{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "eaa651f1-65c5-4e46-a09c-17312056082d",
   "metadata": {},
   "source": [
    "## 使用说明：\n",
    "- 执行下方单元格代码，当出现如下内容即启动成功：\n",
    "  ```\n",
    "  Starting server\n",
    "\n",
    "    To see the GUI go to: http://0.0.0.0:8188\n",
    "  ```\n",
    "- 使用方法：\n",
    "  打开 Comfyui 页面，左上角切换该项目 workflow，然后根据 node 上传图片和视频生成数字人视频\n",
    "  ![wf](./assets/workflow.png)\n",
    "- `/root/示例素材`文件夹中提供了示例图片和音频，可以下载进行使用\n",
    "- **说明：** 数字人视频融合过程较慢，一般需要7-8分钟，请耐心等待\n",
    "- workflow 中 `sd_model` 非必须模型，如若需要请手动下载放置于`root/ComfyUI/custom_nodes/ComfyUI-Hallo/pretrained_models/stable-diffusion-v1-5/`中，一般无需下载使用\n",
    "  \n",
    "- 在【访问自定义服务】中，设置 8188 端口，启动 WebUI\n",
    "\n",
    "## Hallo Workflow 介绍\n",
    "该workflow实现了图片和音频融合实现数字人播报的功能，示例如下：\n",
    "![demo](./assets/示例.png)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "fa7ca53d-9444-4ca0-a07e-598001000217",
   "metadata": {},
   "outputs": [],
   "source": [
    "!sh start.sh"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "297cd32b-e75f-41c8-a88d-b38625c4ce8a",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}