Token导航 LogoToken导航TokenDH.com
效率需要联网clawhub未标认证来源可访问clear审计提醒

lora-pipeline劳拉管道

Agent Skill

lora-pipeline 用于处理浏览器自动化、网页检查和页面信息提取,适合在 OpenClaw 中需要让 Agent 打开页面、读取网页或验证前端流程时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

7,980

周安装

326

GitHub Stars

公开资料未说明

下载量

2,582
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:lora-pipeline(劳拉管道)
来源仓库:https://github.com/iskwang/lora-pipeline
安装命令:
openclaw skills install lora-pipeline
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install lora-pipeline

简介

管理端到端 LoRA 训练:收集和验证照片、抓取数据集、应用质量检查、字幕并在本地训练 LoRA 模型。

SKILL.md

name
lora-pipeline
description
End-to-end LoRA training pipeline: reference photo collection → face verification → dataset scraping → quality check → WD14 captioning → RunPod training. Use this skill whenever a user asks to build a training dataset, collect photos for a LoRA, or train a LoRA model.

LoRA Pipeline

Orchestrates the full LoRA dataset-to-model pipeline. Each phase is self-contained and can be delegated to a sub-agent independently.


Pipeline Overview

Phase 1: 蒐集範例照片   → collect 3–6 reference face photos
Phase 2: 確認人臉正確   → user confirms refs; deepface cross-check
Phase 3: 蒐集 datasets  → scrape web sources guided by face features
Phase 4: 確認照片正確   → face verify + dedup + quality filter + crop
Phase 5: 開始 caption   → WD14 local tagging + trigger word
Phase 6: LoRA training  → RunPod Kohya training → retrieve outputs

Phase Index

PhaseFileCan Sub-AgentModelEst. Time
01 — Reference Collectionphases/01-reference.mdHaiku (Worker)5–10 min
02 — Scrapingphases/02-scraping.mdHaiku (Worker)10–30 min
03 — Verify & Cleanphases/03-verify.mdHaiku (Worker)2–5 min
04 — Captionphases/04-caption.mdHaiku (Worker)1–3 min
05 — Trainingphases/05-training.mdHaiku (Worker) + Sentry15–30 min

To load a specific phase: read skills/lora-pipeline/phases/<phase-file> — each file is independently readable.


Directory Structure

~/.openclaw/workspace/
└── datasets/
    ├── face_references/
    │   └── <lora_name>/          # Phase 1–2: Gold standard refs (3–6 photos)
    │       ├── ref_01.jpg
    │       └── ...
    ├── <lora_name>_raw/          # Phase 3: Raw scraped images (pre-verification)
    │   └── ...
    └── <lora_name>/              # Phase 4–5: Verified + captioned training set
        ├── image001.png
        ├── image001.txt
        └── ...

Privacy Rules (CRITICAL — All Phases)

  • NO DATA INSPECTION: Do NOT cat, read, or analyze image file contents or .txt caption files.
  • NO CLOUD UPLOAD: All face verification (DeepFace) must run locally. Never send images to cloud APIs.
  • NO DATA LEAKAGE: Do not describe dataset details (person names, attributes) to the LLM unnecessarily.
  • Treat datasets as opaque binary blobs except when running local scripts.

Quality Standards (SDXL)

  • Resolution: 1024×1024 minimum after crop
  • Format: Convert all to PNG before training
  • No black borders: Run autocrop before final save
  • Dataset diversity: ≥30% clothed/natural skin shots

Scripts

ScriptLocationPurpose
tag_batch.pyskills/lora-pipeline/scripts/tag_batch.pyLocal WD14 ONNX tagger for a directory
smart_crop.pyskills/lora-pipeline/scripts/smart_crop.pyInteractive or automated single-subject cropping
batch_lora_train.pyskills/lora-pipeline/scripts/batch_lora_train.pyKohya batch training runner for RunPod

Sub-Agent Protocol

Each phase file contains:

  1. Input Contract — what must already exist before this phase starts
  2. Output Contract — what this phase produces
  3. Completion Signal — how to report back (sessions_send + status file fallback)
  4. Error Escalation — sub-agent reports to parent, never self-escalates model tier

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

78.51%
按下载量换算2,027

安全审计

VirusTotal

可疑

ClawScan

可疑

Static analysis

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills