# RanFeng/clipsketch-ai

将视频瞬间转化为手绘故事 Turn Video Moments into Hand-Drawn Stories

Repository: https://github.com/RanFeng/clipsketch-ai
Canonical: https://ross.abutalabs.com/products/clipsketch-ai
Homepage: https://clipsketch-ai.vercel.app
Language: TypeScript
License Family: other
Last push: 2026-01-14T07:28:07+00:00

## Health v2 (maintenance only)
Score: 43/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 62, release rhythm 33, longevity 19
- inputs: {"age_days": 279, "days_push": 231, "days_rel": 232, "gap_med": null, "n_releases_24m": 1}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1840, forks 241 (observed 2026-08-28T04:05:42.989794+00:00)

## What it is
ClipSketch AI is a web-based AI content creation workbench that imports videos from Bilibili and Xiaohongshu links, lets users frame-accurately tag highlight moments, and uses Google Gemini multimodal models to turn those moments into hand-drawn storyboards plus social media copy and covers. It is built with React 19, TypeScript, and Tailwind CSS, and can be run via Node.js or Docker.

## Use cases
- turn video clips into hand-drawn storyboard images
- generate xiaohongshu-style social media captions from video frames
- tag highlight moments in a bilibili video frame by frame
- create video covers with AI
- merge a custom character avatar into generated storyboard scenes
- export tagged frames as a zip of images

## When to choose
- you create derivative content from Bilibili or Xiaohongshu videos and want AI storyboards and captions
- you need millisecond-precise frame tagging with keyboard shortcuts
- you want a self-hosted, Docker-deployable creative tool powered by Gemini

## When to avoid
- you need to process videos from platforms other than Bilibili or Xiaohongshu
- you don't have a Google Gemini API key or want a fully offline tool
- you need a license-clarified production deployment (the repo has no license)

## Facets
- artifact type: application
- maturity: active
- function: web-framework, image-processing, llm-inference, prompt-engineering, video-processing, web-scraping
- domain: artificial-intelligence, large-language-models, image-processing, social-media, web-development
- platform: cross-platform
- tags: storyboard, gemini, bilibili, xiaohongshu, social-media-copywriting, frame-tagging, react, content-creation, video, nodejs, web-server, docker

## Member repositories
- RanFeng/clipsketch-ai (main) score 43

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:42.989794+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 2026-08-30T03:18:02.790939+00:00, confidence not recorded.
  - readme: https://github.com/RanFeng/clipsketch-ai (fetched 2026-08-28T04:05:42.989794+00:00, sha d4e3ca6df981)
- Data as of 2026-08-30T08:39:29.467469+00:00.