ControlNet Canny для SD 3.5 Large использует алгоритм детекции краев для точного переноса контуров на новые генерации. Это идеальное решение для ИИ-художников, которым важен строгий контроль над композицией и сохранение четких границ объектов.
Today we are adding new capabilities to Stable Diffusion 3.5 Large with the release of three ControlNets: Blur, Canny, and Depth. These models are free for both commercial and non-commercial use under the permissive Stability AI Community License. You can download the model weights now from Hugging Face and code from GitHub, with support by Comfy UI. Canny Leverage Canny edge maps to structure your generated images. This control type is particularly useful for illustrations but can be adaptable across all styles.