This extension connects AUTOMATIC1111 Stable Diffusion WebUI with Meta’s Segment Anything Model and GroundingDINO to provide interactive and text-based segmentation. Users can click images to generate masks or enter text prompts for automatic object detection and segmentation. Generated masks integrate with ControlNet for improved inpainting, semantic segmentation control, and automated image matting. The tool also supports creating LoRA and LyCORIS training datasets through automated segmentation workflows.