete today is commercial licensing beyond AGPL-3.0, for cases where you would rather not publish your modifications or need different terms. The rest of the commercial tier is still taking shape; tell us what you need below, or write to support@arc-reel.com.
The commercial platforms are closed-source SaaS — your scripts, character assets and generated content live in their cloud. ArcReel is AGPL-3.0 open source and self-hostable: data stays on your machine, you hold the model API keys, and full novels never leave your server. Against other open-source projects, the difference is coverage and orchestration depth: 11 built-in generation providers with 100+ models, pluggable custom endpoints, and a multi-agent pipeline that runs the whole chain — source text, asset library, episode split, script, character sheets, storyboard, final reel — rather than a script wrapped around a single model. Commercial platforms win on zero-ops and ready templates; ArcReel wins on control, hackability, and zero subscription fees.
All three ship preset in ArcReel. Pick by use case: Veo 3.1 produces the most natural long takes and camera motion, with Fast / Lite variants for speed-cost tradeoffs. Sora 2 / Sora 2 Pro give the strongest realism and acting detail. Seedance 2.0 has the richest multi-modal reference (mix up to 9 images, 3 videos, 3 audio clips per shot), strong Chinese-scene understanding, and token-based pricing that stays predictable on long projects. Vidu Q3 and Kling are further options with reference-to-video support and solid Chinese-scene handling. Switch globally or per-project — no need to commit upfront.
Nano Banana 2 (Gemini 3.1 Flash Image) supports multi-reference input. ArcReel's flow: a Subagent first scans the full novel to extract a cast list, then generates a reference sheet for each character; every downstream storyboard frame conditions on that reference. ArcReel also tracks 'clues' — key props and scene elements — the same way. Consistency is baked into the pipeline, not prompt magic.
No. All image / video / text generation goes to provider APIs (Gemini, Seedance, Sora, Qwen, etc.) in the cloud. Your machine only runs orchestration logic, FFmpeg compositing, and Jianying draft packaging. A normal laptop with macOS / Linux / WSL2 + Docker Compose is enough. If you wire in self-hosted Ollama / vLLM for local LLMs, that machine needs a GPU — but with the preset providers, no GPU required.
It's the Skill + Subagent pattern from the Claude Agent SDK. The main Agent only reads project state and decides the next step; concrete tasks (character extraction, script normalization, storyboard, video) are dispatched to focused Subagents. Each Subagent handles its large context (novel text, reference images) internally and returns only a distilled summary. The main Agent's context never gets blown up, so the pipeline stays stable across long works — and resumes from any stage.
Progressive human-in-the-loop. ArcReel first peeks at the structure, a Subagent proposes cut points (by plot arc, character entry, POV shift), you confirm or adjust in the web UI, and only then does it physically split. Cut everything at once, or step through episode by episode — each episode generates its own script JSON, character sheets, storyboard, and video. Narration splits by reading rhythm, drama by scene / dialogue, ad by selling-point beats.
Yes. ArcReel uses one backend protocol for text, image, video and speech generation, and speaks a range of endpoint formats — self-hosted Ollama and vLLM included. Add a custom provider in settings with Base URL + API Key; ArcReel discovers what's available and infers media type by name. Custom endpoints get the same treatment as the presets: project-level switching, cost tracking, version history. Third-party API gateways work too.
AGPL-3.0 allows commercial use but adds a copyleft and network-service clause: if you modify ArcReel and serve the modified version over a network, you must release your modifications under AGPL-3.0 to end users. Internal use only, or building one-off projects for clients (no network service), doesn't trigger the clause. If you'd rather not open source your modifications, ask us about commercial licensing: support@arc-reel.com.
AI manga drama leans anime / animation style with snappy pacing and strong visual styling; AI short drama leans live-action realism with melodrama / vertical-video pacing; narration video is text-to-speech + images + simple motion, focused on storytelling rather than performance. ArcReel exposes three content types: narration (split by reading rhythm), drama (organized by scene / dialogue) and ad (organized by selling-point beats) — each available in storyboard or reference-video generation mode. Layer on style references and art-direction settings to switch between manga and short-drama looks.