Krea2 Turbo - LM Studio Prompt Enhancer - 32GB Abliterated Workflow

A custom fork of ComfyUI-GGUF is required

I would suggest following these steps:

• Stop ComfyUI if it is running.

• Open your terminal and cd to ComfyUI/custom_nodes.

• Type the following command git clone https://github.com/RealRebelAI/ComfyUI-GGUF_KREA-2.git

• Restart ComfyUI

Once clone the custom node folder structure should look like this:

📂 ComfyUI/
├── 📂 custom_nodes/
│   ├── 📂 ComfyUI-GGUF_KREA-2/

Installing the LMStudio Prompt Enhancer custom node.

• Click the "Extensions" button at the top left hand corner of ComfyUI.

• Search for a Node Pack called "comfyui-lmstudio-prompt-enhancer "

• Install "comfyui-lmstudio-prompt-enhancer "

• Restart ComfyUI and refresh this page.

Learn more about this custom node

I found 2 models in LMStudio model catalogue that fit the 32GB or less requirement for this workflow they are:

• huihui-ornith-1.0-9b-abliterated-mtp you will want to set llm_max_tokens to 5000.

• meta-llama-3.1-8b-instruct-abliterated you will want to set llm_max_tokens to 2500.

🛈 IMPORTANT!!!

You will need to search for, download, and load the model huihui-ornith-1.0-9b-abliterated-mtp or meta-llama-3.1-8b-instruct-abliterated in LM studio. You will also need to start the API server and generate an API Key. Learn how to configure LM Studio here.

Notes for using this 32GB workflow

• If the image looks flat, check the logs in LM Studio, the last log entry will contain a JSON path x.choices[0].message.content if the content field is empty that means the LLM ran out of reasoning tokens, this can be resolved by increasing max_tokens.