This ComfyUI workflow uses Stability AI’s SD 3.5 Large model with a Canny ControlNet to generate images that follow the structure of an input image’s edges. The pipeline loads the SD 3.5 checkpoint (CheckpointLoaderSimple) and the Canny ControlNet (ControlNetLoader), encodes your text prompt (CLIPTextEncode), and extracts a high-contrast edge map from your guide image (Canny). The edge map is applied as a structural constraint via ControlNetApplyAdvanced so the KSampler can synthesize new content that respects the outlines while still following your prompt.

Technically, the workflow creates a latent canvas at your target resolution (EmptySD3LatentImage), conditions the model with your positive prompt plus the ControlNet edge guidance, and optionally zeroes the negative prompt (ConditioningZeroOut) for simplicity. After sampling (KSampler), the result is decoded to RGB (VAEDecode), previewed (PreviewImage), and saved (SaveImage). ImageScale is included to match the Canny edge map to the chosen output size for consistent alignment. This setup is ideal when you want strong compositional control—like sticking to silhouettes or product contours—while letting SD 3.5 handle detail, texture, and style.