{
  "id": "6a7153c2-a483-48c6-bddf-7a3884dee602",
  "revision": 0,
  "last_node_id": 9,
  "last_link_id": 8,
  "nodes": [
    {
      "id": 3,
      "type": "CLIPLoader",
      "pos": [
        10,
        270
      ],
      "size": [
        370,
        150
      ],
      "flags": {},
      "order": 0,
      "mode": 0,
      "showAdvanced": false,
      "inputs": [],
      "outputs": [
        {
          "name": "CLIP",
          "type": "CLIP",
          "links": [
            2
          ]
        }
      ],
      "properties": {
        "cnr_id": "comfy-core",
        "ver": "0.21.0",
        "Node name for S&R": "CLIPLoader",
        "models": [
          {
            "name": "gemma4_e4b_it_fp8_scaled.safetensors",
            "url": "https://huggingface.co/Comfy-Org/gemma-4/resolve/main/text_encoders/gemma4_e4b_it_fp8_scaled.safetensors",
            "directory": "text_encoders"
          }
        ]
      },
      "widgets_values": [
        "gemma4_e4b_it_fp8_scaled.safetensors",
        "stable_diffusion",
        "default"
      ]
    },
    {
      "id": 5,
      "type": "LoadAudio",
      "pos": [
        100,
        870
      ],
      "size": [
        290,
        160
      ],
      "flags": {},
      "order": 1,
      "mode": 0,
      "inputs": [],
      "outputs": [
        {
          "name": "AUDIO",
          "type": "AUDIO",
          "links": [
            8
          ]
        }
      ],
      "properties": {
        "cnr_id": "comfy-core",
        "ver": "0.21.0",
        "Node name for S&R": "LoadAudio"
      },
      "widgets_values": [
        "long_demo.mp3",
        null,
        null
      ]
    },
    {
      "id": 2,
      "type": "LoadImage",
      "pos": [
        10,
        480
      ],
      "size": [
        380,
        340
      ],
      "flags": {},
      "order": 2,
      "mode": 0,
      "inputs": [],
      "outputs": [
        {
          "name": "IMAGE",
          "type": "IMAGE",
          "links": [
            7
          ]
        },
        {
          "name": "MASK",
          "type": "MASK",
          "links": null
        }
      ],
      "properties": {
        "cnr_id": "comfy-core",
        "ver": "0.21.0",
        "Node name for S&R": "LoadImage"
      },
      "widgets_values": [
        "the_lily_veil.png",
        "image"
      ]
    },
    {
      "id": 4,
      "type": "PreviewAny",
      "pos": [
        970,
        270
      ],
      "size": [
        560,
        660
      ],
      "flags": {
        "collapsed": false
      },
      "order": 8,
      "mode": 0,
      "inputs": [
        {
          "name": "source",
          "type": "*",
          "link": 3
        }
      ],
      "outputs": [
        {
          "name": "STRING",
          "type": "STRING",
          "links": null
        }
      ],
      "properties": {
        "cnr_id": "comfy-core",
        "ver": "0.21.0",
        "Node name for S&R": "PreviewAny"
      },
      "widgets_values": [
        null,
        null,
        null
      ]
    },
    {
      "id": 1,
      "type": "TextGenerate",
      "pos": [
        520,
        270
      ],
      "size": [
        400,
        562.65625
      ],
      "flags": {},
      "order": 6,
      "mode": 0,
      "showAdvanced": true,
      "inputs": [
        {
          "name": "clip",
          "type": "CLIP",
          "link": 2
        },
        {
          "name": "image",
          "shape": 7,
          "type": "IMAGE",
          "link": 7
        },
        {
          "name": "video",
          "shape": 7,
          "type": "IMAGE",
          "link": null
        },
        {
          "name": "audio",
          "shape": 7,
          "type": "AUDIO",
          "link": 8
        }
      ],
      "outputs": [
        {
          "name": "generated_text",
          "type": "STRING",
          "links": [
            3
          ]
        }
      ],
      "properties": {
        "cnr_id": "comfy-core",
        "ver": "0.21.0",
        "Node name for S&R": "TextGenerate"
      },
      "widgets_values": [
        "Describe the image, and transcribe the audio",
        2048,
        "on",
        0.7,
        64,
        0.95,
        0.05,
        1.05,
        0,
        0,
        false,
        true
      ]
    },
    {
      "id": 6,
      "type": "LoadVideo",
      "pos": [
        40,
        1140
      ],
      "size": [
        290,
        392
      ],
      "flags": {},
      "order": 3,
      "mode": 0,
      "inputs": [],
      "outputs": [
        {
          "name": "VIDEO",
          "type": "VIDEO",
          "links": [
            5
          ]
        }
      ],
      "properties": {
        "cnr_id": "comfy-core",
        "ver": "0.21.0",
        "Node name for S&R": "LoadVideo"
      },
      "widgets_values": [
        "video_wan_vace_inpainting_input_video.mp4",
        "image"
      ]
    },
    {
      "id": 7,
      "type": "GetVideoComponents",
      "pos": [
        410,
        1140
      ],
      "size": [
        230,
        100
      ],
      "flags": {},
      "order": 7,
      "mode": 0,
      "inputs": [
        {
          "name": "video",
          "type": "VIDEO",
          "link": 5
        }
      ],
      "outputs": [
        {
          "name": "images",
          "type": "IMAGE",
          "links": []
        },
        {
          "name": "audio",
          "type": "AUDIO",
          "links": null
        },
        {
          "name": "fps",
          "type": "FLOAT",
          "links": null
        }
      ],
      "properties": {
        "cnr_id": "comfy-core",
        "ver": "0.21.0",
        "Node name for S&R": "GetVideoComponents"
      },
      "widgets_values": []
    },
    {
      "id": 8,
      "type": "MarkdownNote",
      "pos": [
        -710,
        270
      ],
      "size": [
        640,
        674.96875
      ],
      "flags": {},
      "order": 4,
      "mode": 0,
      "inputs": [],
      "outputs": [],
      "properties": {},
      "widgets_values": [
        "Related PR: [#13376](https://github.com/Comfy-Org/ComfyUI/pull/13376)\n\n## Model Links\n\n- [Hugging Face:Comfy-Org/gemma-4](https://huggingface.co/Comfy-Org/gemma-4)\n- [ModelScope:Comfy-Org/gemma-4](https://modelscope.cn/models/Comfy-Org/gemma-4)\n\n**text_encoders**\n\n- [gemma4_e4b_it_fp8_scaled.safetensors](https://huggingface.co/Comfy-Org/gemma-4/resolve/main/text_encoders/gemma4_e4b_it_fp8_scaled.safetensors) (8.44 GB)\n\n## Model Storage Location\n\n```\n📂 ComfyUI/\n├── 📂 models/\n│   └── 📂 text_encoders/\n│       └── gemma4_e4b_it_fp8_scaled.safetensors\n```\n\n---\n* Other model weights: https://huggingface.co/Comfy-Org/gemma-4/tree/main/text_encoders\n\n## Report Issue\n\nNote: Please update ComfyUI first ([guide](https://docs.comfy.org/installation/update_comfyui)) and prepare required models. Desktop/Cloud updates follow stable releases, so some nightly-supported models may not be available yet.\n\n- Cannot run / runtime errors: [ComfyUI/issues](https://github.com/comfyanonymous/ComfyUI/issues)\n- UI / frontend issues: [ComfyUI_frontend/issues](https://github.com/Comfy-Org/ComfyUI_frontend/issues)\n- Workflow issues: [workflow_templates/issues](https://github.com/Comfy-Org/workflow_templates/issues)\n"
      ],
      "color": "#222",
      "bgcolor": "#000"
    },
    {
      "id": 9,
      "type": "MarkdownNote",
      "pos": [
        -730,
        1020
      ],
      "size": [
        660,
        600
      ],
      "flags": {},
      "order": 5,
      "mode": 0,
      "inputs": [],
      "outputs": [],
      "title": "Gemma4 Core Capabilities",
      "properties": {},
      "widgets_values": [
        "**Core Capabilities**\n\n[Gemma 4](https://huggingface.co/google/gemma-4-E2B-it) models handle a broad range of tasks across text, vision, and audio. Key capabilities include:\n\n+   **Thinking** – Built-in reasoning mode that lets the model think step-by-step before answering.\n+   **Long Context** – Context windows of up to 128K tokens (E2B/E4B) and 256K tokens (26B A4B/31B).\n+   **Image Understanding** – Object detection, Document/PDF parsing, screen and UI understanding, chart comprehension, OCR (including multilingual), handwriting recognition, and pointing. Images can be processed at variable aspect ratios and resolutions.\n+   **Video Understanding** – Analyze video by processing sequences of frames.\n+   **Interleaved Multimodal Input** – Freely mix text and images in any order within a single prompt.\n+   **Function Calling** – Native support for structured tool use, enabling agentic workflows.\n+   **Coding** – Code generation, completion, and correction.\n+   **Multilingual** – Out-of-the-box support for 35+ languages, pre-trained on 140+ languages.\n+   **Audio** (E2B and E4B only) – Automatic speech recognition (ASR) and speech-to-translated-text translation across multiple languages.\n"
      ],
      "color": "#222",
      "bgcolor": "#000"
    }
  ],
  "links": [
    [
      2,
      3,
      0,
      1,
      0,
      "CLIP"
    ],
    [
      3,
      1,
      0,
      4,
      0,
      "STRING"
    ],
    [
      5,
      6,
      0,
      7,
      0,
      "VIDEO"
    ],
    [
      7,
      2,
      0,
      1,
      1,
      "IMAGE"
    ],
    [
      8,
      5,
      0,
      1,
      3,
      "AUDIO"
    ]
  ],
  "groups": [
    {
      "id": 1,
      "title": "Video Input Example",
      "bounding": [
        30,
        1070,
        660,
        500
      ],
      "color": "#3f789e",
      "flags": {}
    }
  ],
  "config": {},
  "extra": {
    "ds": {
      "scale": 0.25392770255200803,
      "offset": [
        1710.5226325043593,
        1195.667376097804
      ]
    },
    "frontendVersion": "1.43.18"
  },
  "version": 0.4
}