{ "id": "6f1d2c3a-5b4e-4f7a-9c1d-0e2b3a4c5d6e", "revision": 0, "last_node_id": 12, "last_link_id": 12, "nodes": [ { "id": 1, "type": "LoadImage", "pos": [40, 300], "size": [320, 380], "flags": {}, "order": 0, "mode": 0, "inputs": [], "outputs": [ {"name": "IMAGE", "type": "IMAGE", "links": [1, 4, 10]}, {"name": "MASK", "type": "MASK", "links": []} ], "properties": {"Node name for S&R": "LoadImage"}, "widgets_values": ["wevisone_seabreeze.jpg", "image"] }, { "id": 2, "type": "WeVisOneVLLoader", "pos": [40, 160], "size": [320, 60], "flags": {}, "order": 1, "mode": 0, "inputs": [], "outputs": [ {"name": "CLIP", "type": "CLIP", "links": [2]} ], "properties": {"Node name for S&R": "WeVisOneVLLoader"}, "widgets_values": ["wevisone_vl_4b_bf16.safetensors"] }, { "id": 3, "type": "WeVisOneVLPerceive", "pos": [420, 160], "size": [340, 260], "flags": {}, "order": 2, "mode": 0, "inputs": [ {"name": "clip", "type": "CLIP", "link": 2}, {"name": "image", "type": "IMAGE", "link": 1} ], "outputs": [ {"name": "text", "type": "STRING", "links": [3]}, {"name": "bboxes", "type": "BOUNDING_BOX", "links": [5]}, {"name": "points", "type": "STRING", "links": []}, {"name": "mask", "type": "MASK", "links": [7, 9]} ], "properties": {"Node name for S&R": "WeVisOneVLPerceive"}, "widgets_values": ["matting", "person", 1024, false] }, { "id": 4, "type": "PreviewAny", "pos": [820, 40], "size": [420, 160], "flags": {}, "order": 3, "mode": 0, "inputs": [ {"name": "source", "type": "*", "link": 3} ], "outputs": [ {"name": "STRING", "type": "STRING", "links": null} ], "properties": {"Node name for S&R": "PreviewAny"}, "widgets_values": [] }, { "id": 5, "type": "DrawBBoxes", "pos": [820, 260], "size": [220, 50], "flags": {}, "order": 4, "mode": 0, "inputs": [ {"name": "image", "type": "IMAGE", "link": 4}, {"name": "bboxes", "type": "BOUNDING_BOX", "link": 5} ], "outputs": [ {"name": "out_image", "type": "IMAGE", "links": [6]} ], "properties": {"Node name for S&R": "DrawBBoxes"}, "widgets_values": [] }, { "id": 6, "type": "PreviewImage", "pos": [1080, 260], "size": [360, 300], "flags": {}, "order": 7, "mode": 0, "inputs": [ {"name": "images", "type": "IMAGE", "link": 6} ], "outputs": [], "properties": {"Node name for S&R": "PreviewImage"}, "widgets_values": [] }, { "id": 7, "type": "MaskToImage", "pos": [820, 620], "size": [220, 30], "flags": {}, "order": 5, "mode": 0, "inputs": [ {"name": "mask", "type": "MASK", "link": 7} ], "outputs": [ {"name": "IMAGE", "type": "IMAGE", "links": [8]} ], "properties": {"Node name for S&R": "MaskToImage"}, "widgets_values": [] }, { "id": 8, "type": "PreviewImage", "pos": [1080, 600], "size": [360, 300], "flags": {}, "order": 8, "mode": 0, "inputs": [ {"name": "images", "type": "IMAGE", "link": 8} ], "outputs": [], "properties": {"Node name for S&R": "PreviewImage"}, "widgets_values": [] }, { "id": 9, "type": "InvertMask", "pos": [820, 960], "size": [220, 30], "flags": {}, "order": 6, "mode": 0, "inputs": [ {"name": "mask", "type": "MASK", "link": 9} ], "outputs": [ {"name": "MASK", "type": "MASK", "links": [11]} ], "properties": {"Node name for S&R": "InvertMask"}, "widgets_values": [] }, { "id": 10, "type": "JoinImageWithAlpha", "pos": [820, 1040], "size": [220, 50], "flags": {}, "order": 9, "mode": 0, "inputs": [ {"name": "image", "type": "IMAGE", "link": 10}, {"name": "alpha", "type": "MASK", "link": 11} ], "outputs": [ {"name": "IMAGE", "type": "IMAGE", "links": [12]} ], "properties": {"Node name for S&R": "JoinImageWithAlpha"}, "widgets_values": [] }, { "id": 11, "type": "PreviewImage", "pos": [1080, 940], "size": [360, 300], "flags": {}, "order": 10, "mode": 0, "inputs": [ {"name": "images", "type": "IMAGE", "link": 12} ], "outputs": [], "properties": {"Node name for S&R": "PreviewImage"}, "widgets_values": [] }, { "id": 12, "type": "MarkdownNote", "pos": [40, 740], "size": [720, 240], "flags": {}, "order": 11, "mode": 0, "inputs": [], "outputs": [], "properties": {}, "widgets_values": ["## WeVisOne-VL Perceive\n\nPick a **task** and write the **query**:\n\n- **detection / point**: labels, one per line (`dog`, `cat`)\n- **referring / matting**: a phrase (`the man on the left`)\n- **count_box / count_point**: the object to count\n- **ocr**: no query; **ocr_grounding**: the text to find\n- **freeform**: the full prompt\n\n`bboxes` work with Draw BBoxes and SAM3 Detect; `points` is JSON for SAM3 point prompts; `mask` is the alpha matte (matting only).\n\nModel: `models/text_encoders/wevisone_vl_4b_bf16.safetensors` (see the pack README to convert it)."], "color": "#432", "bgcolor": "#653" } ], "links": [ [1, 1, 0, 3, 1, "IMAGE"], [2, 2, 0, 3, 0, "CLIP"], [3, 3, 0, 4, 0, "STRING"], [4, 1, 0, 5, 0, "IMAGE"], [5, 3, 1, 5, 1, "BOUNDING_BOX"], [6, 5, 0, 6, 0, "IMAGE"], [7, 3, 3, 7, 0, "MASK"], [8, 7, 0, 8, 0, "IMAGE"], [9, 3, 3, 9, 0, "MASK"], [10, 1, 0, 10, 0, "IMAGE"], [11, 9, 0, 10, 1, "MASK"], [12, 10, 0, 11, 0, "IMAGE"] ], "groups": [], "config": {}, "extra": {"ds": {"scale": 0.8, "offset": [0, 0]}}, "version": 0.4 }