# Hunyuan-PromptEnhancer/PromptEnhancer

[CVPR 2026] PromptEnhancer is a prompt-rewriting tool, refining prompts into clearer, structured versions for better image generation.

Repository: https://github.com/Hunyuan-PromptEnhancer/PromptEnhancer
Canonical: https://ross.abutalabs.com/products/promptenhancer
Homepage: https://hunyuan-promptenhancer.github.io/
Language: Python
License: NOASSERTION
License Family: other
Topics: prompt, prompt-engineering, prompt-enhancer, hunyuan, vlm, hunyuan-image, image-editing, image-to-image, text-to-image
Last push: 2026-08-18T03:09:57+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 35, longevity 25
- inputs: {"age_days": 358, "days_push": 15, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3758, forks 326 (observed 2026-08-28T04:08:17.854792+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: prompt-engineering, machine-learning, nlp
- domain: artificial-intelligence, image-processing, large-language-models
- platform: python
- tags: text-to-image, prompt-rewriting, chain-of-thought, reinforcement-learning, diffusion-models, hunyuan, vlm, image-generation, gpu, linux

## Member repositories
- Hunyuan-PromptEnhancer/PromptEnhancer (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:17.854792+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:28:55.191334+00:00, confidence not recorded.
  - readme: https://github.com/Hunyuan-PromptEnhancer/PromptEnhancer (fetched 2026-08-28T04:08:17.854792+00:00, sha 66b2571ad86c)
  - homepage: https://hunyuan-promptenhancer.github.io/ (fetched 2026-08-29T09:22:55.931798+00:00, sha ab45ccf1cacd)
- Data as of 2026-08-30T08:39:29.467469+00:00.