AI-Toolkit LoRA Trainer

AI-Toolkit LoRA Trainer is an AI Engineering skill for Claude Code, published by artokun in comfyui-mcp.

659 stars103 forkson artokun/comfyui-mcpAdded 2026/08/24+9% in starsRepository updated 2026/08/24

agent-skillsai-agentclaude-codeclaude-plugincomfyuicomfyui-extensioncomfyui-mcpcomfyui-mcp-serverfluximage-generationlocal-firstmcpmcp-servermodel-context-protocolofflineollamaself-hostedstable-diffusionvideo-generationwan

Install in seconds

Install AI-Toolkit LoRA Trainer

Copy AI-Toolkit LoRA Trainer into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/artokun/comfyui-mcp/tree/main/plugin/skills/ai-toolkit-trainer ~/.claude/skills/ai-toolkit-trainer

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/artokun/comfyui-mcp.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: plugin/skills/ai-toolkit-trainer/SKILL.md in artokun/comfyui-mcp
Installs to: ~/.claude/skills/ai-toolkit-trainer
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What AI-Toolkit LoRA Trainer does

AI-Toolkit LoRA Trainer trains custom LoRAs with ostris AI-Toolkit for WAN 2.2/2.1 and Z-Image. Use it to prepare datasets, tune training settings, and generate a LoRA for use in ComfyUI.

AI-Toolkit LoRA Trainer is cataloged under AI Engineering on DirSkills. AI-Toolkit LoRA Trainer comes from a repository tagged agent-skills, ai-agent, claude-code, claude-plugin and comfyui.

Documentation

README

Excerpt

AI-Toolkit LoRA Trainer (WAN 2.2 & Z-Image)

Overview

AI-Toolkit by ostris is "the ultimate training toolkit for finetuning diffusion models" (MIT license) — a standalone trainer with its own web UI, NOT a ComfyUI custom node. It runs a Node.js UI front end over a Python (run.py) training backend, and trains LoRAs for many model families — here we cover WAN 2.2 / 2.1 video models and Z-Image (Turbo & Base).

Repo: https://github.com/ostris/ai-toolkit (cloned by the installers).
Backend: python run.py config/<job>.yml. UI: a Node.js app under ui/ that schedules/monitors jobs (you don't have to keep the UI open while a job runs).
Output: a standard .safetensors LoRA you drop into ComfyUI models/loras/ and load with LoraLoaderModelOnly.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about AI-Toolkit LoRA Trainer

What else does artokun publish alongside AI-Toolkit LoRA Trainer?
AI-Toolkit LoRA Trainer is one of 25 skills that DirSkills catalogs from artokun/comfyui-mcp, the repository it ships in. Its siblings there include Anima Base, Citron Anima LoRA Trainer and Civitai. Each one is a separate skill with its own page in this directory, installs the same way AI-Toolkit LoRA Trainer does, and is maintained by artokun in that same repository. The rest of the collection is listed on the artokun/comfyui-mcp page.
How does AI-Toolkit LoRA Trainer compare to other AI Engineering skills?
AI-Toolkit LoRA Trainer ranks #1831 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of AI-Toolkit LoRA Trainer against them. Open each page to compare what they document and how they install.