SeanScripts-ComfyUI-PixtralLlamaMolmoVision/examples/llama_vision_bounding_box_workflow.json

{"last_node_id":48,"last_link_id":66,"nodes":[{"id":30,"type":"RegexSubstitution","pos":[480,370],"size":[210,102],"flags":{},"order":4,"mode":0,"inputs":[{"name":"string","type":"STRING","link":47,"widget":{"name":"string"}},{"name":"replace","type":"STRING","link":46,"widget":{"name":"replace"}}],"outputs":[{"name":"STRING","type":"STRING","links":[64],"slot_index":0,"shape":3}],"properties":{"Node name for S&R":"RegexSubstitution"},"widgets_values":["{object}","test {object} test","test","M"]},{"id":15,"type":"DF_Text_Box","pos":[75,550],"size":[247.62606811523438,92.8243179321289],"flags":{},"order":0,"mode":0,"inputs":[],"outputs":[{"name":"STRING","type":"STRING","links":[46],"slot_index":0,"shape":3}],"properties":{"Node name for S&R":"DF_Text_Box"},"widgets_values":["text"]},{"id":1,"type":"LoadImage","pos":[366,605],"size":[315,314],"flags":{},"order":1,"mode":0,"inputs":[],"outputs":[{"name":"IMAGE","type":"IMAGE","links":[7,12,63],"slot_index":0,"shape":3},{"name":"MASK","type":"MASK","links":null,"shape":3}],"properties":{"Node name for S&R":"LoadImage"},"widgets_values":["CogVideoX-I2V_00006.png","image"]},{"id":10,"type":"ParseBoundingBoxes","pos":[1125,315],"size":[210,102],"flags":{},"order":6,"mode":0,"inputs":[{"name":"image","type":"IMAGE","link":12},{"name":"string","type":"STRING","link":65,"widget":{"name":"string"}}],"outputs":[{"name":"BBOX","type":"BBOX","links":[26,27],"slot_index":0,"shape":3}],"properties":{"Node name for S&R":"ParseBoundingBoxes"},"widgets_values":["",true,true]},{"id":12,"type":"Display Any (rgthree)","pos":[1418,251],"size":[248.57421875,85.7146224975586],"flags":{},"order":9,"mode":0,"inputs":[{"name":"source","type":"*","link":27,"dir":3}],"outputs":[],"properties":{"Node name for S&R":"Display Any (rgthree)"},"widgets_values":["[[36, 72, 648, 144]]"]},{"id":6,"type":"BboxVisualize","pos":[1431,410],"size":[210,78],"flags":{},"order":8,"mode":0,"inputs":[{"name":"images","type":"IMAGE","link":7},{"name":"bboxes","type":"BBOX","link":26}],"outputs":[{"name":"images","type":"IMAGE","links":[8],"slot_index":0,"shape":3}],"properties":{"Node name for S&R":"BboxVisualize"},"widgets_values":[3]},{"id":7,"type":"PreviewImage","pos":[1702,404],"size":[443,489],"flags":{},"order":10,"mode":0,"inputs":[{"name":"images","type":"IMAGE","link":8}],"outputs":[],"properties":{"Node name for S&R":"PreviewImage"},"widgets_values":[]},{"id":4,"type":"Display Any (rgthree)","pos":[1692,138],"size":[502.48602294921875,207.90098571777344],"flags":{},"order":7,"mode":0,"inputs":[{"name":"source","type":"*","link":66,"dir":3}],"outputs":[],"properties":{"Node name for S&R":"Display Any (rgthree)"},"widgets_values":["The bounding box coordinates of the text are: [(0.05, 0.15), (0.95, 0.45)]."]},{"id":44,"type":"LlamaVisionModelLoader","pos":[489,175],"size":[351.37103271484375,58],"flags":{},"order":2,"mode":0,"inputs":[],"outputs":[{"name":"VISION_MODEL","type":"VISION_MODEL","links":[62],"slot_index":0,"shape":3}],"properties":{"Node name for S&R":"LlamaVisionModelLoader"},"widgets_values":["Llama-3.2-11B-Vision-Instruct-nf4"]},{"id":46,"type":"LlamaVisionGenerateText","pos":[722,293],"size":[383,384],"flags":{},"order":5,"mode":0,"inputs":[{"name":"llama_vision_model","type":"VISION_MODEL","link":62},{"name":"images","type":"IMAGE","link":63,"shape":7},{"name":"prompt","type":"STRING","link":64,"widget":{"name":"prompt"}}],"outputs":[{"name":"STRING","type":"STRING","links":[65,66]}],"properties":{"Node name for S&R":"LlamaVisionGenerateText"},"widgets_values":["","Caption this image.",256,true,0.3,0.9,40,"<|eot_id|>",929916883,"randomize",false,false]},{"id":14,"type":"DF_Text_Box","pos":[25,132],"size":[419.071044921875,355.2226867675781],"flags":{},"order":3,"mode":0,"inputs":[],"outputs":[{"name":"STRING","type":"STRING","links":[47],"slot_index":0,"shape":3}],"properties":{"Node name for S&R":"DF_Text_Box"},"widgets_values":["Create an approximate bounding box containing the {object} in this image. Your response should only include the coordinates of the upper-left and lower-right corners of the bounding box relative to the image size, e.g. [(0.0, 0.0), (1.0, 1.0)] is a bounding box that covers the entire image. The bounding box coordinates of the {object} are:"]}],"links":[[7,1,0,6,0,"IMAGE"],[8,6,0,7,0,"IMAGE"],[12,1,0,10,0,"IMAGE"],[26,10,0,6,1,"BBOX"],[27,10,0,12,0,"*"],[46,15,0,30,1,"STRING"],[47,14,0,30,0,"STRING"],[62,44,0,46,0,"VISION_MODEL"],[63,1,0,46,1,"IMAGE"],[64,30,0,46,2,"STRING"],[65,46,0,10,1,"STRING"],[66,46,0,4,0,"*"]],"groups":[],"config":{},"extra":{"ds":{"scale":1,"offset":[191.67246566216193,168.1576626509841]},"node_versions":{"ComfyUI-PixtralLlamaMolmoVision":"01728a16308eaa501dd025cb70f14a3b07a322a1","Derfuu_ComfyUI_ModdedNodes":"d0905bed31249f2bd0814c67585cf4fe3c77c015","comfy-core":"0.3.13","rgthree-comfy":"5d771b8b56a343c24a26e8cea1f0c87c3d58102f","ComfyUI-KJNodes":"2abf557e3d6ae6618456a190044a85a52f2a585a"},"VHS_latentpreview":false,"VHS_latentpreviewrate":0},"version":0.4}