Xiaoer Upscale

在 Mac 上把图片本地放大/提清晰度(超分辨率),并装好「Finder 右键 → 快速操作 → 超分 4K/8K」。 USE WHEN 用户说图片放大、超分、提清晰度、图糊了、做高清版、把这张图变清楚、 4K/8K 图、image upscale、super resolution、右键放大图片、Mac 右键超分。纯本地离线、不用 API key、不花钱(OpenCV dnn_superres,CPU 即可)。

33 stars 6 forksImages, Video & Audio

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add Jane-xiaoer/claude-skill-xiaoer-upscale --skill xiaoer-upscale

Manual install

git clone --depth 1 https://github.com/Jane-xiaoer/claude-skill-xiaoer-upscale.git /tmp/claude-skill-xiaoer-upscale
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skill-xiaoer-upscale/. ~/.claude/skills/xiaoer-upscale

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# 小耳超分 · Mac 本地图片超分 + 右键 4K/8K

把"图片放大/提清晰度"做成两种入口:命令行 `upscale` + Finder 右键。
**引擎 = OpenCV `dnn_superres`,在 CPU 上跑,不调任何 AI API、不用 key、不联网**(装完拔网也能用)。唯一联网 = 安装时下 3 个模型(~41MB)。

## 一键安装

```bash
bash scripts/install.sh
```

装完得到:
- **命令行**:`upscale 图片.jpg --8k`(别名 `超分`)
- **右键**:选图片 → 右键 → 快速操作 → **超分 4K / 8K / 极速4K**(后台跑、完成弹通知、不卡 Finder)

安装脚本做了 5 件事:建 venv 装 `opencv-contrib-python`+Pillow → 下 3 个模型 → 生成 CLI 壳 → 生成 3 个右键 `.workflow` → `pbs -flush` 注册。全用 `$HOME`,**不写死用户名**,别人照装即可。

## 命令行用法

```bash
upscale 图.jpg              # 默认满血 4x
upscale 图.jpg --4k         # 目标长边 3840
upscale 图.jpg --8k         # 目标长边 7680
upscale 图.jpg --16k        # 目标长边 15360(源不够大时为插值,非真细节)
upscale 图.jpg --long 5000  # 自定义长边
upscale 图.jpg --scale 2    # 相对原图 2 倍
upscale 图.jpg --model edsr # 换模型(默认 lapsrn)
```
输出 `原名_档次.jpg` 存到同目录,带轻度 unsharp 锐化。

## 三档模型(速度 / 质量 · CPU 无 GPU)

| 模型 | 右键档 | 速度(2K 源) | 质量 | 用途 |
|------|--------|------------|------|------|
| **fsrcnn** | 极速4K | ~0.5s | 稍软 | 快速预览 / 批量 |
| **lapsrn** | 4K / 8K | **~6 分钟** | 好 | 出片默认 |
| **edsr** | (仅 CLI) | ~8 分钟+ | 最好 | 极致质量少用,大图可能上小时/OOM |

**关键认知**:模型是 4x,真实细节上限 = 源图长边 ×4。**2K 源 → 4K/8K 是真提升;16K 基本是插值**(源撑不起)。源本身 4-5K 才谈得上真 16K。

## 右键设置 & 排障(别人在新 Mac 上最容易卡这里)

1. **右键没出现「超分」菜单项** → 系统设置(System Settings)→ 搜「扩展 / Extensions」或「访达 / Finder」→ 在"添加的扩展 / 访达"里**勾上** 超分 4K / 8K / 极速4K。装完 `pbs -flush` 一般会自动出现,这是兜底。*(旧版 macOS:系统偏好设置 → 扩展 → 访达扩展。)*
2. **菜单项藏在哪** → 选中图片右键 →「**快速操作 / Quick Actions**」子菜单里(条目多时会折叠进这里,不在最外层)。

Read the full skill on GitHub

Details

Skill name: xiaoer-upscale
Repository: Jane-xiaoer/claude-skill-xiaoer-upscale
License: MIT
Repo updated: 15 July 2026

FAQ

What does the Xiaoer Upscale skill do?

How do I install the Xiaoer Upscale skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add Jane-xiaoer/claude-skill-xiaoer-upscale --skill xiaoer-upscale. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Xiaoer Upscale popular?

It lives in Jane-xiaoer/claude-skill-xiaoer-upscale, which has 33 GitHub stars and 6 forks.

Related skills

Interflow Video Cut

derek-zhuolin/interflow-video-cut

Turn a local talking-head / 口播 video into metadata, transcript, and an AI-composed card-based video where the agent composes cards by cloning styled templates and filling them (designing bespoke only when content needs it), then renders to MP4. Ships with the Interflow AI club sign-off ("Interflow AI 出品"). Use when the user asks for interflow-video-cut, 口播成片, talking-head repurposing, video takeaways, transcript cleanup, or turning a spoken video into a captioned card video.

Images, Video & Audio

Awwwards 3d

tsogjavklann/awwwards-3d

Build production-grade Awwwards-style scroll-driven 3D websites in the visual language of Active Theory, Lusion, 14islands, Bonhomme, Resn, Studio Freight, Locomotive, and Igloo Inc. Use when the user asks for an "Awwwards-style", "scroll-driven 3D", "WebGL hero", "3D landing page", "interactive product showcase", "scroll storytelling site", "cinematic web experience", "creative dev portfolio", "premium 3D site", "Lusion-style", "Active Theory-style", "scroll 3D animation", or mentions Three.js + GSAP + Lenis together. Also triggers on Mongolian phrases like "3D вэб", "scroll-тэй 3D", "premium

Images, Video & Audio

Factory

AirsupHQ/factory-skill

Turn a one line description of a factory ("a line that makes 2,000 e-bike motors a day", "a bakery that bakes 10,000 croissants an hour", "a battery cell gigafactory") into a single self-contained HTML page with a live 3D tilt-shift miniature of that factory, driven by a real discrete event simulation (stations, cycle times, batches, finite buffers, shifts, breakdowns, scrap) with a live HUD for throughput against target, takt, utilization, WIP, lead time and the bottleneck, where clicking a station lets you add a machine or change a cycle time and watch the bottleneck move. Use it whenever so

Images, Video & Audio

Data Master

MAGA2010/data-master

Analyze datasets with preserved raw inputs, explicit cleaning decisions, reproducible figures and PDF reports. Full statistics for one tabular file; descriptive time-series analysis; integrity profiling for text, image, audio, geographic and mixed inputs. Use for data cleaning, EDA, group comparisons, statistical reports, 跑数据 or 数据分析 with a traceable evidence trail.

Images, Video & Audio

Animated Sketch Diagram

OLDyade/animated-sketch-diagram

生成"黑墨手绘涂鸦"风格的动画架构图/流程图：米色纸面、针管笔墨线、极淡水洗色块、简笔涂鸦图标、序号章、连线上的流动圆点动画、图标微动效。产出单文件自包含动画 HTML（SVG+CSS），可一键导出无缝循环 GIF。当用户想画架构图、流程图、信息图、技术示意图、对比图、pipeline/workflow 可视化，或提到"手绘风""涂鸦风""动图""animated diagram""GIF 架构图"时使用；即使用户没明说要动画，做技术概念科普配图时也应优先考虑本 skill。

Images, Video & Audio

Cxp Character Forge

CXP-2024/cxp-character-forge

从参考立绘通过 Tripo 兼容代理生成带贴图的 3D 人物，接续 Blender 外形检查、组件修整、按需绑骨动作与资产交付。用于人物建模和已有生成任务续作。

Images, Video & Audio

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.