A custom node for ComfyUI that expands text prompts using the SuperPrompt-v1 T5 model. This node helps generate more detailed and descriptive prompts from simple input text, which can be particularly useful for image generation workflows.

• Expands simple prompts into more detailed descriptions
• Configurable generation parameters
• Optional removal of incomplete sentences
• GPU acceleration support (when available)
• Automatic model downloading and caching

• Python 3.x
• PyTorch
• Transformers
• ComfyUI

1. Install ComfyUI if you haven't already
2. Clone this repository into your ComfyUI custom nodes directory:

cd ComfyUI/custom_nodes/
git clone https://github.com/your-username/ComfyUI-Prompt-Expander.git

3. Install the required dependencies:

pip install -r requirements.txt

1. After installation, restart ComfyUI
2. In the node menu, find the "Prompt Expander" node under the "text" category
3. Connect the node to your workflow

• prompt (STRING): The input text you want to expand
• max_new_tokens (INT): Maximum number of new tokens to generate (1-2048, default: 512)
• repetition_penalty (FLOAT): Penalty for repetition in generated text (0.0-2.0, default: 1.2)
• remove_incomplete_sentences (BOOLEAN): Whether to remove incomplete sentences from the output (default: True)

Input prompt: "a beautiful girl" Output: [The model will generate a more detailed description of the scene]

This node uses the roborovski/superprompt-v1 model, which will be automatically downloaded on first use and cached in the user's home directory under .models/.

[Your License Here]

• Model: roborovski/superprompt-v1
• https://github.com/NeuralSamurAI/Comfyui-Superprompt-Unofficial