# 869413421/ai-moive-studio

自然语言驱动的无限画布工作流 Agent，让 AI 视频创作第一次真正变成可编辑的工作流。   AICON 面向创作者，提供从剧本拆解、分镜生成、素材生成、视频合成到内容分发的一整套能力。   不是只给你一个输入框，而是让你用自然语言和无限画布一起驱动创作，把文本、图片、视频节点组织成完整链路，真正把“从灵感到   成片”放进一个系统里完成。

Repository: https://github.com/869413421/ai-moive-studio
Canonical: https://ross.abutalabs.com/products/ai-moive-studio
Homepage: https://aicon-studio.com
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ai, video, movie
Last push: 2026-04-06T05:41:44+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 76, release rhythm 63, longevity 21
- inputs: {"age_days": 296, "days_push": 149, "days_rel": 247, "gap_med": 17, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1456, forks 234 (observed 2026-08-28T04:04:46.932360+00:00)

## What it is
AICON is a full-stack, self-hostable AI video creation studio that pairs a natural-language-driven agent with an infinite-canvas node editor for text, image, and video generation nodes. It turns long-form text such as novels or screenplays into characters, scenes, storyboards, keyframes, and generated videos, then composites voiceover, subtitles, and music and can auto-publish the results (e.g., to Bilibili).

## Use cases
- turn a novel or screenplay into an AI-generated movie
- generate storyboards, keyframes, and transition videos from a script
- build AI image and video generation workflows on an infinite canvas
- batch-produce narrated explainer or picture-commentary short videos with images, voiceover, and subtitles
- keep characters visually consistent across generated shots using reference images
- organize prompts, reference images, and multi-version generations in a visual node editor
- automatically upload and publish finished videos to Bilibili

## When to choose
- You want an end-to-end pipeline from long text to finished, publishable video inside one system
- You prefer node-based canvas editing where an assistant scaffolds the workflow but you control when generation runs
- Character consistency across scenes is important and you want reference-image-driven generation
- You produce picture-narration or plot short videos at volume and need concurrent image, speech, and subtitle generation
- You want to swap model providers via OpenAI-compatible base URLs and self-host the whole stack

## When to avoid
- You need frame-accurate manual video editing - use a professional NLE instead
- You expect one-click fully autonomous generation; the canvas assistant only builds nodes and connections, and you trigger each generation step manually
- You don't want to operate the backend stack (PostgreSQL, Redis, Celery, MinIO) or manage your own model API keys
- You need fully offline generation - the tool depends on external model providers

## Facets
- artifact type: application
- maturity: active
- function: video-processing, image-processing, tts, agent-framework, workflow-automation, prompt-engineering
- domain: artificial-intelligence, large-language-models, media
- platform: self-hosted, python
- tags: ai-video-generation, text-to-video, infinite-canvas, node-editor, storyboard-generation, script-breakdown, character-consistency, picture-narration, voiceover, bilibili, vue3, fastapi, celery, minio, self-hostable, content-creation, movie-production, video, ai-agents, web-server, docker

## Member repositories
- 869413421/ai-moive-studio (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:46.932360+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:35:34.652783+00:00, confidence not recorded.
  - readme: https://github.com/869413421/ai-moive-studio (fetched 2026-08-28T04:04:46.932360+00:00, sha d2647ed53e22)
  - homepage: https://aicon-studio.com (fetched 2026-08-29T11:44:32.407051+00:00, sha 6372b334ccd4)
- Data as of 2026-08-30T08:39:29.467469+00:00.