Browse Models
The simplest way to self-host ControlNet SD 1.5 Canny. Launch a dedicated cloud GPU server running Lab Station OS to download and serve the model using any compatible app or framework.
Download model weights for local inference. Must be used with a compatible app, notebook, or codebase. May run slowly, or not work at all, depending on your system resources, particularly GPU(s) and available VRAM.
ControlNet SD 1.5 Canny is a Stable Diffusion model that uses edge detection to guide image generation while maintaining creative flexibility. It features a LoRA variant that reduces model size by up to 92% and includes improvements in edge map processing and dataset curation from version 1.1.
ControlNet SD 1.5 Canny is a specialized edge detection model within the ControlNet family that adds conditional control to Stable Diffusion 1.5's text-to-image generation process. The model uses the Canny edge detection algorithm to create sharp, defined lines around areas of high contrast in input images, which then guide the image generation process while maintaining the original composition but allowing for stylistic variations.
The model is built on the ControlNet architecture, which enables conditional control in text-to-image diffusion models. ControlNet SD 1.5 Canny was trained for three days using eight Nvidia A100 80G GPUs with a batch size of 256. The training process involved using Canny edge detection with random thresholds and addresse