{ "id": "b1b52a7e-e128-4de3-83e0-2238301079ca", "revision": 0, "last_node_id": 16, "last_link_id": 14, "nodes": [ { "id": 7, "type": "AILab_LoadImage", "pos": [ -1200, 70 ], "size": [ 300, 720 ], "flags": {}, "order": 1, "mode": 0, "inputs": [], "outputs": [ { "name": "IMAGE", "type": "IMAGE", "links": [ 11 ] }, { "name": "MASK", "type": "MASK", "links": null }, { "name": "WIDTH", "type": "INT", "links": null }, { "name": "HEIGHT", "type": "INT", "links": null } ], "properties": { "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "Node name for S&R": "AILab_LoadImage", "ue_properties": { "widget_ue_connectable": {}, "input_ue_unconnectable": {}, "version": "7.3" } }, "widgets_values": [ "", "2430364.png", "lanczos", 1, 1, "longest_side", 0, "image" ], "color": "#2e3e57", "bgcolor": "#4b5b73" }, { "id": 11, "type": "VHS_LoadVideo", "pos": [ -880, 480 ], "size": [ 247.455078125, 551.455078125 ], "flags": {}, "order": 0, "mode": 0, "inputs": [ { "name": "meta_batch", "shape": 7, "type": "VHS_BatchManager", "link": null }, { "name": "vae", "shape": 7, "type": "VAE", "link": null } ], "outputs": [ { "name": "IMAGE", "type": "IMAGE", "links": [ 13 ] }, { "name": "frame_count", "type": "INT", "links": null }, { "name": "audio", "type": "AUDIO", "links": null }, { "name": "video_info", "type": "VHS_VIDEOINFO", "links": null } ], "properties": { "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "cnr_id": "comfyui-videohelpersuite", "ver": "08e8df15db24da292d4b7f943c460dc2ab442b24", "Node name for S&R": "VHS_LoadVideo", "ue_properties": { "widget_ue_connectable": {}, "input_ue_unconnectable": {}, "version": "7.3" } }, "widgets_values": { "video": "sing_1.mp4", "force_rate": 0, "custom_width": 0, "custom_height": 0, "frame_load_cap": 0, "skip_first_frames": 0, "select_every_nth": 1, "format": "AnimateDiff", "choose video to upload": "image", "videopreview": { "hidden": false, "paused": false, "params": { "filename": "sing_1.mp4", "type": "input", "format": "video/mp4", "force_rate": 0, "custom_width": 0, "custom_height": 0, "frame_load_cap": 0, "skip_first_frames": 0, "select_every_nth": 1 } } }, "color": "#323", "bgcolor": "#535" }, { "id": 12, "type": "PreviewAny", "pos": [ -470, 70 ], "size": [ 890, 350 ], "flags": {}, "order": 6, "mode": 0, "inputs": [ { "name": "source", "type": "*", "link": 12 } ], "outputs": [], "properties": { "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "cnr_id": "comfy-core", "ver": "0.3.65", "Node name for S&R": "PreviewAny", "ue_properties": { "widget_ue_connectable": {}, "input_ue_unconnectable": {}, "version": "7.3" } }, "widgets_values": [], "color": "#42526b", "bgcolor": "#2e3e57" }, { "id": 13, "type": "PreviewAny", "pos": [ -200, 480 ], "size": [ 620, 370 ], "flags": {}, "order": 5, "mode": 0, "inputs": [ { "name": "source", "type": "*", "link": 14 } ], "outputs": [], "properties": { "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "cnr_id": "comfy-core", "ver": "0.3.65", "Node name for S&R": "PreviewAny", "ue_properties": { "widget_ue_connectable": {}, "input_ue_unconnectable": {}, "version": "7.3" } }, "widgets_values": [], "color": "#323", "bgcolor": "#535" }, { "id": 14, "type": "AILab_QwenVL", "pos": [ -885, 70 ], "size": [ 400, 276 ], "flags": {}, "order": 4, "mode": 0, "inputs": [ { "name": "image", "shape": 7, "type": "IMAGE", "link": 11 }, { "name": "video", "shape": 7, "type": "IMAGE", "link": null } ], "outputs": [ { "name": "text", "type": "STRING", "links": [ 12 ] } ], "properties": { "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "Node name for S&R": "AILab_QwenVL", "ue_properties": { "widget_ue_connectable": {}, "input_ue_unconnectable": {}, "version": "7.3" } }, "widgets_values": [ "Qwen3-VL-4B-Instruct", "8-bit (Balanced)", "Create a detailed text-to-image prompt from this image.", "", 1024, true, 289564980581148, "randomize" ], "color": "#42526b", "bgcolor": "#2e3e57" }, { "id": 15, "type": "AILab_QwenVL_Advanced", "pos": [ -616.2724609375, 480 ], "size": [ 400, 420 ], "flags": {}, "order": 3, "mode": 0, "inputs": [ { "name": "image", "shape": 7, "type": "IMAGE", "link": null }, { "name": "video", "shape": 7, "type": "IMAGE", "link": 13 } ], "outputs": [ { "name": "text", "type": "STRING", "links": [ 14 ] } ], "properties": { "enableTabs": false, "tabWidth": 65, "tabXOffset": 10, "hasSecondTab": false, "secondTabText": "Send Back", "secondTabOffset": 80, "secondTabWidth": 65, "ue_properties": { "widget_ue_connectable": {}, "input_ue_unconnectable": {} }, "Node name for S&R": "AILab_QwenVL_Advanced" }, "widgets_values": [ "Qwen3-VL-4B-Instruct", "8-bit (Balanced)", "Describe this video in detail.", "", 1024, 0.6, 0.9, 1, 1.2, 16, "auto", true, 1, "randomize" ], "color": "#323", "bgcolor": "#535" }, { "id": 16, "type": "MarkdownNote", "pos": [ -1780, 80 ], "size": [ 550, 530 ], "flags": {}, "order": 2, "mode": 0, "inputs": [], "outputs": [], "properties": {}, "widgets_values": [ "## **⚙️ Parameters**\n\n| Parameter | Description | Default | Range | Node(s) |\n| :---- | :---- | :---- | :---- | :---- |\n| **model\\_name** | The Qwen-VL model to use. | Qwen3-VL-4B-Instruct | \\- | Standard & Advanced |\n| **quantization** | On-the-fly quantization. Ignored for pre-quantized models (e.g., FP8). | 8-bit (Balanced) | 4-bit, 8-bit, None | Standard & Advanced |\n| **preset\\_prompt** | A selection of pre-defined prompts for common tasks. | \"Describe this...\" | Any text | Standard & Advanced |\n| **custom\\_prompt** | Overrides the preset prompt if provided. | | Any text | Standard & Advanced |\n| **max\\_tokens** | Maximum number of new tokens to generate. | 1024 | 64-2048 | Standard & Advanced |\n| **keep\\_model\\_loaded** | Keep the model in VRAM for faster subsequent runs. | True | True/False | Standard & Advanced |\n| **seed** | A seed for reproducible results. | 1 | 1 \\- 2^64-1 | Standard & Advanced |\n| **temperature** | Controls randomness. Higher values \\= more creative. (Used when num\\_beams is 1). | 0.6 | 0.1-1.0 | Advanced Only |\n| **top\\_p** | Nucleus sampling threshold. (Used when num\\_beams is 1). | 0.9 | 0.0-1.0 | Advanced Only |\n| **num\\_beams** | Number of beams for beam search. \\> 1 disables temperature/top\\_p sampling. | 1 | 1-10 | Advanced Only |\n| **repetition\\_penalty** | Discourages repeating tokens. | 1.2 | 0.0-2.0 | Advanced Only |\n| **frame\\_count** | Number of frames to sample from the video input. | 16 | 1-64 | Advanced Only |\n| **device** | Override automatic device selection. | auto | auto, cuda, cpu | Advanced Only |" ], "color": "#432", "bgcolor": "#653" } ], "links": [ [ 11, 7, 0, 14, 0, "IMAGE" ], [ 12, 14, 0, 12, 0, "*" ], [ 13, 11, 0, 15, 1, "IMAGE" ], [ 14, 15, 0, 13, 0, "*" ] ], "groups": [], "config": {}, "extra": { "frontendVersion": "1.28.6", "VHS_latentpreview": false, "VHS_latentpreviewrate": 0, "VHS_MetadataImage": true, "VHS_KeepIntermediate": true, "ue_links": [], "links_added_by_ue": [], "ds": { "scale": 0.6308868299625972, "offset": [ 1917.2877306922048, 249.41690338677327 ] } }, "version": 0.4 }