#1010th of 56 in Image and videoFor image, video and design, video and animation

arcreel

Self-hosted workbench that turns novels or scripts into short videos

Stars
6.4k
License
AGPL-3.0
Last commit
Nov 2026
Last release
Nov 2026
Language
Python
Stars, last 29 weeks+4,576
21 Apr 2026: 1,851 stars28 Apr 2026: 1,987 stars5 May 2026: 2,059 stars12 May 2026: 2,162 stars19 May 2026: 2,249 stars26 May 2026: 2,337 stars2 Jun 2026: 2,423 stars9 Jun 2026: 2,495 stars16 Jun 2026: 2,613 stars23 Jun 2026: 2,790 stars30 Jun 2026: 3,030 stars7 Jul 2026: 3,165 stars14 Jul 2026: 3,271 stars21 Jul 2026: 3,511 stars28 Jul 2026: 3,731 stars4 Aug 2026: 3,842 stars11 Aug 2026: 3,941 stars18 Aug 2026: 4,045 stars25 Aug 2026: 4,175 stars1 Sept 2026: 4,295 stars8 Sept 2026: 4,378 stars15 Sept 2026: 4,457 stars22 Sept 2026: 5,120 stars29 Sept 2026: 5,237 stars6 Oct 2026: 5,317 stars13 Oct 2026: 5,485 stars20 Oct 2026: 5,626 stars27 Oct 2026: 5,781 stars3 Nov 2026: 6,137 stars10 Nov 2026: 6,427 stars

1,851 on 21 Apr 20266,427 on 10 Nov 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

ArcReel runs a pipeline from novel, finished script or product material through content analysis, character/scene/prop assets, storyboards, video clips and narration to a final cut. Generation uses text, image, video and TTS providers configured in Settings, with cost tracking before and after each run. Output can be composed directly or exported as a Jianying draft for further editing.

Who it is for: Creators self-hosting short-video production from novels or scripts

Ranked among open-source alternatives to Midjourney (#10 of 10).

Strengths

  • Reuses asset reference images across storyboards to keep characters consistent
  • Stages can be confirmed, single assets regenerated, and versions rolled back
  • Shows estimated and actual cost per generation
  • Exports Jianying drafts; supports SQLite or PostgreSQL

Weaknesses

  • Generation depends on external provider APIs that you configure and pay for
  • Jianying export targets the mainland China version; CapCut compatibility not verified
  • AGPL-3.0; white-label or non-AGPL commercial use needs a separate agreement
  • Default Compose publishes port 1241 on all interfaces; add auth and HTTPS for remote use

What it needs

  • no GPU
  • Docker + Compose
  • Needs Docker, Docker Compose, text/image/video/TTS provider APIs, SQLite or PostgreSQL
  • Models: text LLM providers, image generation providers, video generation providers, TTS providers
  • port 1241

Quick answers

Is arcreel open source?

Yes. Its code is on GitHub under the AGPL-3.0 license.

Can you run arcreel with Docker?

Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.

Does arcreel need a GPU?

No, it runs without one.

Also in Image and video

See all 56
Also in Image and video
RankProjectScore
1frigateLocal NVR with realtime object detection for IP cameras37.4k starsMIT92 out of 100
2MoneyPrinterTurboGenerates short videos from a topic, with script, footage, voiceover and subtitles142.4k stars+12,729 (+9.8%) in 30 daysMIT88 out of 100
3toonflow-appInfinite-canvas tool for AI short drama and comic video production21.4k stars+4,197 (+24%) in 30 daysMIT86 out of 100
#4ComfyUINode-graph editor for running diffusion image, video, audio and 3D workflows146.3k stars+9,609 (+7.0%) in 30 daysGPL-3.085 out of 100
#5InvokeAIWeb UI for diffusion image generation with inpainting canvas and node workflows29.1k stars+545 (+1.9%) in 30 daysApache-2.085 out of 100