# trainer-integration

trainer-integration is a Claude Code skill for adding or refining LoRA training support for models in Draw Things. It covers trainer wiring, checkpoint export, and validation.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 171 repo stars
- Author: drawthingsai
- License: GPL-3.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/drawthingsai/local-code-community/tree/HEAD/.agents/skills/trainer-integration/SKILL.md
- Updated: 2026-11-17
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/trainer-integration

## What it does

The skill lays out a workflow for adding LoRA training paths for generative models available in Draw Things app and CLI. It covers model builders, trainer dispatch, tokenizer setup, and fixed encoders. Flux1 serves as the reference path; the workflow advises reusing only the pieces a model needs.

The checklist covers trainable-key selection in both the CLI and app, weight loading with the required model key and codec list, rotary handling, and attention backend checks. It also addresses numerical stability and LoRA checkpoint export. Qwen Image uses the Qwen 2.5 tokenizer, while Z Image uses Qwen 3.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add drawthingsai/local-code-community --skill trainer-integration -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/trainer-integration/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/trainer-integration/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add drawthingsai/local-code-community --skill trainer-integration -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/trainer-integration/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add drawthingsai/local-code-community --skill trainer-integration -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/trainer-integration/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install drawthingsai/local-code-community .agents/skills/trainer-integration
```

2. **Manually: put the files in place**
- File: `.github/skills/trainer-integration/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add drawthingsai/local-code-community --skill trainer-integration -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/drawthingsai/local-code-community --path .agents/skills/trainer-integration
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/trainer-integration/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/drawthingsai/local-code-community/tree/HEAD/.agents/skills/trainer-integration/SKILL.md

## When to use it
- add a LoRA training path for a Draw Things model
- align trainable-key selection between the CLI and app
- connect the model's tokenizer and fixed encoder
- check training numerics and LoRA checkpoint export

## Example prompts
- Add LoRA training for a new Draw Things model and use the Flux1 path as a reference.
- Check which tokenizer the Qwen Image training path needs.
- Find where to add version-specific model selection in the CLI and app.

## Similar
- [scenario-model-training](https://affpapa.org/en/nevibecode/skills/scenario-model-training.md) — skill · 929 installs
- [llm-integration](https://affpapa.org/en/nevibecode/skills/orchestkit-llm-integration.md) — skill · 218 installs
- [huggingface-llm-trainer](https://affpapa.org/en/nevibecode/skills/huggingface-llm-trainer.md) — skill · 2500 installs
- [huggingface-vision-trainer](https://affpapa.org/en/nevibecode/skills/huggingface-vision-trainer.md) — skill · 2100 installs
- [nemotron-customize](https://affpapa.org/en/nevibecode/skills/nemotron-customize.md) — skill · 2200 installs
- [ml-model-training](https://affpapa.org/en/nevibecode/skills/secondsky-ml-model-training.md) — skill · 484 installs

From the same set: [drawthingsai/local-code-community](https://affpapa.org/en/nevibecode/by/drawthingsai/local-code-community.md) — 20 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
