# Model Registry

Curated download URLs and target directories, organized by family (Flux, WAN, LTX...

- Repository: https://github.com/artokun/comfyui-mcp (883 stars)
- Category: AI and agents
- License: MIT
- Last updated: 2026-10-26
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add artokun/comfyui-mcp --skill model-registry -g -a claude-code -y`
Codex: `npx skills add artokun/comfyui-mcp --skill model-registry -g -a codex -y`
Cursor: `npx skills add artokun/comfyui-mcp --skill model-registry -g -a cursor -y`
Gemini CLI: `npx skills add artokun/comfyui-mcp --skill model-registry -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add artokun/comfyui-mcp`

## Description

Curated download URLs and target directories, organized by family (Flux, WAN, LTX, Qwen, Z-Image, SD15/SDXL), for every model the comfyui-mcp skills reference, covering checkpoints, VAEs, text encoders, and LoRAs. Use when downloading models with download_model (action:"download" / action:"download_civitai"), when a workflow fails with a missing-model error, or when setting up a new machine.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Model Registry

One table per family: filename → source URL → target subdir under
`<COMFYUI>/models/`. Use with `download_model({ action: "download", url, target_subfolder, filename })`.
This registry grows with every release. If a model you need is missing, use
`action:"search"` (HuggingFace) or `action:"download_civitai"` and consider
contributing the row.

**Quant column (kitchen).** Filenames in this registry are mostly bf16 / fp8. NVFP4 and MXFP8 siblings, when a vendor publishes them, are the same stem with `nvfp4` / `mxfp8` in the name and belong in `diffusion_models/` too. `kitchen` action:"assess" only offers an NVFP4 swap when that sibling is **already listed locally**, it does not guess a URL from the filename. Blackwell (SM ≥ 10.0) is the GPU that can run NVFP4 / MXFP8 compute.

**Conventions**
- HF "resolve" URLs download directly: `https://huggingface.co/<repo>/resolve/main/<path>`
- 🔒 = gated repo, needs `HUGGINGFACE_TOKEN` (accept the license on the HF page first)
- CivitAI model-page URLs need `download_model` `action:"download_civitai"` (resolves version → file); raw `civitai.com/api/download/...` URLs work with `action:"download"` + `CIVITAI_API_TOKEN`
- Always verify the exact filename a workflow's loader expects. The `model-compatibility` skill covers which VAE/CLIP pairs with which architecture

## Shared VAEs & text encoders (download these once)

The rest: https://github.com/artokun/comfyui-mcp/blob/HEAD/plugin/skills/model-registry/SKILL.md