PromptEnhancer is a GGUF prompt rewriting engine that loads quantized models to rewrite plain text prompts into clearer, structured versions while preserving the original subject, style, and layout. It is designed to refine image editing instructions by incorporating visual context from the input image, producing precise editing prompts.
The tool operates through a structured prompt rewriting engine that combines editing instructions with visual context from images, embedding that context into the rewriting process for context-aware refinement. It runs inference with a minimal memory footprint by leveraging quantized weights and optimized tensor operations, making it more resource-efficient than full-precision models.
PromptEnhancer supports two primary capabilities: rewriting plain text prompts for text-to-image generation and refining image editing instructions. Both functions preserve the original subject, style, and layout while producing clearer, more structured outputs. The project provides documentation for loading and running the GGUF model to enhance prompts.