New Version of DataSet-Prepare-Gemini

Table of Contents

1. Configuration
2. Run The Workflow!

plz read this guid for lora training ,

https://civitai.com/articles/7365/flux-lora-training-low-gpu-kohya-ssdscript-linux

I have prepared this tool and the node to be highly accurate and fast. Let’s get started!

Clone the Repository

First, clone this repository into your ComfyUI’s custom_nodes directory:

cd /path/to/ComfyUI/custom_nodes
git clone https://github.com/al-swaiti/ComfyUI-OllamaGemini

Install Required Dependencies

Ensure you have the necessary dependencies installed:

pip install google-generativeai requests vtracer

Configuration

1. Gemini API Key Setup

• Get your free API key from Google AI Studio.
• Create a new API key or use an existing one.
• Copy the API key.
• Add your API key to the config.json file in the node directory:

{
    "GEMINI_API_KEY": "your_api_key_here"
}

2. DataSet Setup

• Lora Key-word: Define your LoRA keyword (e.g., goldxxx). This keyword will be used in image generation.
• Image Location: Specify the directory where your dataset images are stored.
• Enable Auto-Queue: Ensure automatic queuing for a seamless workflow.

Run The Workflow!

Once everything is set up, execute your workflow and generate high-quality outputs!

If you’re satisfied with this setup, get even more enhancements with:

• My Special Merge of Flux
• GGUF Format
• BNB-NF4
• FP8 Precision

This combination ensures maximum performance and efficiency for AI-driven image generation. 🚀for