Skip to content
Happylancing Directory

liyupi/ai-desktop-outfit-video

HL-2026-1025·0861New

AI 桌面换装视频怎么做？把全网刷屏的「桌面动态壁纸换装」逐帧拆解，整理成一条可直接复制的提示词模板：一条提示词直出 30 秒成片，固定机位一镜到底，中文对白和字幕全部由模型生成，无需后期剪辑。适配即梦、豆包、Seedance 2.5 等 AI 视频工具，附火山方舟 API 脚本，并封装成 Cursor / Claude Code 可一键安装的 Agent Skill：说一句想法，它反过来采访你，自动写出精准提示词。

View on GitHub

Star history

1 snapshots

One observation so far (55 stars on Oct 25). The curve appears after the next snapshots.
Last 7 days
Not enough history (1 snapshot)
Last 30 days
Not enough history (1 snapshot)
Method
Differences between stored snapshots. How trends work

Quick start

pip install arkruntime requests

Taken from the project's README. Happylancing Directory does not run or test repository code; review commands before running them.

Why it is in the catalog

GitHub search: AI video generation.

  1. Oct 25GitHub search · source

More in AI Video Generation

  • Anil-matcha/Open-Generative-AI

    Unrestricted Open-source alternative to AI video platforms — Free AI image & video generation studio with 600+ models (Flux, Midjourney, Kling, Sora, Veo). No content filters. Self-hosted, MIT licensed.

    31.5K
  • shinshin86/mesh-avatar-studio

    Turn one illustration into an animated 2D mesh avatar with a coding agent and a local editor

    1,026
  • sitor-ai/frametell

    Frametell: turn your ideas and material into vivid explainer videos with an AI director agent. Local-first, any model.

    400
  • imbutus/ComfyUI-MiniMaxDirector

    Timeline director for the MiniMax H3 video model in ComfyUI — shots, camera moves and audio cues compiled into the structured prompt H3 reads. Independent project, inspired by LTXDirector.

    68
  • qianshuixia/shrimpreel

    Open-source template for "one photo → AI video that follows a viral template" SaaS sites, one site per trending keyword. Cloudflare Workers + D1/R2/KV/Queues, TanStack Start + Hono, Google sign-in, credit packs (Waffo/Dodo), fal.ai video generation, admin console.

    264
  • ruashots/ComfyUI-OpenH3-IR

    Four ComfyUI nodes for MiniMax H3: name your media with @, lock exact dialogue, and get the structured brief H3 wants. No <Picture 1> bookkeeping, no second service to start.

    38