#30 · Primary category: Prompt Engineering Tools

PromptEnhancer

hunyuan hunyuan-image image-editing image-to-image prompt prompt-engineering prompt-enhancer text-to-image vlm

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

Project last updated:08/18/26

GitHub Stars

3.8K

Forks

326

Contributors

5

License

Other

Why we included this project

Vague prompts are the usual culprit when text-to-image output misses the mark, and PromptEnhancer tackles that problem before the generation model ever sees your words. Built by Tencent Hunyuan's research team, it runs a chain-of-thought rewriting model behind a small Python API, so you can drop it into a pipeline and get more consistent images without hand-tuning every prompt. An image-editing mode also uses the source image as visual context to tighten editing instructions, and quantized GGUF checkpoints let the whole thing run on a single consumer GPU rather than a big cluster. The repo ships the 7B model and an evaluation dataset, which helps if you want to compare rewriting quality on your own workloads. It is a self-contained component, not a framework, so the real question is whether the extra preprocessing step earns its place in your generation stack.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category