{ "id": "1c99f525-0a37-45ba-a28a-7df7c3af66b4", "revision": 0, "last_node_id": 12, "last_link_id": 14, "nodes": [ { "id": 1, "type": "VLLMOmniUnderstanding", "pos": [ 1191.2177053682556, 144.66829928181377 ], "size": [ 400, 268 ], "flags": {}, "order": 8, "mode": 0, "inputs": [ { "localized_name": "image", "name": "image", "shape": 7, "type": "IMAGE", "link": 1 }, { "localized_name": "video", "name": "video", "shape": 7, "type": "VIDEO", "link": 2 }, { "localized_name": "audio", "name": "audio", "shape": 7, "type": "AUDIO", "link": 3 }, { "localized_name": "sampling_params", "name": "sampling_params", "shape": 7, "type": "SAMPLING_PARAMS", "link": 14 }, { "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": "output_text", "name": "output_text", "type": "BOOLEAN", "widget": { "name": "output_text" }, "link": null }, { "localized_name": "output_audio", "name": "output_audio", "type": "BOOLEAN", "widget": { "name": "output_audio" }, "link": null }, { "localized_name": "use_audio_in_video", "name": "use_audio_in_video", "type": "BOOLEAN", "widget": { "name": "use_audio_in_video" }, "link": null } ], "outputs": [ { "localized_name": "text_response", "name": "text_response", "type": "STRING", "links": [ 8 ] }, { "localized_name": "audio_response", "name": "audio_response", "type": "AUDIO", "links": [ 9 ] } ], "properties": { "Node name for S&R": "VLLMOmniUnderstanding" }, "widgets_values": [ "http://localhost:8000/v1", "Qwen/Qwen2.5-Omni-7B", "", true, true, true ] }, { "id": 3, "type": "LoadVideo", "pos": [ 729.5984141255855, -198.631920454299 ], "size": [ 282.798828125, 233.0743408203125 ], "flags": {}, "order": 0, "mode": 0, "inputs": [ { "localized_name": "file", "name": "file", "type": "COMBO", "widget": { "name": "file" }, "link": null }, { "localized_name": "choose file to upload", "name": "upload", "type": "IMAGEUPLOAD", "widget": { "name": "upload" }, "link": null } ], "outputs": [ { "localized_name": "VIDEO", "name": "VIDEO", "type": "VIDEO", "links": [ 2 ] } ], "properties": { "Node name for S&R": "LoadVideo" }, "widgets_values": [ "draw.mp4", "image" ] }, { "id": 4, "type": "LoadAudio", "pos": [ 729.8037086965753, 99.86963519703949 ], "size": [ 282.798828125, 136 ], "flags": {}, "order": 1, "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": [ 3 ] } ], "properties": { "Node name for S&R": "LoadAudio" }, "widgets_values": [ "Megan-Fox.mp3", null, null ] }, { "id": 5, "type": "VLLMOmniARSampling", "pos": [ 510.3517536642828, 658.073751009259 ], "size": [ 270, 178 ], "flags": {}, "order": 2, "mode": 0, "inputs": [ { "localized_name": "max_tokens", "name": "max_tokens", "type": "INT", "widget": { "name": "max_tokens" }, "link": null }, { "localized_name": "temperature", "name": "temperature", "type": "FLOAT", "widget": { "name": "temperature" }, "link": null }, { "localized_name": "top_p", "name": "top_p", "type": "FLOAT", "widget": { "name": "top_p" }, "link": null }, { "localized_name": "repetition_penalty", "name": "repetition_penalty", "type": "FLOAT", "widget": { "name": "repetition_penalty" }, "link": null }, { "localized_name": "seed", "name": "seed", "type": "INT", "widget": { "name": "seed" }, "link": null } ], "outputs": [ { "localized_name": "AR sampling params", "name": "AR sampling params", "type": "SAMPLING_PARAMS", "links": [ 12 ] } ], "properties": { "Node name for S&R": "VLLMOmniARSampling" }, "widgets_values": [ 100, 1, 1, 1, -1, "randomize" ] }, { "id": 7, "type": "VLLMOmniARSampling", "pos": [ 503.33235181647115, 419.34158016181806 ], "size": [ 270, 178 ], "flags": {}, "order": 3, "mode": 0, "inputs": [ { "localized_name": "max_tokens", "name": "max_tokens", "type": "INT", "widget": { "name": "max_tokens" }, "link": null }, { "localized_name": "temperature", "name": "temperature", "type": "FLOAT", "widget": { "name": "temperature" }, "link": null }, { "localized_name": "top_p", "name": "top_p", "type": "FLOAT", "widget": { "name": "top_p" }, "link": null }, { "localized_name": "repetition_penalty", "name": "repetition_penalty", "type": "FLOAT", "widget": { "name": "repetition_penalty" }, "link": null }, { "localized_name": "seed", "name": "seed", "type": "INT", "widget": { "name": "seed" }, "link": null } ], "outputs": [ { "localized_name": "AR sampling params", "name": "AR sampling params", "type": "SAMPLING_PARAMS", "links": [ 5, 13 ] } ], "properties": { "Node name for S&R": "VLLMOmniARSampling" }, "widgets_values": [ 100, 1, 1, 1, -1, "randomize" ] }, { "id": 8, "type": "VLLMOmniSamplingParamsList", "pos": [ 820.6056617389042, 426.38372037182273 ], "size": [ 263.066015625, 66 ], "flags": {}, "order": 7, "mode": 0, "inputs": [ { "localized_name": "param1", "name": "param1", "type": "SAMPLING_PARAMS", "link": 5 }, { "localized_name": "param2", "name": "param2", "shape": 7, "type": "SAMPLING_PARAMS", "link": 12 }, { "localized_name": "param3", "name": "param3", "shape": 7, "type": "SAMPLING_PARAMS", "link": 13 } ], "outputs": [ { "localized_name": "param list", "name": "param list", "type": "SAMPLING_PARAMS", "links": [ 14 ] } ], "properties": { "Node name for S&R": "VLLMOmniSamplingParamsList" }, "widgets_values": [] }, { "id": 11, "type": "MarkdownNote", "pos": [ 826.2328280438272, 569.1890318701705 ], "size": [ 333.8220435590464, 261.63596728060656 ], "flags": {}, "order": 4, "mode": 0, "inputs": [], "outputs": [], "title": "Note: Sampling Parameters", "properties": {}, "widgets_values": [ "## Sampling Parameter Types\n\nThere are two types of sampling parameters: one for autoregression and one for diffusion.\nYou should ensure that you have chosen the correct type of sampling parameters for the model you request.\n\n## Stages & Shorthand\n\nFor multi-stage models such as Qwen Omni, you can either\n- connect one sampling parameter node, which is applied to all stages.\n- connect exactly the same number of sampling parameter nodes to a \"Multi-Stage Sampling Parameter List\" node, then connect this node to the primary request node.\n\nNote that this shorthand is intended to stay consistent with the [online serving API](https://docs.vllm.ai/projects/vllm-omni/en/latest/user_guide/examples/online_serving/qwen2_5_omni/)" ], "color": "#432", "bgcolor": "#000" }, { "id": 12, "type": "MarkdownNote", "pos": [ 378.9866207003777, 152.59550252215752 ], "size": [ 319.7287574247016, 107.15904081906785 ], "flags": {}, "order": 6, "mode": 0, "inputs": [], "outputs": [], "title": "Note: Input", "properties": {}, "widgets_values": [ "Note that not all models support every modality as input. For example, `ByteDance-Seed/BAGEL-7B-MoT` in Multimodality Understanding mode only support text and image input.\n\nYou should ensure that the input are supported by the model. You can check the corresponding [online serving documentation](https://docs.vllm.ai/projects/vllm-omni/en/latest/user_guide/examples/online_serving/bagel/) for confirmation." ], "color": "#432", "bgcolor": "#000" }, { "id": 2, "type": "LoadImage", "pos": [ 394.4674804308822, -207.6987397548834 ], "size": [ 282.798828125, 314 ], "flags": {}, "order": 5, "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": [ 1 ] }, { "localized_name": "MASK", "name": "MASK", "type": "MASK", "links": null } ], "properties": { "Node name for S&R": "LoadImage" }, "widgets_values": [ "example.png", "image" ] }, { "id": 10, "type": "PreviewAudio", "pos": [ 1664.548345556043, 297.5921292054054 ], "size": [ 270, 88 ], "flags": {}, "order": 10, "mode": 0, "inputs": [ { "localized_name": "audio", "name": "audio", "type": "AUDIO", "link": 9 }, { "localized_name": "audioUI", "name": "audioUI", "type": "AUDIO_UI", "widget": { "name": "audioUI" }, "link": null } ], "outputs": [], "properties": { "Node name for S&R": "PreviewAudio" }, "widgets_values": [] }, { "id": 9, "type": "ShowText|pysssss", "pos": [ 1649.2506875091847, 66.22823888292349 ], "size": [ 318.7188464232943, 173.38502269972975 ], "flags": {}, "order": 9, "mode": 0, "inputs": [ { "localized_name": "text", "name": "text", "type": "STRING", "link": 8 } ], "outputs": [ { "localized_name": "STRING", "name": "STRING", "shape": 6, "type": "STRING", "links": null } ], "properties": { "Node name for S&R": "ShowText|pysssss" }, "widgets_values": [] } ], "links": [ [ 1, 2, 0, 1, 0, "IMAGE" ], [ 2, 3, 0, 1, 1, "VIDEO" ], [ 3, 4, 0, 1, 2, "AUDIO" ], [ 5, 7, 0, 8, 0, "SAMPLING_PARAMS" ], [ 8, 1, 0, 9, 0, "STRING" ], [ 9, 1, 1, 10, 0, "AUDIO" ], [ 12, 5, 0, 8, 1, "SAMPLING_PARAMS" ], [ 13, 7, 0, 8, 2, "SAMPLING_PARAMS" ], [ 14, 8, 0, 1, 3, "SAMPLING_PARAMS" ] ], "groups": [ { "id": 1, "title": "Sampling Parameters", "bounding": [ 480.1649301181556, 341.08402513937995, 692.4113568972277, 510.48648853403665 ], "color": "#3f789e", "font_size": 24, "flags": {} }, { "id": 2, "title": "Input", "bounding": [ 344.2364817813528, -287.5850484183313, 704.8832238768634, 559.5124009832894 ], "color": "#3f789e", "font_size": 24, "flags": {} } ], "config": {}, "extra": { "workflowRendererVersion": "LG", "ds": { "scale": 0.9478575057427204, "offset": [ 33.81037136029557, 307.1974296197726 ] } }, "version": 0.4 }