UmeAiRT's picture
Add AGENTS.md
a4dcf32 verified
|
Raw
History Blame
2.2 kB

AGENTS.md — ComfyUI-Auto_installer-Assets

Purpose

Pure assets repository (HuggingFace LFS) for model files and installation binaries used by ComfyUI-Auto_installer. No code — only large binary files.

Ecosystem

This repo is consumed by the Auto_installer project's PowerShell download scripts. Any file rename or move here must be reflected in the corresponding download scripts.

Folder Structure

Folder Contents Notes
models/diffusion_models/ Backbone models (GGUF + safetensors) Official ComfyUI folder. Organized by family (FLUX/, WAN/, etc.)
models/text_encoders/ Text encoders (T5, QWEN, GEMMA, LLAMA) Official ComfyUI folder. NOT clip/
models/clip/ CLIP models only (clip_l, clip_g, ViT, longclip) Legacy alias of text_encoders/. Do NOT put text encoders here
models/checkpoints/ Full merged checkpoints
models/loras/ LoRA adapters
models/vae/ VAE models (transverse, shared across families)
models/controlnet/ ControlNet models
models/xlabs/ XLabs custom node models ⚠️ Hardcoded path — do NOT move
models/onnx/ ONNX upscalers for TensorRT ⚠️ Hardcoded path — do NOT move
bin/ Installation executables (Git, Python, CUDA, etc.)
whl/ Pre-compiled Python wheels
packages/ Zip archives (extensions, build tools, configs)

Naming Conventions

GGUF files — Follow the official GGUF spec

Format: <BaseName>-<SizeLabel>-<FineTune>-<Encoding>.gguf

  • CamelCase BaseName: Flux1, Wan2.1, HiDream, LTXV, LTX-2, Qwen
  • Uppercase SizeLabel: 14B, 1.3B, 13B
  • Uppercase Encoding: Q4_K_S, Q8_0, Q6_K
  • Hyphens between components

Examples: Flux1-Dev-Q4_K_S.gguf, Wan2.2-T2V-HighNoise-14B-Q8_0.gguf

Safetensors files — Community convention

  • Lowercase with hyphens as separators
  • Precision suffixes: fp16, bf16, fp8_e4m3fn, fp8_scaled

Examples: wan2.1-t2v-14b-fp16.safetensors, qwen-image-edit-fp8_e4m3fn.safetensors