---
license: apache-2.0
language:
- en
pipeline_tag: text-to-image
tags:
- koji
- gguf-node
widget:
- text: "masterpiece, best quality, 1girl, yellow eyes, medium hair, stairs, cherry blossoms, temple, fox girl, detached sleeves, animal ears, happy, arms behind back, tail,"
  parameters:
    negative_prompt: "(worst quality, low quality:1.4),"
  output:
    url: samples\ComfyUI_00001_.png

- text: "masterpiece, best quality, 1girl, architecture, garden, city, looking at viewer,  upper body,"
  parameters:
    negative_prompt: "(worst quality, low quality:1.4),"
  output:
    url: samples\ComfyUI_00002_.png
---

# **gguf quantized version of koji (mini test pack)**

<Gallery />

### **setup (in general)**
- drag gguf file(s) to diffusion_models folder (./ComfyUI/models/diffusion_models)
- drag l-clip, to text_encoders folder (./ComfyUI/models/text_encoders)
- drag vae decoder to vae folder (./ComfyUI/models/vae)

### **run it straight (no installation needed way)**
- get the comfy pack with the new gguf-node [here](https://github.com/calcuis/gguf/releases)
- run the .bat file in the main directory

### **workflow**
- drag any workflow json file to the activated browser; or
- drag any generated output file (i.e., picture, video, etc.; which contains the workflow metadata) to the activated browser

### **review**
- mini model based on sd1
- small size; super fast; except quality issue, which is a good model for testing the node

### **reference**
- creator [ikena](https://civitai.com/user/Ikena)
- comfyui [comfyanonymous](https://github.com/comfyanonymous/ComfyUI)
- gguf-node ([pypi](https://pypi.org/project/gguf-node)|[repo](https://github.com/calcuis/gguf)|[pack](https://github.com/calcuis/gguf/releases))