Hunyuan-PromptEnhancer/PromptEnhancer

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

3758 stars · 326 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

PromptEnhancer is a prompt-rewriting framework from Tencent Hunyuan that uses a Chain-of-Thought rewriter trained via reinforcement learning to refine user prompts into clearer, structured versions for text-to-image diffusion models. It enhances pretrained T2I models like HunyuanImage 2.1 without modifying their weights, and also supports image-to-image prompt editing.

Use cases

• rewrite short prompts into detailed structured prompts for image generation
• improve attribute binding and compositional accuracy in text-to-image outputs
• enhance prompts for HunyuanImage and other diffusion models without fine-tuning
• generate prompts for image-to-image editing workflows
• evaluate prompt-image alignment with the AlignEvaluator reward model

When to choose

• you use text-to-image models and get poor results from short or vague prompts
• you want prompt enhancement without retraining or modifying the image model
• you work with HunyuanImage 2.1 or compatible diffusion pipelines
• you need multilingual or text-in-image prompt refinement

When to avoid

• you need a general-purpose LLM prompt enhancer for text-only tasks
• you lack GPU resources to run the 7B rewriter model
• you need a lightweight CPU-only tool
• you require a permissive open-source license for commercial use

Facets

library · maturity active

prompt-engineering machine-learning nlp artificial-intelligence image-processing large-language-models python text-to-image prompt-rewriting chain-of-thought reinforcement-learning diffusion-models hunyuan vlm image-generation gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Hunyuan-PromptEnhancer/PromptEnhancer")