Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add MCKRUZ/ComfyUI-Expert --skill comfyui-lora-traininggit clone --depth 1 https://github.com/MCKRUZ/ComfyUI-ExpertWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mckruz/comfyui-expert/comfyui-lora-training)<a href="https://agentmods.dev/skills/mckruz/comfyui-expert/comfyui-lora-training"><img src="https://agentmods.dev/badge/skills/mckruz/comfyui-expert/comfyui-lora-training/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mckruz/comfyui-expert/comfyui-lora-training"><img src="https://agentmods.dev/badge/skills/mckruz/comfyui-expert/comfyui-lora-training.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00058 | $0.02048 |
| Opus 5 | $0.00029 | $0.01024 |
| Sonnet 5 | $0.00012 | $0.00410 |
| Haiku 4.5 | $0.00006 | $0.00205 |
Grade A, and why
comfyui-lora-training scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ComfyUI LoRA Training
Guide the user through dataset preparation, training configuration, and evaluation for character LoRAs.
When to Train vs Zero-Shot
| Scenario | Recommendation |
|---|---|
| Need absolute consistency across many images | Train LoRA |
| Building a character series or ongoing project | Train LoRA |
| Quick one-off generation | Use zero-shot (InstantID/PuLID) |
| Limited references (1-5 images) | Use zero-shot |
| Testing concepts | Use zero-shot first, train if committing |
Training Pipeline
1. DATASET PREP
|-- Collect/generate 15-30 reference images
|-- Preprocess (crop, resize, diversify styles)
|-- Caption with trigger word + descriptions
|
2. CONFIGURE TRAINING
|-- Select training tool (Kohya/AI-Toolkit/FluxGym)
|-- Set hyperparameters based on model type
|-- Configure checkpointing
|
3. TRAIN
|-- Monitor loss curve
|-- Save checkpoints every 250-500 steps
|
4. EVALUATE
|-- Test each checkpoint with identical prompts
|-- Check identity accuracy, flexibility, overfitting
|-- Select best checkpoint
|
5. INTEGRATE
|-- Copy to ComfyUI models/loras/
|-- Update character profile with trigger word + strength
|-- Test in full workflow (LoRA + identity method)
Dataset Preparation
Image Requirements
| Aspect | Minimum | Optimal | Maximum |
|---|---|---|---|
| Count | 10-15 | 20-30 | 50+ |
| Resolution | 512x512 | 1024x1024 | - |
| Format | PNG/high JPEG | PNG | - |
Content Diversity Checklist
- Multiple angles (front, 3/4, profile, back)
- Various expressions (neutral, smile, serious, laugh, etc.)
- Different lighting conditions (studio, natural, dramatic)
- Varied backgrounds (or transparent/solid)
- Multiple outfits/contexts
- Some close-ups, some medium shots
- If from 3D renders: include style variations (see below)
Preprocessing 3D Renders
Problem: Training directly on 3D renders bakes in the "3D" aesthetic.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 264 lines · 58 tokens per session scan A 20e773ffe290
comfyui-lora-training is a skill published in the GitHub repository MCKRUZ/ComfyUI-Expert (91 stars, last pushed 5mo ago), licensed MIT. It adds 58 tokens to every session and 2,048 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
Prompt craft for ComfyUI generation
Use when writing prompts for ComfyUI image or video models: choosing tags vs literary format, fixing composition and anatomy artifacts, picking samplers per LoRA, and writing short movement prompts for video. Neutral examples only.
emotion-to-camera-language
A guide for turning vague visual feelings—such as cinematic, atmospheric, elegant, or healing—into concrete image or video prompt details. It uses lighting direction, depth of field, camera position, and the subject’s state.
flux-txt2img
Build Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader patterns.
prompt-engineering
ComfyUI prompt engineering knowledge covering CLIP text encoding syntax, weight modifiers, model-specific prompting strategies, and best practices.
civitai
Discover Civitai models with the BUILT-IN downloadmodel action:"searchcivitai" and install/generate them locally. Find a checkpoint/LoRA/embedding on Civitai, download it into ComfyUI, and use its trigger words. Optionally pair the official Civitai MCP for community features (images browsing, posting, collections).
higgsfield-seedance
Rewrites scene descriptions using professional cinematography language, structures prompts with a six-slot formula (camera + subject + action + setting + style + lighting), and diagnoses content filter rejections via a preflight linter. Use whenever the user asks for a Seedance 2.0 / Seedance Pro prompt, describes a…