# Stonewuu/ai-fusion-video

【融光】 - 基于 Agent 的全流程AI短剧/漫剧/视频创作平台 - Java & agentscope2.0 | Agent-based end-to-end AI creation platform for short dramas, motion comics, and videos – built on Java & & agentscope 2.0.

Repository: https://github.com/Stonewuu/ai-fusion-video
Canonical: https://ross.abutalabs.com/products/ai-fusion-video
Language: Java
License: MIT
License Family: permissive
Topics: agents, automation, java, short-drama, video-generation, agentscope
Last push: 2026-08-18T04:36:42+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 96, longevity 12
- inputs: {"age_days": 170, "days_push": 15, "days_rel": 27, "gap_med": 2, "n_releases_24m": 18}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1354, forks 288 (observed 2026-08-28T04:04:29.061788+00:00)

## What it is
RongGuang (Fusion Video) is a self-hosted, agent-driven web platform for end-to-end AI creation of short dramas, motion comics, and videos, combining project management, screenplay organization, storyboarding, and image/video generation in one workspace. It ships a Java 21 backend built on AgentScope 2.0 (with Skill, MCP, and sub-agent support), a Next.js frontend, and Docker Compose deployment, connecting to OpenAI-compatible, Anthropic, Gemini, DashScope, and Ollama model services with local or S3-compatible storage.

## Use cases
- generate AI short drama videos from a script
- turn screenplays into storyboards with AI assistance
- create motion comics using AI agents
- generate images and videos for each scene of a script
- self-host an AI video creation studio with my own API keys
- manage video projects with teams and AI agent workspaces

## When to choose
- you need an end-to-end workflow from script to storyboard to generated video
- you want a self-hosted platform where model API keys and media storage stay under your control
- you work in teams on episodic video projects and need roles, assets, and reusable media management
- you want an agent workspace with streaming chat, multimodal input, MCP tools, and sub-agents for multi-step creative tasks

## When to avoid
- you only need a simple one-click text-to-video generator without project or storyboard management
- you need professional non-linear video editing rather than AI-assisted creation
- you want a lightweight library or CLI to embed in your own app instead of a full web platform
- you cannot run a Java 21 backend plus Next.js frontend stack

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, video-processing, image-processing, chat-interface, workflow-automation, self-hosted, mcp
- domain: artificial-intelligence, media, entertainment
- platform: jvm, self-hosted
- tags: ai-video-generation, short-drama, motion-comics, storyboard, screenplay, agentscope, agent-workspace, multimodal, video-creation, s3-storage, ai-agents, video, nodejs, docker, web-server

## Member repositories
- Stonewuu/ai-fusion-video (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:29.061788+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 2026-08-30T04:42:00.222560+00:00, confidence not recorded.
  - readme: https://github.com/Stonewuu/ai-fusion-video (fetched 2026-08-28T04:04:29.061788+00:00, sha b5476891748a)
- Data as of 2026-08-30T08:39:29.467469+00:00.