Hunyuan-PromptEnhancer/PromptEnhancer

PromptEnhancer is a prompt-rewriting tool, refining prompts into clearer, structured versions for better image generation.

54
/ 100
Established

Employs chain-of-thought reasoning to decompose prompts into structured components (subject, action, style, attributes), with support for both T2I and image-to-image editing modes via specialized 7B/32B language models. Integrates with HunyuanImage and supports multiple deployment options including full-precision, GGUF-quantized (Q4/Q6/Q8), and vision-language variants for efficient inference across GPU memory constraints. Includes a T2I-Keypoints-Eval benchmark for evaluating semantic preservation across prompt rewriting.

3,648 stars.

No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 19 / 25

How are scores calculated?

Stars

3,648

Forks

314

Language

Python

License

Last pushed

Jan 26, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/Hunyuan-PromptEnhancer/PromptEnhancer"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.