Files
vllm-omni/apps/ComfyUI-vLLM-Omni/example_workflows/vLLM-Omni Video Generation.json
T

2 lines
8.9 KiB
JSON

{"id":"3aea1d08-7de5-4997-ba71-b2f66ad72a21","revision":0,"last_node_id":24,"last_link_id":35,"nodes":[{"id":13,"type":"SaveVideo","pos":[1315.729153459605,-137.92038948394355],"size":[374,313.7692307692308],"flags":{},"order":9,"mode":0,"inputs":[{"localized_name":"video","name":"video","type":"VIDEO","link":32},{"localized_name":"filename_prefix","name":"filename_prefix","type":"STRING","widget":{"name":"filename_prefix"},"link":null},{"localized_name":"format","name":"format","type":"COMBO","widget":{"name":"format"},"link":null},{"localized_name":"codec","name":"codec","type":"COMFY_DYNAMICCOMBO_V3","widget":{"name":"codec"},"link":null}],"outputs":[{"localized_name":"video","name":"video","type":"VIDEO","links":null}],"properties":{},"widgets_values":["video/ComfyUI","auto","auto"]},{"id":10,"type":"MarkdownNote","pos":[183.74636797766794,-571.2529158046766],"size":[240.3326478922474,136.3505820791881],"flags":{},"order":0,"mode":0,"inputs":[],"outputs":[],"title":"Note: Task and Input","properties":{},"widgets_values":["vLLM-Omni nodes are categorized based on the output modality. The \"Generate Video\" node supports both *text-to-video*, *frame-to-video*, and *reference-to-video* generation. The node will create corresponding payload depending on whether an input image is present or not."],"color":"#432","bgcolor":"#000"},{"id":4,"type":"LoadImage","pos":[452.07189605801125,-569.7242536425791],"size":[270,314],"flags":{},"order":1,"mode":0,"inputs":[{"localized_name":"image","name":"image","type":"COMBO","widget":{"name":"image"},"link":null},{"localized_name":"choose file to upload","name":"upload","type":"IMAGEUPLOAD","widget":{"name":"upload"},"link":null}],"outputs":[{"localized_name":"IMAGE","name":"IMAGE","type":"IMAGE","links":[29]},{"localized_name":"MASK","name":"MASK","type":"MASK","links":null}],"properties":{"Node name for S&R":"LoadImage"},"widgets_values":["rap.png","image"]},{"id":23,"type":"LoadImage","pos":[9.206110246057657,-7.6955291509170785],"size":[270,314],"flags":{},"order":2,"mode":0,"inputs":[{"localized_name":"image","name":"image","type":"COMBO","widget":{"name":"image"},"link":null},{"localized_name":"choose file to upload","name":"upload","type":"IMAGEUPLOAD","widget":{"name":"upload"},"link":null}],"outputs":[{"localized_name":"IMAGE","name":"IMAGE","type":"IMAGE","links":[34]},{"localized_name":"MASK","name":"MASK","type":"MASK","links":null}],"properties":{"Node name for S&R":"LoadImage"},"widgets_values":["white-cat.jpg","image"]},{"id":22,"type":"MarkdownNote","pos":[-9.783113411416666,-148.8790300038605],"size":[297.3012007349086,88],"flags":{},"order":3,"mode":0,"inputs":[],"outputs":[],"title":"Note: Reference to video (r2v)","properties":{},"widgets_values":["For r2v tasks, connect this Video Reference block to the main Generate Video block. Then disconnect the \"frame\" input above."],"color":"#432","bgcolor":"#000"},{"id":24,"type":"LoadAudio","pos":[317.9929742385805,-141.44821500065095],"size":[282.798828125,136],"flags":{},"order":4,"mode":0,"inputs":[{"localized_name":"audio","name":"audio","type":"COMBO","widget":{"name":"audio"},"link":null},{"localized_name":"audioUI","name":"audioUI","type":"AUDIO_UI","widget":{"name":"audioUI"},"link":null},{"localized_name":"choose file to upload","name":"upload","type":"AUDIOUPLOAD","widget":{"name":"upload"},"link":null}],"outputs":[{"localized_name":"AUDIO","name":"AUDIO","type":"AUDIO","links":[35]}],"properties":{"Node name for S&R":"LoadAudio"},"widgets_values":["nothing-beats-a-jet2-holiday.mp3",null,""]},{"id":21,"type":"VLLMOmniVideoReferences","pos":[376.6129172897595,105.41557277556292],"size":[156.9380859375,126],"flags":{},"order":7,"mode":0,"inputs":[{"localized_name":"image_1","name":"image_1","shape":7,"type":"IMAGE","link":34},{"localized_name":"image_2","name":"image_2","shape":7,"type":"IMAGE","link":null},{"localized_name":"audio_1","name":"audio_1","shape":7,"type":"AUDIO","link":35},{"localized_name":"audio_2","name":"audio_2","shape":7,"type":"AUDIO","link":null},{"localized_name":"video_1","name":"video_1","shape":7,"type":"VIDEO","link":null},{"localized_name":"video_2","name":"video_2","shape":7,"type":"VIDEO","link":null}],"outputs":[{"localized_name":"references","name":"references","type":"VIDEO_REFERENCES","links":null}],"properties":{"Node name for S&R":"VLLMOmniVideoReferences"},"widgets_values":[]},{"id":8,"type":"VLLMOmniDiffusionSampling","pos":[83.24620208113915,422.08543477542605],"size":[284.205078125,226],"flags":{},"order":5,"mode":0,"inputs":[{"localized_name":"n","name":"n","type":"INT","widget":{"name":"n"},"link":null},{"localized_name":"num_inference_steps","name":"num_inference_steps","type":"INT","widget":{"name":"num_inference_steps"},"link":null},{"localized_name":"guidance_scale","name":"guidance_scale","type":"FLOAT","widget":{"name":"guidance_scale"},"link":null},{"localized_name":"true_cfg_scale","name":"true_cfg_scale","type":"FLOAT","widget":{"name":"true_cfg_scale"},"link":null},{"localized_name":"vae_use_slicing","name":"vae_use_slicing","type":"BOOLEAN","widget":{"name":"vae_use_slicing"},"link":null},{"localized_name":"vae_use_tiling","name":"vae_use_tiling","type":"BOOLEAN","widget":{"name":"vae_use_tiling"},"link":null},{"localized_name":"seed","name":"seed","type":"INT","widget":{"name":"seed"},"link":null}],"outputs":[{"localized_name":"diffusion sampling params","name":"diffusion sampling params","type":"SAMPLING_PARAMS","links":[30]}],"properties":{"Node name for S&R":"VLLMOmniDiffusionSampling"},"widgets_values":[1,50,1,1,false,false,213,"randomize"]},{"id":18,"type":"VLLMOmniMiniMaxH3Params","pos":[483.0944676363692,426.7197881452892],"size":[276.56796875,82],"flags":{},"order":6,"mode":0,"inputs":[{"localized_name":"audio_flow_shift","name":"audio_flow_shift","type":"FLOAT","widget":{"name":"audio_flow_shift"},"link":null},{"localized_name":"flow_shift","name":"flow_shift","type":"FLOAT","widget":{"name":"flow_shift"},"link":null}],"outputs":[{"localized_name":"MiniMax-H3 video params","name":"MiniMax-H3 video params","type":"VIDEO_PARAMS","links":[33]}],"properties":{"Node name for S&R":"VLLMOmniMiniMaxH3Params"},"widgets_values":[3,12]},{"id":16,"type":"VLLMOmniGenerateVideo","pos":[826.1428043381621,-148.53719710697413],"size":[425.5948726785682,551.767376721426],"flags":{},"order":8,"mode":0,"inputs":[{"localized_name":"frame","name":"frame","shape":7,"type":"IMAGE","link":29},{"localized_name":"references","name":"references","shape":7,"type":"VIDEO_REFERENCES","link":null},{"localized_name":"sampling_params","name":"sampling_params","shape":7,"type":"SAMPLING_PARAMS","link":30},{"localized_name":"lora","name":"lora","shape":7,"type":"REMOTE_LORA","link":null},{"localized_name":"model_params","name":"model_params","shape":7,"type":"VIDEO_PARAMS","link":33},{"localized_name":"url","name":"url","type":"STRING","widget":{"name":"url"},"link":null},{"localized_name":"model","name":"model","type":"STRING","widget":{"name":"model"},"link":null},{"localized_name":"prompt","name":"prompt","type":"STRING","widget":{"name":"prompt"},"link":null},{"localized_name":"negative_prompt","name":"negative_prompt","type":"STRING","widget":{"name":"negative_prompt"},"link":null},{"localized_name":"width","name":"width","type":"INT","widget":{"name":"width"},"link":null},{"localized_name":"height","name":"height","type":"INT","widget":{"name":"height"},"link":null},{"localized_name":"fps","name":"fps","type":"INT","widget":{"name":"fps"},"link":null},{"localized_name":"num_frames","name":"num_frames","type":"INT","widget":{"name":"num_frames"},"link":null}],"outputs":[{"localized_name":"video","name":"video","type":"VIDEO","links":[32]}],"properties":{"Node name for S&R":"VLLMOmniGenerateVideo"},"widgets_values":["http://localhost:8000/v1","/workspace/models/hub/models--MiniMaxAI--MiniMax-H3/snapshots/428986c4aa5280855b9ac26eff8d1a46b5999cd0/FL2VA","A scene of urban fantasy art. A dynamic graffiti art character. A boy made of spray paint comes to life on a concrete wall. He sings an English rap song at high speed while striking a classic, energetic rapper pose. The scene is set under an urban railway bridge at night. The light comes from a single street lamp, creating a cinematic atmosphere full of high energy and amazing detail. The audio of the video consists entirely of the rap, with no other dialogue or noise.","",832,480,24,120]}],"links":[[29,4,0,16,0,"IMAGE"],[30,8,0,16,2,"SAMPLING_PARAMS"],[32,16,0,13,0,"VIDEO"],[33,18,0,16,4,"VIDEO_PARAMS"],[34,23,0,21,0,"IMAGE"],[35,24,0,21,2,"AUDIO"]],"groups":[{"id":1,"title":"Image-to-video input (first-frame-to-video)","bounding":[168.92390079062986,-653.2124402506535,560.8246471437027,407.4246532472182],"color":"#3f789e","flags":{}},{"id":2,"title":"Reference-to-video input","bounding":[-66.75175444110151,-225.24978633666066,805.4597228678848,554.7384400819777],"color":"#3f789e","flags":{}}],"config":{},"extra":{"workflowRendererVersion":"LG","ds":{"scale":0.8,"offset":[1240.4751945653188,770.6151743053379]}},"version":0.4}