Instructions to use wiikoo/cf-1028 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wiikoo/cf-1028 with Diffusers:

pip install -U diffusers transformers accelerate

import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("wiikoo/cf-1028", dtype=torch.bfloat16, device_map="cuda")

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]

llama-cpp-python

How to use wiikoo/cf-1028 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="wiikoo/cf-1028",
	filename="clip/Qwen2.5-VL-7B-Abliterated-Caption-it.Q8_0.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use wiikoo/cf-1028 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf wiikoo/cf-1028:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf wiikoo/cf-1028:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf wiikoo/cf-1028:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf wiikoo/cf-1028:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf wiikoo/cf-1028:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf wiikoo/cf-1028:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf wiikoo/cf-1028:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf wiikoo/cf-1028:Q4_K_M

Use Docker

docker model run hf.co/wiikoo/cf-1028:Q4_K_M

LM Studio
Jan
Ollama
How to use wiikoo/cf-1028 with Ollama:
```
ollama run hf.co/wiikoo/cf-1028:Q4_K_M
```

Unsloth Studio

How to use wiikoo/cf-1028 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for wiikoo/cf-1028 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for wiikoo/cf-1028 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for wiikoo/cf-1028 to start chatting

Docker Model Runner
How to use wiikoo/cf-1028 with Docker Model Runner:
```
docker model run hf.co/wiikoo/cf-1028:Q4_K_M
```

Lemonade

How to use wiikoo/cf-1028 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull wiikoo/cf-1028:Q4_K_M

Run and chat with the model

lemonade run user.cf-1028-Q4_K_M

List all available models

lemonade list

wiikoo commited on Oct 28, 2025

Commit

f9bbc00

verified ·

1 Parent(s): 870c520

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -71

README.md CHANGED Viewed

@@ -1,71 +0,0 @@
----
-license: other
-tags:
-- comfyui
-- stable-diffusion
-- models
-- lora
-- controlnet
----
-# ComfyUI Models Collection
-Complete model collection for ComfyUI workflows.
-## 📊 Overview
-**Total Size**: ~363GB
-**Categories**: 40+ model types
-**Last Updated**: October 28, 2025
-## 📁 Directory Structure
-```
-models/
-├── LLM/                    # Large Language Models (46GB)
-├── checkpoints/            # SD Checkpoints (29GB)
-├── diffusion_models/       # Diffusion Models (62GB)
-├── clip/                   # CLIP Models (21GB)
-├── controlnet/             # ControlNet (5.7GB)
-├── loras/                  # LoRA Models
-├── vae/                    # VAE Models
-├── upscale_models/         # Upscalers
-└── ...                     # 30+ more categories
-```
-## 🚀 Quick Download
-```bash
-# Install HuggingFace CLI
-pip install -U "huggingface_hub[cli]"
-# Download specific category
-huggingface-cli download wiikoo/cf-1028 --include "models/loras/*" --local-dir ./
-# Download checkpoints
-huggingface-cli download wiikoo/cf-1028 --include "models/checkpoints/*" --local-dir ./
-```
-## 📋 Model Categories
-| Category | Size | Description |
-|----------|------|-------------|
-| **LLM** | 46GB | Qwen3-VL, Vision-Language models |
-| **Checkpoints** | 29GB | Stable Diffusion base models |
-| **Diffusion Models** | 62GB | Various diffusion architectures |
-| **CLIP** | 21GB | Text and vision encoders |
-| **ControlNet** | 5.7GB | Control models for SD |
-## 💡 Usage
-Download models to ComfyUI's models directory:
-```bash
-cd /path/to/ComfyUI
-huggingface-cli download wiikoo/cf-1028 models/ --local-dir ./
-```
----
-**Repository**: https://huggingface.co/wiikoo/cf-1028
-**Maintained by**: wiikoo