图片转网页.json

{
  "last_node_id": 31,
  "last_link_id": 45,
  "nodes": [
    {
      "id": 28,
      "type": "LoadImage",
      "pos": [
        434,
        482
      ],
      "size": {
        "0": 554.9673461914062,
        "1": 386.22503662109375
      },
      "flags": {},
      "order": 0,
      "mode": 0,
      "inputs": [],
      "outputs": [
        {
          "name": "IMAGE",
          "type": "IMAGE",
          "links": [
            42
          ],
          "shape": 3,
          "label": "IMAGE"
        },
        {
          "name": "MASK",
          "type": "MASK",
          "links": null,
          "shape": 3,
          "label": "MASK"
        }
      ],
      "properties": {
        "Node name for S&R": "LoadImage"
      },
      "widgets_values": [
        "1727365635168.png",
        "image"
      ]
    },
    {
      "id": 11,
      "type": "show_text_party",
      "pos": [
        1488,
        501
      ],
      "size": {
        "0": 546.4871215820312,
        "1": 411.0308837890625
      },
      "flags": {},
      "order": 2,
      "mode": 0,
      "inputs": [
        {
          "name": "text",
          "type": "STRING",
          "link": 41,
          "widget": {
            "name": "text"
          },
          "label": "text"
        }
      ],
      "outputs": [
        {
          "name": "STRING",
          "type": "STRING",
          "links": [
            43
          ],
          "shape": 6,
          "label": "STRING"
        }
      ],
      "properties": {
        "Node name for S&R": "show_text_party"
      },
      "widgets_values": [
        "",
        "Preview\nCode\n238 lines (194 loc) - 24.4 KB\nCode 55\\% faster with GitHub Copilot\n\\title{\n项目综述\n}\nComfyUI LLM Party，从最基础的 LLM 多工具调用、角色设定快速搭建自己的专属AI助手、到可以行业落地的词向量RAG、GraphRAG来本地化的管理行业内知识库；从单一的智能体流水线，到复杂的智能体与智能体辐射状交互模式、环形交互模式的构建从个人用户需要的接入自己的社交 APP(QQ、飞书、Discord)，到流媒体工作者需要的一站式LIM+TTS+ComfyUI工作流；从普通学生所需要的第一个LMI应用的简单上手起步，到科研工作者们常用的各类参数调试接口，模型适配。这一切，你都可以在ComfyUI LLM Party中找到答案。\n\\section*{最新更新}\n1. 大幅调整了本地LLM加载器节点，不用自己选择model type了。重新添加了lava加载器节点和GGUF加载器节点。本地LLM模型键节点上的 model type 已改成LLM、VLM-GGUF、LLM-GGUF三个选项，对应了直接加载LLM模型、加载VLM模型和加载GGUF格式的LLM模型。重新支持了VLM模型和GGUF格式的LLM模型。现在本地调用可以兼容更多的模型了! 示例工.作流: LLM local, IJava, GGU\n2. 已加入easyOCR节点，用于识别图中文字和位置，可以生成对应的mask，可以返回一个json字符串供LLM查看，有普通版本和高级版本供大家选择!\n3. 在comfyui LLM party中复现了chatgpt-o1系列模型的草莓系统，参考了Llamaber \\(\\mathrm{m}\\) 的提示词，示例工作流：Strawberry system compared to\n4. 新增了GPT-sovits节点，可以调用GPT-sovits模型，将文字根据你的参考音频转换为语音，也可以将你微调后的模型路径填入 (如果不填充基其虚拟模型进行推理 )，获得你想要的任务意色。使用时，需要下载GPT-sovits项目和对应的基底模型到本地，然后在GPT-sovits项目文件夹下用 runtime|python.exe api_v2.py 启动API服务。此外，chatTTS节点被移动到了comfyui LLM mafia中。原因是chatTTS的依赖库较多，且在 \\(y p\\) 中的许可且CC BY-NC 4.0，这是一个非商用许可证。即使chatTTS的github项目是AGPL协议的，我们还是为了避免不必要的麻烦，将chatTTS节点移到了comfyui LLM mafia中。希望大家能够理解！"
      ]
    },
    {
      "id": 29,
      "type": "mini_party",
      "pos": [
        2110,
        519
      ],
      "size": {
        "0": 419.20635986328125,
        "1": 291.5276184082031
      },
      "flags": {},
      "order": 3,
      "mode": 0,
      "inputs": [
        {
          "name": "input_str",
          "type": "STRING",
          "link": 43,
          "widget": {
            "name": "input_str"
          },
          "label": "input_str"
        }
      ],
      "outputs": [
        {
          "name": "output_str",
          "type": "STRING",
          "links": [
            45
          ],
          "shape": 3,
          "label": "output_str"
        }
      ],
      "properties": {
        "Node name for S&R": "mini_party"
      },
      "widgets_values": [
        "",
        "把我的输入转成markdown格式",
        "gpt-4o-mini",
        "",
        "",
        true
      ]
    },
    {
      "id": 27,
      "type": "got_ocr",
      "pos": [
        1079,
        537
      ],
      "size": {
        "0": 315,
        "1": 250
      },
      "flags": {},
      "order": 1,
      "mode": 0,
      "inputs": [
        {
          "name": "image",
          "type": "IMAGE",
          "link": 42,
          "label": "image"
        }
      ],
      "outputs": [
        {
          "name": "text",
          "type": "STRING",
          "links": [
            41
          ],
          "slot_index": 0,
          "shape": 3,
          "label": "text"
        }
      ],
      "properties": {
        "Node name for S&R": "got_ocr"
      },
      "widgets_values": [
        "E:\\GitHub\\model\\GOT-OCR2_0",
        "auto",
        "format",
        true,
        "",
        "",
        false,
        false,
        "E:\\GitHub\\ComfyUI_windows_portable_nvidia\\ComfyUI_windows_portable\\ComfyUI\\custom_nodes\\comfyui_LLM_party\\output"
      ]
    },
    {
      "id": 31,
      "type": "Browser_display",
      "pos": [
        2588,
        537
      ],
      "size": {
        "0": 315,
        "1": 82
      },
      "flags": {},
      "order": 4,
      "mode": 0,
      "inputs": [
        {
          "name": "md_or_html",
          "type": "STRING",
          "link": 45,
          "widget": {
            "name": "md_or_html"
          },
          "slot_index": 0
        }
      ],
      "outputs": [
        {
          "name": "log",
          "type": "STRING",
          "links": null,
          "shape": 3,
          "label": "log"
        }
      ],
      "properties": {
        "Node name for S&R": "Browser_display"
      },
      "widgets_values": [
        "",
        true
      ]
    }
  ],
  "links": [
    [
      41,
      27,
      0,
      11,
      0,
      "STRING"
    ],
    [
      42,
      28,
      0,
      27,
      0,
      "IMAGE"
    ],
    [
      43,
      11,
      0,
      29,
      0,
      "STRING"
    ],
    [
      45,
      29,
      0,
      31,
      0,
      "STRING"
    ]
  ],
  "groups": [],
  "config": {},
  "extra": {
    "ds": {
      "scale": 0.5559917313492456,
      "offset": [
        -720.3939780128053,
        -72.94613307417796
      ]
    }
  },
  "version": 0.4
}