model-registry

1# Model Registry
2 
3One table per family: filename → source URL → target subdir under
4`<COMFYUI>/models/`. Use with `download_model({ action: "download", url, target_subfolder, filename })`.
5This registry grows with every release. If a model you need is missing, use
6`action:"search"` (HuggingFace) or `action:"download_civitai"` and consider
7contributing the row.
8 
9**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.
10 
11**Conventions**
12- HF "resolve" URLs download directly: `https://huggingface.co/<repo>/resolve/main/<path>`
13- 🔒 = gated repo, needs `HUGGINGFACE_TOKEN` (accept the license on the HF page first)
14- 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`
15- Always verify the exact filename a workflow's loader expects. The `model-compatibility` skill covers which VAE/CLIP pairs with which architecture
16 
17## Shared VAEs & text encoders (download these once)
18 
19| File | Source | Target |
20|---|---|---|
21…