Instructions to use UmeAiRT/ComfyUI-Auto-Installer-Assets with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use UmeAiRT/ComfyUI-Auto-Installer-Assets with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("UmeAiRT/ComfyUI-Auto-Installer-Assets", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
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