train-character-lora SKILL.md skillA
train-character-lora from artokun/comfyui-mcp is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add artokun/comfyui-mcp/train-character-lora@git:20260825.ea35391Pins git:20260825.ea35391 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- artokun/comfyui-mcp
- Path
plugin/skills/train-character-lora/SKILL.md- Versions recorded
- 4
- Latest version
- git:20260825.ea35391, committed Aug 25, 2026
- First version recorded
- Jul 21, 2026
- Size
- 5,239 bytes
- Repository stars
- 896
- License
- MIT
Train a character/identity LoRA locally on FLUX.1-dev via the comfyui-mcp train_* tools (GPU Docker + ostris ai-toolkit). Use when the user wants to train a LoRA of a person/character from their photos on the local GPU. Covers dataset prep, launch, monitoring, and using the result in ComfyUI. For WAN/Z-Image training via the ai-toolkit UI see ai-toolkit-trainer.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Train a Character LoRA (local, Flux.1-dev)
## Overview
The trainer runs ostris ai-toolkit's `run.py` inside a headless GPU Docker container,
driven through the three `train_*` MCP tools. You (the LLM) are the UI. Each takes
an `action`: `train_prepare_dataset` owns the datasets, `train_start` owns the jobs, and
`train_doctor` owns the trainer itself. You generate the dataset, launch the job, watch
progress, and the finished LoRA lands in ComfyUI `models/loras/` and the LoRA catalog
without further steps.
- Base model: FLUX.1-dev (the best proven character consistency; needs ~24GB VRAM with
quantization, RTX 4090 class).
- Phase-1 scope: character LoRAs only. Style/slider/edit and other bases come later.
## The flow (tool sequence)
1. `train_doctor {action:"doctor"}`. Preflight once per session. Checks docker daemon,
`--gpus all` GPU passthrough, trainer image, HF_TOKEN. If `image:false`, run
`train_doctor {action:"build_image"}` (one-time, several minutes, since it builds CUDA
plus torch plus ai-toolkit). If `hfTokenSet:false`, warn the user: the first run
downloads FLUX.1-dev (gated HF repo) and needs `HF_TOKEN` in the MCP server env.
…Read the whole file at its exact version.
How to install
mdr add artokun/comfyui-mcp/train-character-lora@sha256:76e6643f948283d8The line at the top of this page pins the label git:20260825.ea35391, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_efwgjx4mwxhjfzbn)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Jul 21, 2026 and Aug 25, 2026, about one every 12 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260825.ea35391 latest | 2026-08-25 | ea35391 | 5,239 B | A | view · diff |
| git:20260819.9fe9ea3 | 2026-08-19 | 9fe9ea3 | 5,330 B | A | view · diff |
| git:20260806.68e5efc | 2026-08-06 | 68e5efc | 5,147 B | A | view · diff |
| git:20260721.3a871de | 2026-07-21 | 3a871de | 4,798 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5239 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
artokun/comfyui-mcp · 896 stars · license MIT · pushed 2026-11-04 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_efwgjx4mwxhjfzbn GET https://markdownregistry.com/api/v1/resolve?ref=artokun/comfyui-mcp/train-character-lora GET https://markdownregistry.com/api/v1/blob/76e6643f948283d815edeff0b0b0c94dc0b48c2c9e3698fa0e49cb0024410e4b
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.