prompt-generator-comfyui

prompt-generator-comfyui

Dynamic JSON Badge Dynamic JSON Badge

Custom AI prompt generator node for ComfyUI. With this node, you can use text generation models to generate prompts. Before using, text generation model has to be trained with prompt dataset or you can use the pretrained models.

Table Of Contents

• prompt-generator-comfyui
• Table Of Contents
• Setup
  • For Portable Installation of the ComfyUI
  • For Manual Installation of the ComfyUI
  • For ComfyUI Manager Users
• Features
• Example Workflow
• Pretrained Prompt Models
  • Dataset
  • Models
• Variables
  • Quantization
  • Random Generation
  • Lock The Generation
  • How Recursive Works?
  • How Preprocess Mode Works?
    • Example
• Troubleshooting
  • Package Version
    • For Manual Installation of the ComfyUI
    • For Portable Installation of the ComfyUI
  • New Updates On The Node
  • Quantize Values Are Not Updated
• Contributing
• Example Outputs

Setup

For Portable Installation of the ComfyUI

1. Clone the repository with git clone https://github.com/alpertunga-bile/prompt-generator-comfyui.git command under custom_nodes folder
2. Go to the ComfyUI_windows_portable folder and install the required packages with .\python_embeded\Scripts\python.exe -s -m pip install -r .\ComfyUI\custom_nodes\prompt-generator-comfyui\requirements.txt command
3. Put your generator under the models/prompt_generators folder. You have to put generator as folder. Do not just put pytorch_model.bin file for example.
4. Go to the ComfyUI_windows_portable folder and run the run_nvidia_gpu.bat file
5. Open the hires.fixWithPromptGenerator.json or basicWorkflowWithPromptGenerator.json workflow

For Manual Installation of the ComfyUI

1. Clone the repository with git clone https://github.com/alpertunga-bile/prompt-generator-comfyui.git command under custom_nodes folder.
2. Activate the virtual environment if there is one and install the required packages with pip install -r requirements.txt command
3. Put your generator under the models/prompt_generators folder. You have to put generator as folder. Do not just put pytorch_model.bin file for example.
4. Open the hires.fixWithPromptGenerator.json or basicWorkflowWithPromptGenerator.json workflow

For ComfyUI Manager Users

1. Download the node with ComfyUI Manager
   • The required packages are installed automatically when installing the node.
2. Put your generator under the models/prompt_generators folder. You have to put generator as folder. Do not just put pytorch_model.bin file for example.
3. Open the hires.fixWithPromptGenerator.json or basicWorkflowWithPromptGenerator.json workflow

Features

• Multiple output generation is added. You can choose from 5 outputs with the