> For the complete documentation index, see [llms.txt](https://metaverse-imagen.gitbook.io/ai-tools-research/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://metaverse-imagen.gitbook.io/ai-tools-research/ai-tools-main-categories/images-art-and-design/image-generation/fooocus/fooocus-faqs/what-is-pyracanny.md).

# What is PyraCanny?

**PyraCanny** is an advanced edge detection technique used in image generation, primarily within the context of the **Fooocus** interface for the **Stable Diffusion** AI image generator. It improves upon the traditional Canny edge detection method by incorporating a **pyramid scheme**.

Here's a breakdown of what PyraCanny does:

**Standard Canny edge detection:**

* Can miss intricate details in high-resolution images (like the 1024px used by SDXL).
* Relies on a single resolution for analysis, potentially overlooking subtle edges.

**PyraCanny to the rescue:**

* **Leverages a pyramid of multiple resolutions:** analyzes the image at decreasing resolutions, from coarse to fine.
* **Detects edges at each resolution level:** captures both broad strokes and finer details.
* **Softly combines edge detections across resolutions:** creates a more comprehensive and accurate edge map.

**Benefits of using PyraCanny:**

* **Preserves more image details:** especially useful for high-resolution images or those with intricate textures.
* **Improves edge accuracy:** captures subtle lines and boundaries that standard Canny might miss.
* **Leads to cleaner, more defined AI-generated images:** with crisper lines and borders.

**Where you might encounter PyraCanny:**

* **Fooocus interface for Stable Diffusion:** accessible as an "advanced" control option for image generation.
* **Discussions around Stable Diffusion and image prompting:** mentioned as a way to enhance edge detection in generated images.

Overall, PyraCanny represents a significant step forward in edge detection for image generation, contributing to more detailed and refined AI-produced artwork.