<h3 id="wevisone-ai-powered-masking-and-image-editing">WeVisOne – AI-Powered Masking and Image Editing</h3>This workflow uses the WeVisOne text encoder. ⚠️ Important: For now, only the 4B variant is supported.<h3 id="how-to-use-it">How to use it</h3><ol><li>Load your image.</li><li>Tell WeVisOne what you want it to find or mask.</li><li>Adjust your editing prompt to describe the changes you want.</li><li>Hit Queue and let it do its thing!</li></ol>The workflow can also be used with the LanPaint custom node, if you have it installed.<h3 id="what-makes-wevisone-interesting">What makes WeVisOne interesting?</h3>WeVisOne has a lot more to offer than just segmentation. It supports several visual tasks, including:<ul><li>Segmentation: Create precise masks around specific objects or areas.</li><li>Bounding boxes: Detect objects and return their locations.</li><li>Point detection: Identify specific points within an image.</li><li>Background removal: Isolate subjects from their backgrounds.</li></ul>WeVisOne could be a great addition to image-editing workflows, especially when you need accurate masks for specific regions.It's a relatively small 4B model, so don't expect miracles, but its capabilities make it worth experimenting with!Works with MOSS and KREA2Downloads : <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/WeVisOne-VL/tree/main/text_encoders">https://huggingface.co/Comfy-Org/WeVisOne-VL/tree/main/text_encoders</a>Custom Node: <a target="_blank" rel="ugc" href="https://huggingface.co/paralaif/ComfyUI-WeVisOne-VL">https://huggingface.co/paralaif/ComfyUI-WeVisOne-VL</a>

Files with SHA256: 79e57b2f0d384f4713e6873a7511e25026313138bf4ec5b7d23de6e73626c78c