OpenParable
Skip to content
← Back to skills

Model Registry

Apps & Automation
model-registry

Model Registry is an Agent Skill for apps & automation published in the artokun/comfyui-mcp repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

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

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/artokun/comfyui-mcp/blob/HEAD/plugin/skills/model-registry/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/model-registry, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Model Registry

One table per family: filename → source URL → target subdir under <COMFYUI>/models/. Use with download_model(url, target_subfolder, filename). This registry grows with every release — if a model you need is missing, use search_models (HuggingFace) or download_civitai_model and consider contributing the row.

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_civitai_model (resolves version → file); raw civitai.com/api/download/... URLs work with download_model + CIVITAI_API_TOKEN
  • Always verify the exact filename a workflow's loader expects — model-compatibility skill covers which VAE/CLIP pairs with which architecture

Shared VAEs & text encoders (download these once)

FileSourceTarget
ae.safetensors (Flux/Z-Image VAE)huggingface.co/black-forest-labs/FLUX.1-schnell/resolve/main/ae.safetensors (Apache, not gated)vae/
vae-ft-mse-840000-ema-pruned.safetensors (SD1.5 VAE)huggingface.co/stabilityai/sd-vae-ft-mse-original/resolve/main/vae-ft-mse-840000-ema-pruned.safetensorsvae/
clip_l.safetensorshuggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensorstext_encoders/
t5xxl_fp8_e4m3fn.safetensorshuggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp8_e4m3fn.safetensorstext_encoders/
umt5_xxl_fp8_e4m3fn_scaled.safetensors (WAN)huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensorstext_encoders/

Flux (see flux-txt2img skill for workflows)

FileSourceTarget
flux1-dev.safetensors 🔒huggingface.co/black-forest-labs/FLUX.1-devdiffusion_models/
flux1-schnell.safetensorshuggingface.co/black-forest-labs/FLUX.1-schnell/resolve/main/flux1-schnell.safetensorsdiffusion_models/
flux2-vae.safetensors (Flux 2 Klein)huggingface.co/Comfy-Org/flux2-klein — check repo for current pathvae/

WAN 2.x video (see wan-t2v-video / wan-flf-video skills)

Comfy-Org repackages everything: huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged under split_files/.

FilePath in repoTarget
wan2.2_i2v_high_noise_14B_fp8_scaled.safetensorssplit_files/diffusion_models/diffusion_models/
wan2.2_i2v_low_noise_14B_fp8_scaled.safetensorssplit_files/diffusion_models/diffusion_models/
wan_2.1_vae.safetensorssplit_files/vae/vae/
wan2.2_i2v_lightx2v_4steps_lora_v1_high_noise.safetensorssplit_files/loras/loras/
wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensorssplit_files/loras/loras/
Magical-morph I2V LoRAs (high/low)huggingface.co/NikolaSigmoid/wan2.2-i2v-loras-magical-morphloras/
SkinMorph Redmond I2V 14Bcivitai.com/models/2210162 (use download_civitai_model)loras/

LTX-2 19B video (see ltxv2-video skill)

FileSourceTarget
ltx-2-19b-distilled.safetensorshuggingface.co/Lightricks/LTX-2 — check repo for the bf16 distilled pathcheckpoints/
gemma_3_12B_it_fp4_mixed.safetensorshuggingface.co/Comfy-Org LTX repackagetext_encoders/
ltx-2-spatial-upscaler-x2-1.0.safetensorshuggingface.co/Lightricks/LTX-2upscale_models/
Camera-control LoRAs (dolly-left, distilled-384)huggingface.co/Lightricks/LTX-2 LoRA dirloras/

Qwen-Image (see qwen-txt2img / qwen-image-edit skills)

FileSourceTarget
qwen_image_fp8_e4m3fn.safetensorshuggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/diffusion_models/qwen_image_fp8_e4m3fn.safetensorsdiffusion_models/
qwen_2.5_vl_7b_fp8_scaled.safetensorssame repo, split_files/text_encoders/text_encoders/
qwen_image_vae.safetensorssame repo, split_files/vae/vae/
qwen_image_edit_2511_bf16.safetensorshuggingface.co/Comfy-Org/Qwen-Image-Edit_ComfyUI — check repodiffusion_models/
Qwen-Image 2512 Lightning LoRAhuggingface.co/lightx2v/Qwen-Image-2512-Lightningloras/
Qwen-Image-Edit 2511 Lightning LoRAhuggingface.co/lightx2v/Qwen-Image-Edit-2511-Lightningloras/
Qwen-Image 2512 Turbo LoRAhuggingface.co/Wuli-art/Qwen-Image-2512-Turbo-LoRAloras/

Z-Image (see z-image-txt2img skill)

FileSourceTarget
z_image_turbo_bf16.safetensorshuggingface.co/Comfy-Org/z_image_turbo — check repo for split_files pathdiffusion_models/
z_image_base_bf16.safetensorssame family repodiffusion_models/
qwen_3_4b.safetensors (Z-Image text encoder)Comfy-Org repackage, split_files/text_encoders/text_encoders/

SDXL / SD1.5 community checkpoints (CivitAI)

Use download_civitai_model(model_id) — it resolves the latest version and handles auth:

ModelCivitAI
RedCraft RedZ ImageDXcivitai.com/models/958009
(2027494 entry in model-settings.json)civitai.com/models/2027494
Copax Timelesscivitai.com/models/copaxTimeless (search by name)

Failure modes

  • 404 on an HF resolve URL — the repo restructured. Open the repo page, find the file under "Files", and rebuild the resolve URL.
  • 401/403 — gated repo: set HUGGINGFACE_TOKEN after accepting the license, or CIVITAI_API_TOKEN for early-access CivitAI files.
  • Wrong dropdown after download — file landed in the wrong models/ subdir; check the Target column and model-compatibility.
  • Downloads resume automatically on retry (HTTP Range) — re-run the same download_model call after a network drop.