https://stefano-blando.github.io/en/tags/sam/SAMHugoBlox Kit (https://hugoblox.com)en-USSun, 10 Mar 2024 00:00:00 +0000https://stefano-blando.github.io/media/icon_hu_8d0dee6c10a3c598.pnghttps://stefano-blando.github.io/en/tags/sam/https://stefano-blando.github.io/en/projects/ai-photo-editor/Sun, 10 Mar 2024 00:00:00 +0000https://stefano-blando.github.io/en/projects/ai-photo-editor/<p>This project explores the intersection of <strong>precise computer vision</strong> and <strong>generative image editing</strong> by combining <strong>Segment Anything (SAM)</strong> with <strong>Stable Diffusion XL</strong>.</p> <p>The core idea is straightforward: segmentation provides exact control over what should be changed, while diffusion-based inpainting provides the generative flexibility to actually change it. That makes the system useful not only as a demo, but as a concrete example of how discriminative and generative models can be combined inside the same workflow.</p> <p>Built in <strong>Python</strong> with <strong>PyTorch</strong>, <strong>Diffusers</strong>, and <strong>Gradio</strong>, the project supports interactive masking, object replacement, and background generation while keeping the pipeline lightweight enough to run on consumer hardware with the right optimizations.</p>