AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Vision / Multimodal/
Toonflow-app
Toonflow-app logo

Toonflow-app

Active·★ 22.1k·MIT·Updated 2026-11-16
★ Most Popular

Toonflow is an open-source creation platform for AI short dramas, motion comics and short videos. It combines scripts, storyboards, character materials and generation tasks on an infinite canvas. Its practical appeal is organizing relationships between creative artifacts while allowing configurable model providers. We reviewed a fixed source commit and selected local modules, rather than judging a demonstration film. The repository declares Bun 1.4.3; our module checks used Node.js native TypeScript stripping and did not establish full application compatibility or a successful deployment.

Twenty checks covered media port compatibility, invalid connection rejection, asset cleanup candidates, canvas identification, Chinese text decoding and one Compose declaration. IMAGE-to-IMAGE and wildcard matching worked; IMAGE-to-VIDEO, self connections and missing ports were rejected. Referenced asset directories were retained when calculating cleanup candidates, while an unreferenced valid node directory was returned. UTF-8 and BOM-marked UTF-16LE Chinese decoded, and binary text was rejected. A leading root canvas marker can identify a file without validating the remaining JSON, which matters when assessing imports and recovery.

Use a small project to verify real references, provider behavior, failed-task recovery and output quality before scaling production. We did not start the UI, delete assets, generate images or videos, build a Docker image or restore a complete backup. The documented Compose setup binds to loopback and persists application data; remote access requires attention because the README states the UI and API lack separate login authentication. MIT licensing permits self-hosting, while model charges and local compute requirements remain separate. Choose it for an evaluated creative workflow, with the selected model and project material included in acceptance.

Read the full review, verification scope and sources →

Hands-on tested · Tested on 2026-11-05 with commit 6086cdffceb704a632eca143dd16cd461a78cdac (selected modules under Node; not a full Bun application test).

Setup: macOS arm64; Node.js 26.6.0, CPython 3.12.13; selected modules and temporary synthetic files only

Commands run

python3.12 doc/review-fixtures/memory-video-20261105/verify.py --sources <source-parent> --output /tmp/memory-video-results.json

What we saw

  • Twenty checks of selected unmodified modules passed under Node.js 26.6.0; not a full Bun application test.
  • Port constraints, reference-aware cleanup candidates and Chinese text decoding behaved as recorded; leading canvas marker is not full validation.
  • No UI, model, image/video generation, asset deletion, Docker build or backup restoration.

Data as of 2026-11-12.

License
MIT
Latest release
v2.0.10 · 2026-11-05
Last commit
2026-11-05
Contributors
6
Forks
3,861
Open issues and PRs
4
First published
2026-01-29

Source: GitHub, npm and PyPI public APIs.

#ai-agents#ai-comic#ai-content-creation#ai-filmmaking#ai-short-drama#generative-ai#image-generation#image-to-video
↗ Visit site★ GitHub
01

Features

01Infinite canvas for scripts, assets and video clips
02Shot-by-shot video generation from text and image references
03Desktop, Android, Docker and server deployment
04Third-party APIs or local ComfyUI and LLMs
05MCP, A2A and plugin market
02

Why choose it

+Selected connection code rejected incompatible media types, self connections and missing handles.
+Referenced asset directories were retained when calculating cleanup candidates.
+UTF-8 and BOM-marked UTF-16LE Chinese script samples decoded successfully.
03

Trade-offs

!Canvas identification is not full JSON validation; a leading marker can accept malformed remainder.
!Full UI, generation quality, Docker deployment and backup restoration were not tested.
!The documented server lacks separate UI/API login; provider costs and compute remain separate.
05

Maintenance check

ActiveChecked: 2026-11-12
Last commit
2026-11-05
Commits, last 90 days
100+
Releases, last 90 days
11
Latest release
v2.0.10 (2026-11-05)
Open issues
4
Recent issues with at least one comment
29/30
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 0, 0, 0, 0, 0, 0, 5, 4, 1, 1, 4, 0

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #396 [Bug] 工作区固定大图标和工具栏缺少响应式密度,小窗口下信息展示不全1 comments · 2026-11-06

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

04

Who it fits

Pick it if
  • You need a canvas to organize a small AI video production trial.
  • You can evaluate the actual model, references and recovery workflow.
Look elsewhere if
  • You require demonstrated finished-film quality before trying it.
  • You need a remotely deployed authenticated service without additional setup.
06

Compatibility

Bun
1.4.3 declared by source
Verified via docs
Docker Compose
Documented self-hosted deployment
Verified via docs
FFmpeg
Media runtime dependency
Verified via docs
07

Use cases

↳Producing AI short dramas or comic videos
↳Keeping a video project's script, characters and shots in one place
08

Alternatives

⚡Top VS:
VSGenAI_Agents★25.0k→VSdramaclaw★7.7k→VSffmpeg-skill★7.7k→VSdrama-skills★4.4k→
video-shotcraft logo
video-shotcraft★ 21.0k
AI video skill for Claude Code & Codex — cinematic, editable product promos with Remotion: 124 shot recipe cards, 150 motion previews, beat sync, sound design, Motion Workbench & JianYing (CapCut CN) export.
GenAI_Agents logo
GenAI_Agents★ 25.0k
50+ tutorials and implementations for Generative AI Agent techniques, from basic conversational bots to complex multi-agent systems.
VSCompare→
dramaclaw logo
dramaclaw★ 7.7k
A general-purpose AIGC video engine: script to finished film in one pipeline — dramas, ads, product videos, otome games, and more. | 通用 AIGC 视频引擎 —— 从剧本到成片一条流水线,漫剧、广告、电商、乙游皆可
VSCompare→
ffmpeg-skill logo
ffmpeg-skill★ 7.7k
Local video editor for coding agents: 42 FFmpeg tools with a machine-readable contract and an MCP server, for Claude Code, Cursor and Codex. Cut, captions, reframe, loudness, platform exports. No cloud, no API keys.
VSCompare→
drama-skills logo
drama-skills★ 4.4k
AI 短剧与漫剧制作 skill 合集:小说改剧本、角色设定三视图、分镜脚本、生图/生视频提示词与成片审片,适配 Claude Code / Codex 等 | Open-source agent skills for AI short dramas & motion comics
VSCompare→
raea logo
raea★ 2.7k
Render Anything Engine: tell your AI what to make. Videos, motion graphics, 3D and games as React and TypeScript, rendered on your own GPU. Rust + Bevy, macOS, Linux and Windows.
VSCompare→
awesome-short-drama-skills logo
awesome-short-drama-skills★ 2.5k
AI 短剧 · 漫剧 Skill(技能包)精选:剧本、改编、分镜、Seedance / 可灵 / MiniMax 视频提示词,千问、豆包、龙虾 OpenClaw、WorkBuddy、Claude Code、Codex 等智能体可用 | Curated agent skills for AI short drama, micro drama / microdrama, vertical drama and manju (AI comic drama): screenwriting, storyboards, Seedance / Kling / MiniMax video prompts
VSCompare→
blender-skills logo
blender-skills★ 2.0k
Professional Blender 5.3 workflows as Agent Skills for Claude Code, Codex, Gemini CLI, Copilot and Cursor: modeling, UVs, PBR, baking, rigging, animation, export and QA.
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs05Maintenance check04Who it fits06Compatibility07Use cases08Alternatives
HBAI-Ltd /
Toonflow-app
↗

A canvas for AI short-drama scripts, assets and media tasks

22.1k3.9kMIT
Last commit2d ago
StatusActive
CategoryVision / Multimodal
Contributors6
Latest releasev2.0.10
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.