Stars
A bilingual reference studio for poses, costumes, and AI character creation.
244 pixel art effects, every one a small piece of code. Plus a Claude Code skill to make your own.
ComfyUI workflow for MosaicDiff, including the custom nodes and the models that are not public downloads.
中文版 AI 姿势参考图库 · 1439 组 / 2878 张图片 / 完整汉化 · 零依赖静态画廊
Make games with your AI coding agent: 79 game-dev skills and a router for Godot, Unity, Unreal, Roblox, three.js, Phaser and 6 more engines. Checked on the real engines.
数学(小学到高中)、英语(三年级到高中)、初中物理的知识图谱:1644 个知识点、2403 条先修边、6723 道题,对齐课标,附自适应前置诊断。
Peach: Local-first video metadata scraper and media manager.
现代化的开源跨平台视频下载工具 — 一键保存全网无水印高清视频 / A modern, cross-platform open-source video downloader GUI for yt-dlp & FFmpeg
Qwen-Image 2.1 NSFW/姿势出图 skill:作者级提示词配方 + NSFW LoRA + 136 姿势 VNCCS 人偶控制;适用 Claude Code / Codex / Cursor / OpenClaw
Reverse engineer anything with agents, from app behavior down to native binaries.
A ComfyUI helper node for infinite-video workflows with chained MiniMax H3 segments.
Real-time audio translation, captures system audio + mic, runs ASR (Whisper/SenseVoice), translates via LLM API with streaming display. Perfect for VTubers, livestreamers, and watching foreign cont…
leejet / ComfyUI-GGUF
Forked from city96/ComfyUI-GGUFGGUF Quantization support for native ComfyUI models
🎬 Evidence-led Seedance 2.5 / 2.0 prompt library: 840+ cases traced to original posts, 490+ cross-model retest runs, 27 copy-ready templates, 79 installable AI-video Skills. Synced daily from goodc…
Split-screen video comparison tool using FFmpeg and SDL2
Desktop app to manage markdown knowledge bases
Desktop app for comparing two videos side by side with synchronized playback, trimming, and combined export. Built with Tauri + React + FFmpeg.
TK Toolkit (formerly Anima Toolkit) — all-in-one Anima/SD toolkit for ComfyUI: LoRA manager (batch apply + Civitai metadata & downloads), Danbooru search & waterfall gallery, bilingual prompt cards…
LoRA Manager for ComfyUI - A powerful extension for organizing, previewing, and integrating LoRA models with metadata and workflow support.
Agent Skill for turning Chinese classical poems into vertical Chinese-art videos with ImageGen stills, Docker I2V, calligraphy captions, retained ambience, BGM and final MP4 QA.
Agent skill: convert Chinese story copy or ordered images into a hand-drawn diary-comic animation (silent MP4 picture track).
Codex Skill for Eastern xianxia storyboards, camera movement and video continuity.
Codex Skill for cinematic Eastern xianxia stills, celestial realms and sky megastructures.