[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77868B4EYGCSHAN07BCDW6X":3,"skill-same:01M77868B4EYGCSHAN07BCDW6X":47},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M77868B4EYGCSHAN07BCDW6X","comfyui-v8",null,"ComfyUI V8 秋叶中文版 全流程助手。提供安装检测、一键启动、工作流生成（文生图\u002F图生图\u002FControlNet\u002FInstantID等）、参数优化、故障排查、批量生成、模型管理等功能。All-in-one assistant for ComfyUI V8 (Aki bundle) with workflow generation, one-click startup, troubleshooting, and advanced features.","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fc\u002Fcomfyui-v8\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: comfyui-v8\ndescription: ComfyUI V8 秋叶中文版 全流程助手。提供安装检测、一键启动、工作流生成（文生图\u002F图生图\u002FControlNet\u002FInstantID等）、参数优化、故障排查、批量生成、模型管理等功能。All-in-one assistant for ComfyUI V8 (Aki bundle) with workflow generation, one-click startup, troubleshooting, and advanced features.\n---\n\n# ComfyUI V8 秋叶中文版助手 \u002F ComfyUI V8 Aki Bundle Assistant\n\n## 功能概览 \u002F Features\n\n| 功能 | 描述 |\n|------|------|\n| 🔍 环境检测 | 检测整合包安装状态、模型、依赖 |\n| 🚀 一键启动 | 启动绘世启动器或ComfyUI核心服务 |\n| 🎨 工作流生成 | 文生图、图生图、ControlNet、InstantID、扩图、局部重绘 |\n| ⚙️ 参数优化 | 显存优化、常用参数推荐 |\n| 🐛 故障排查 | 常见错误诊断与修复方案 |\n| 📦 模型管理 | Checkpoint\u002FLoRA\u002FControlNet 模型切换 |\n| 🔄 批量生成 | 多提示词批量出图 |\n| 🔗 增强功能 | 绘世启动器\u002F300+节点\u002F国内加速\u002FFLUX支持 |\n| 📊 工作流管理 | 导出\u002F导入\u002F复制\u002F对比 |\n\n## 触发词 \u002F Triggers\n\n`ComfyUI`, `comfyui`, `秋叶`, `绘世启动器`, `文生图`, `图生图`, `ControlNet`, `InstantID`, `扩图`, `局部重绘`, `工作流`, `comfy workflow`\n\n## 使用方法 \u002F Usage\n\n### 命令格式 \u002F Command Format\n\n```\n检测ComfyUI环境        # 环境检测\n启动ComfyUI            # 一键启动\n生成文生图工作流        # 文生图\n生成图生图工作流        # 图生图\n生成ControlNet工作流    # ControlNet\n生成InstantID工作流     # InstantID\n生成扩图工作流          # 扩图\n生成局部重绘工作流       # 局部重绘\n优化ComfyUI参数         # 参数优化\nComfyUI故障排查         # 故障排查\n批量生成图片            # 批量生成\n管理ComfyUI模型         # 模型管理\n```\n\n## 核心参数 \u002F Core Parameters\n\n### 文生图 \u002F Text-to-Image\n\n| 参数 | 默认值 | 说明 |\n|------|--------|------|\n| prompt | 高质量, 8k, 高清, 细节丰富 | 正向提示词 |\n| negative_prompt | 模糊, 低分辨率, 畸形, 水印 | 负向提示词 |\n| model | sdxl_base.safetensors | 模型选择 |\n| width | 1024 | 宽度 |\n| height | 1024 | 高度 |\n| steps | 28 | 采样步数 |\n| cfg | 7 | CFG强度 |\n| sampler | dpmpp_2m | 采样器 |\n| scheduler | karras | 调度器 |\n\n### 模型类型 \u002F Model Types\n\n- **SDXL Base**: `sdxl_base.safetensors` (1024x1024 推荐)\n- **SD 1.5**: `sd15_base.safetensors` (512x512 推荐)\n- **FLUX**: `flux_dev.safetensors` \u002F `flux_schnell.safetensors` (1024x1024+)\n- **InstantID**: 需要 `antelopev2` embeddings + `ip-adapter-instantid-sdxl.safetensors`\n\n## 工作流 JSON 结构（秋叶V8标准）\u002F Workflow JSON Structure\n\n```json\n{\n  \"name\": \"秋叶V8-文生图\",\n  \"nodes\": [\n    {\"type\": \"CheckpointLoaderSimple\", \"inputs\": {\"ckpt_name\": \"sdxl_base.safetensors\"}},\n    {\"type\": \"CLIPTextEncode\", \"inputs\": {\"text\": \"正向提示词\"}},\n    {\"type\": \"CLIPTextEncode\", \"inputs\": {\"text\": \"负向提示词\"}},\n    {\"type\": \"EmptyLatentImage\", \"inputs\": {\"width\": 1024, \"height\": 1024, \"batch_size\": 1}},\n    {\"type\": \"KSampler\", \"inputs\": {\"steps\": 28, \"cfg\": 7, \"sampler_name\": \"dpmpp_2m\", \"scheduler\": \"karras\"}},\n    {\"type\": \"VAEDecode\", \"inputs\": {}},\n    {\"type\": \"SaveImage\", \"inputs\": {\"filename_prefix\": \"txt2img\"}}\n  ]\n}\n```\n\n## 故障排查 \u002F Troubleshooting\n\n| 错误现象 | 解决方案 |\n|----------|----------|\n| 启动闪退 | 安装 .NET Framework 4.8+、以管理员运行、检查路径无中文\u002F空格 |\n| 显存不足 | 开启 --lowvram 模式、降低分辨率、分块加载模型 |\n| 模型加载失败 | 检查模型完整性、确认放置在正确目录 (models\u002Fcheckpoints) |\n| 节点缺失 | 绘世启动器 → 拓展管理 → 一键安装缺失节点 |\n| 中文乱码 | 秋叶V8已内置中文，无需修改，重启即可 |\n| 卡在 \"Loading models\" | 检查网络\u002F磁盘空间、手动下载模型到 models\u002Fcheckpoints |\n\n## 显存优化方案 \u002F VRAM Optimization\n\n| 显存 | 推荐方案 |\n|------|----------|\n| \u003C 6GB | 4bit量化、SD 1.5\u002F7B小模型、关闭高分辨率 |\n| 6-12GB | 8bit量化、1024x1024、启用VAE分块解码 |\n| > 12GB | FP16原生、1536x1536高分辨率、批量生成 |\n\n```bash\n# 启动参数（编辑 启动ComfyUI.bat）\n# 低显存模式\n.\\python_embeded\\python.exe .\\main.py --lowvram --cpu\n\n# 中等显存（RTX 3060 12G）\n.\\python_embeded\\python.exe .\\main.py --normalvram\n\n# 秋叶V8启动器勾选「低显存模式」即可\n```\n\n## 模型目录结构 \u002F Model Directory Structure\n\n```\nComfyUI-aki-V8\u002F\n├── models\u002F\n│   ├── checkpoints\u002F          # SD\u002FSDXL\u002FFLUX 主模型\n│   ├── lora\u002F                  # LoRA 模型\n│   ├── controlnet\u002F            # ControlNet 模型\n│   ├── embeddings\u002F           # Textual Inversion \u002F InstantID\n│   ├── vae\u002F                   # VAE 模型\n│   └── upscale_models\u002F        # 放大模型 (ESRGAN等)\n├── user\u002F\n│   └── default\u002F\n│       └── workflows\u002F         # 默认工作流存储\n└── 启动ComfyUI.bat            # 启动脚本\n```\n\n## 工作流模板（秋叶V8标准节点）\u002F Workflow Templates\n\n### 1. 文生图 (Text-to-Image)\n\n```json\n{\n  \"name\": \"秋叶V8-文生图\",\n  \"nodes\": [\n    {\"type\": \"CheckpointLoaderSimple\", \"inputs\": {\"ckpt_name\": \"sdxl_base.safetensors\"}},\n    {\"type\": \"CLIPTextEncode\", \"inputs\": {\"text\": \"正向提示词\"}},\n    {\"type\": \"CLIPTextEncode\", \"inputs\": {\"text\": \"负向提示词\"}},\n    {\"type\": \"EmptyLatentImage\", \"inputs\": {\"width\": 1024, \"height\": 1024, \"batch_size\": 1}},\n    {\"type\": \"KSampler\", \"inputs\": {\"steps\": 28, \"cfg\": 7, \"sampler_name\": \"dpmpp_2m\", \"scheduler\": \"karras\"}},\n    {\"type\": \"VAEDecode\", \"inputs\": {}},\n    {\"type\": \"SaveImage\", \"inputs\": {\"filename_prefix\": \"txt2img\"}}\n  ]\n}\n```\n\n### 2. 图生图 (Image-to-Image)\n\n```json\n{\n  \"name\": \"秋叶V8-图生图\",\n  \"nodes\": [\n    {\"type\": \"CheckpointLoaderSimple\", \"inputs\": {\"ckpt_name\": \"sdxl_base.safetensors\"}},\n    {\"type\": \"CLIPTextEncode\", \"inputs\": {\"text\": \"正向提示词\"}},\n    {\"type\": \"CLIPTextEncode\", \"inputs\": {\"text\": \"负向提示词\"}},\n    {\"type\": \"LoadImage\", \"inputs\": {\"image\": \"input.png\"}},\n    {\"type\": \"VAEEncode\", \"inputs\": {}},\n    {\"type\": \"KSampler\", \"inputs\": {\"steps\": 28, \"cfg\": 7, \"sampler_name\": \"dpmpp_2m\", \"scheduler\": \"karras\"}},\n    {\"type\": \"VAEDecode\", \"inputs\": {}},\n    {\"type\": \"SaveImage\", \"inputs\": {\"filename_prefix\": \"img2img\"}}\n  ]\n}\n```\n\n### 3. ControlNet 线稿\u002F边缘\u002F姿态控制\n\n```json\n{\n  \"name\": \"秋叶V8-ControlNet\",\n  \"nodes\": [\n    {\"type\": \"CheckpointLoaderSimple\", \"inputs\": {\"ckpt_name\": \"sdxl_base.safetensors\"}},\n    {\"type\": \"CLIPTextEncode\", \"inputs\": {\"text\": \"正向提示词\"}},\n    {\"type\": \"CLIPTextEncode\", \"inputs\": {\"text\": \"负向提示词\"}},\n    {\"type\": \"LoadImage\", \"inputs\": {\"image\": \"control.png\"}},\n    {\"type\": \"ControlNetLoader\", \"inputs\": {\"control_net_name\": \"canny.safetensors\"}},\n    {\"type\": \"ControlNetApply\", \"inputs\": {\"strength\": 0.8}},\n    {\"type\": \"EmptyLatentImage\", \"inputs\": {\"width\": 1024, \"height\": 1024, \"batch_size\": 1}},\n    {\"type\": \"KSampler\", \"inputs\": {\"steps\": 28, \"cfg\": 7, \"sampler_name\": \"dpmpp_2m\", \"scheduler\": \"karras\"}},\n    {\"type\": \"VAEDecode\", \"inputs\": {}},\n    {\"type\": \"SaveImage\", \"inputs\": {\"filename_prefix\": \"controlnet\"}}\n  ]\n}\n```\n\n### 4. InstantID 人脸一致性\n\n```json\n{\n  \"name\": \"秋叶V8-InstantID人脸\",\n  \"nodes\": [\n    {\"type\": \"CheckpointLoaderSimple\", \"inputs\": {\"ckpt_name\": \"ip-adapter-instantid-sdxl.safetensors\"}},\n    {\"type\": \"CLIPTextEncode\", \"inputs\": {\"text\": \"正向提示词\"}},\n    {\"type\": \"CLIPTextEncode\", \"inputs\": {\"text\": \"负向提示词\"}},\n    {\"type\": \"LoadImage\", \"inputs\": {\"image\": \"face.png\"}},\n    {\"type\": \"InstantIDModelLoader\", \"inputs\": {}},\n    {\"type\": \"InstantIDApply\", \"inputs\": {\"strength\": 0.7}},\n    {\"type\": \"EmptyLatentImage\", \"inputs\": {\"width\": 1024, \"height\": 1024, \"batch_size\": 1}},\n    {\"type\": \"KSampler\", \"inputs\": {\"steps\": 28, \"cfg\": 7, \"sampler_name\": \"dpmpp_2m\", \"scheduler\": \"karras\"}},\n    {\"type\": \"VAEDecode\", \"inputs\": {}},\n    {\"type\": \"SaveImage\", \"inputs\": {\"filename_prefix\": \"instantid\"}}\n  ],\n  \"models_required\": [\"antelopev2\", \"ip-adapter-instantid-sdxl\"]\n}\n```\n\n### 5. 扩图 (Outpainting)\n\n```json\n{\n  \"name\": \"秋叶V8-智能扩图\",\n  \"nodes\": [\n    {\"type\": \"CheckpointLoaderSimple\", \"inputs\": {\"ckpt_name\": \"sdxl_base.safetensors\"}},\n    {\"type\": \"CLIPTextEncode\", \"inputs\": {\"text\": \"正向提示词\"}},\n    {\"type\": \"CLIPTextEncode\", \"inputs\": {\"text\": \"负向提示词\"}},\n    {\"type\": \"LoadImage\", \"inputs\": {\"image\": \"base.png\"}},\n    {\"type\": \"ImageResize\", \"inputs\": {\"width\": 2048, \"height\": 2048, \"method\": \"lanczos\"}},\n    {\"type\": \"VAEEncode\", \"inputs\": {}},\n    {\"type\": \"KSampler\", \"inputs\": {\"steps\": 28, \"cfg\": 7, \"sampler_name\": \"dpmpp_2m\", \"scheduler\": \"karras\"}},\n    {\"type\": \"VAEDecode\", \"inputs\": {}},\n    {\"type\": \"SaveImage\", \"inputs\": {\"filename_prefix\": \"outpaint\"}}\n  ]\n}\n```\n\n### 6. 局部重绘 (Inpainting)\n\n```json\n{\n  \"name\": \"秋叶V8-局部重绘\",\n  \"nodes\": [\n    {\"type\": \"CheckpointLoaderSimple\", \"inputs\": {\"ckpt_name\": \"sdxl_base.safetensors\"}},\n    {\"type\": \"CLIPTextEncode\", \"inputs\": {\"text\": \"正向提示词\"}},\n    {\"type\": \"CLIPTextEncode\", \"inputs\": {\"text\": \"负向提示词\"}},\n    {\"type\": \"LoadImage\", \"inputs\": {\"image\": \"base.png\"}},\n    {\"type\": \"LoadImage\", \"inputs\": {\"image\": \"mask.png\"}},\n    {\"type\": \"VAEEncodeForInpaint\", \"inputs\": {}},\n    {\"type\": \"KSampler\", \"inputs\": {\"steps\": 28, \"cfg\": 7, \"sampler_name\": \"dpmpp_2m\", \"scheduler\": \"karras\"}},\n    {\"type\": \"VAEDecode\", \"inputs\": {}},\n    {\"type\": \"SaveImage\", \"inputs\": {\"filename_prefix\": \"inpaint\"}}\n  ]\n}\n```\n\n## 常见报错修复 \u002F Common Error Fixes\n\n| 错误 | 修复方法 |\n|------|----------|\n| 缺少.NET | 安装.NET 6.0桌面运行时，绘世启动器会自动引导下载 |\n| 显存不足 | 启动器勾选低显存、4bit量化、减小尺寸 |\n| 节点缺失 | 绘世启动器 → 拓展管理 → 一键安装缺失节点 |\n| 模型加载失败 | 模型路径无中文\u002F空格，放到models\u002Fcheckpoints |\n| 中文乱码 | 秋叶V8已内置中文，无需修改，重启即可 |\n\n## 注意事项 \u002F Notes\n\n- 秋叶V8已内置中文界面，无需额外汉化\n- 模型建议放置在 `models\u002Fcheckpoints\u002F` 目录\n- FLUX 模型需要更多显存 (建议 16GB+)\n- 定期使用绘世启动器更新内核和插件\n- 工作流保存路径：`user\u002Fdefault\u002Fworkflows\u002F`\n\n## 秋叶V8专属增强功能 \u002F Aki V8 Exclusive Features\n\n| 功能 | 说明 |\n|------|------|\n| 绘世启动器 | 内核\u002F插件\u002F模型\u002F更新 一站式管理 |\n| 300+预装节点 | ControlNet\u002FInstantID\u002FLayerDiffusion\u002FIC-Light |\n| 中文界面 | 节点\u002F菜单\u002F提示\u002F日志 全汉化 |\n| 国内加速 | GitHub镜像 + 模型下载加速 |\n| 全模型支持 | FLUX \u002F SD3 \u002F SDXL \u002F SD1.5 |\n| 一键备份 | 工作流\u002F模型\u002F配置 备份还原 |\n\n## 机器人触发指令 \u002F Bot Commands\n\n| 指令 | 功能 |\n|------|------|\n| `ComfyUI检测` | 环境检测 |\n| `启动ComfyUI` | 一键启动 |\n| `生成文生图工作流` | 生成txt2img |\n| `生成ControlNet工作流` | 生成ControlNet |\n| `ComfyUI显存优化` | VRAM优化 |\n| `ComfyUI修复` | 报错修复 |\n| `ComfyUI增强功能` | 查看V8增强功能 |\n","# ComfyUI V8 秋叶中文版助手 \u002F ComfyUI V8 Aki Bundle Assistant\n\n## 功能概览 \u002F Features\n\n| 功能 | 描述 |\n|------|------|\n| 🔍 环境检测 | 检测整合包安装状态、模型、依赖 |\n| 🚀 一键启动 | 启动绘世启动器或ComfyUI核心服务 |\n| 🎨 工作流生成 | 文生图、图生图、ControlNet、InstantID、扩图、局部重绘 |\n| ⚙️ 参数优化 | 显存优化、常用参数推荐 |\n| 🐛 故障排查 | 常见错误诊断与修复方案 |\n| 📦 模型管理 | Checkpoint\u002FLoRA\u002FControlNet 模型切换 |\n| 🔄 批量生成 | 多提示词批量出图 |\n| 🔗 增强功能 | 绘世启动器\u002F300+节点\u002F国内加速\u002FFLUX支持 |\n| 📊 工作流管理 | 导出\u002F导入\u002F复制\u002F对比 |\n\n## 触发词 \u002F Triggers\n\n`ComfyUI`, `comfyui`, `秋叶`, `绘世启动器`, `文生图`, `图生图`, `ControlNet`, `InstantID`, `扩图`, `局部重绘`, `工作流`, `comfy workflow`\n\n## 使用方法 \u002F Usage\n\n### 命令格式 \u002F Command Format\n\n```\n检测ComfyUI环境        # 环境检测\n启动ComfyUI            # 一键启动\n生成文生图工作流        # 文生图\n生成图生图工作流        # 图生图\n生成ControlNet工作流    # ControlNet\n生成InstantID工作流     # InstantID\n生成扩图工作流          # 扩图\n生成局部重绘工作流       # 局部重绘\n优化ComfyUI参数         # 参数优化\nComfyUI故障排查         # 故障排查\n批量生成图片            # 批量生成\n管理ComfyUI模型         # 模型管理\n```\n\n## 核心参数 \u002F Core Parameters\n\n### 文生图 \u002F Text-to-Image\n\n| 参数 | 默认值 | 说明 |\n|------|--------|------|\n| prompt | 高质量, 8k, 高清, 细节丰富 | 正向提示词 |\n| negative_prompt | 模糊, 低分辨率, 畸形, 水印 | 负向提示词 |\n| model | sdxl_base.safetensors | 模型选择 |\n| width | 1024 | 宽度 |\n| height | 1024 | 高度 |\n| steps | 28 | 采样步数 |\n| cfg | 7 | CFG强度 |\n| sampler | dpmpp_2m | 采样器 |\n| scheduler | karras | 调度器 |\n\n### 模型类型 \u002F Model Types\n\n- **SDXL Base**: `sdxl_base.safetensors` (1024x1024 推荐)\n- **SD 1.5**: `sd15_base.safetensors` (512x512 推荐)\n- **FLUX**: `flux_dev.safetensors` \u002F `flux_schnell.safetensors` (1024x1024+)\n- **InstantID**: 需要 `antelopev2` embeddings + `ip-adapter-instantid-sdxl.safetensors`\n\n## 工作流 JSON 结构（秋叶V8标准）\u002F Workflow JSON Structure\n\n```json\n{\n  \"name\": \"秋叶V8-文生图\",\n  \"nodes\": [\n    {\"type\": \"CheckpointLoaderSimple\", \"inputs\": {\"ckpt_name\": \"sdxl_base.safetensors\"}},\n    {\"type\": \"CLIPTextEncode\", \"inputs\": {\"text\": \"正向提示词\"}},\n    {\"type\": \"CLIPTextEncode\", \"inputs\": {\"text\": \"负向提示词\"}},\n    {\"type\": \"EmptyLatentImage\", \"inputs\": {\"width\": 1024, \"height\": 1024, \"batch_size\": 1}},\n    {\"type\": \"KSampler\", \"inputs\": {\"steps\": 28, \"cfg\": 7, \"sampler_name\": \"dpmpp_2m\", \"scheduler\": \"karras\"}},\n    {\"type\": \"VAEDecode\", \"inputs\": {}},\n    {\"type\": \"SaveImage\", \"inputs\": {\"filename_prefix\": \"txt2img\"}}\n  ]\n}\n```\n\n## 故障排查 \u002F Troubleshooting\n\n| 错误现象 | 解决方案 |\n|----------|----------|\n| 启动闪退 | 安装 .NET Framework 4.8+、以管理员运行、检查路径无中文\u002F空格 |\n| 显存不足 | 开启 --lowvram 模式、降低分辨率、分块加载模型 |\n| 模型加载失败 | 检查模型完整性、确认放置在正确目录 (models\u002Fcheckpoints) |\n| 节点缺失 | 绘世启动器 → 拓展管理 → 一键安装缺失节点 |\n| 中文乱码 | 秋叶V8已内置中文，无需修改，重启即可 |\n| 卡在 \"Loading models\" | 检查网络\u002F磁盘空间、手动下载模型到 models\u002Fcheckpoints |\n\n## 显存优化方案 \u002F VRAM Optimization\n\n| 显存 | 推荐方案 |\n|------|----------|\n| \u003C 6GB | 4bit量化、SD 1.5\u002F7B小模型、关闭高分辨率 |\n| 6-12GB | 8bit量化、1024x1024、启用VAE分块解码 |\n| > 12GB | FP16原生、1536x1536高分辨率、批量生成 |\n\n```bash\n# 启动参数（编辑 启动ComfyUI.bat）\n# 低显存模式\n.\\python_embeded\\python.exe .\\main.py --lowvram --cpu\n\n# 中等显存（RTX 3060 12G）\n.\\python_embeded\\python.exe .\\main.py --normalvram\n\n# 秋叶V8启动器勾选「低显存模式」即可\n```\n\n## 模型目录结构 \u002F Model Directory Structure\n\n```\nComfyUI-aki-V8\u002F\n├── models\u002F\n│   ├── checkpoints\u002F          # SD\u002FSDXL\u002FFLUX 主模型\n│   ├── lora\u002F                  # LoRA 模型\n│   ├── controlnet\u002F            # ControlNet 模型\n│   ├── embeddings\u002F           # Textual Inversion \u002F InstantID\n│   ├── vae\u002F                   # VAE 模型\n│   └── upscale_models\u002F        # 放大模型 (ESRGAN等)\n├── user\u002F\n│   └── default\u002F\n│       └── workflows\u002F         # 默认工作流存储\n└── 启动ComfyUI.bat            # 启动脚本\n```\n\n## 工作流模板（秋叶V8标准节点）\u002F Workflow Templates\n\n### 1. 文生图 (Text-to-Image)\n\n```json\n{\n  \"name\": \"秋叶V8-文生图\",\n  \"nodes\": [\n    {\"type\": \"CheckpointLoaderSimple\", \"inputs\": {\"ckpt_name\": \"sdxl_base.safetensors\"}},\n    {\"type\": \"CLIPTextEncode\", \"inputs\": {\"text\": \"正向提示词\"}},\n    {\"type\": \"CLIPTextEncode\", \"inputs\": {\"text\": \"负向提示词\"}},\n    {\"type\": \"EmptyLatentImage\", \"inputs\": {\"width\": 1024, \"height\": 1024, \"batch_size\": 1}},\n    {\"type\": \"KSampler\", \"inputs\": {\"steps\": 28, \"cfg\": 7, \"sampler_name\": \"dpmpp_2m\", \"scheduler\": \"karras\"}},\n    {\"type\": \"VAEDecode\", \"inputs\": {}},\n    {\"type\": \"SaveImage\", \"inputs\": {\"filename_prefix\": \"txt2img\"}}\n  ]\n}\n```\n\n### 2. 图生图 (Image-to-Image)\n\n```json\n{\n  \"name\": \"秋叶V8-图生图\",\n  \"nodes\": [\n    {\"type\": \"CheckpointLoaderSimple\", \"inputs\": {\"ckpt_name\": \"sdxl_base.safetensors\"}},\n    {\"type\": \"CLIPTextEncode\", \"inputs\": {\"text\": \"正向提示词\"}},\n    {\"type\": \"CLIPTextEncode\", \"inputs\": {\"text\": \"负向提示词\"}},\n    {\"type\": \"LoadImage\", \"inputs\": {\"image\": \"input.png\"}},\n    {\"type\": \"VAEEncode\", \"inputs\": {}},\n    {\"type\": \"KSampler\", \"inputs\": {\"steps\": 28, \"cfg\": 7, \"sampler_name\": \"dpmpp_2m\", \"scheduler\": \"karras\"}},\n    {\"type\": \"VAEDecode\", \"inputs\": {}},\n    {\"type\": \"SaveImage\", \"inputs\": {\"filename_prefix\": \"img2img\"}}\n  ]\n}\n```\n\n### 3. ControlNet 线稿\u002F边缘\u002F姿态控制\n\n```json\n{\n  \"name\": \"秋叶V8-ControlNet\",\n  \"nodes\": [\n    {\"type\": \"CheckpointLoaderSimple\", \"inputs\": {\"ckpt_name\": \"sdxl_base.safetensors\"}},\n    {\"type\": \"CLIPTextEncode\", \"inputs\": {\"text\": \"正向提示词\"}},\n    {\"type\": \"CLIPTextEncode\", \"inputs\": {\"text\": \"负向提示词\"}},\n    {\"type\": \"LoadImage\", \"inputs\": {\"image\": \"control.png\"}},\n    {\"type\": \"ControlNetLoader\", \"inputs\": {\"control_net_name\": \"canny.safetensors\"}},\n    {\"type\": \"ControlNetApply\", \"inputs\": {\"strength\": 0.8}},\n    {\"type\": \"EmptyLatentImage\", \"inputs\": {\"width\": 1024, \"height\": 1024, \"batch_size\": 1}},\n    {\"type\": \"KSampler\", \"inputs\": {\"steps\": 28, \"cfg\": 7, \"sampler_name\": \"dpmpp_2m\", \"scheduler\": \"karras\"}},\n    {\"type\": \"VAEDecode\", \"inputs\": {}},\n    {\"type\": \"SaveImage\", \"inputs\": {\"filename_prefix\": \"controlnet\"}}\n  ]\n}\n```\n\n### 4. InstantID 人脸一致性\n\n```json\n{\n  \"name\": \"秋叶V8-InstantID人脸\",\n  \"nodes\": [\n    {\"type\": \"CheckpointLoaderSimple\", \"inputs\": {\"ckpt_name\": \"ip-adapter-instantid-sdxl.safetensors\"}},\n    {\"type\": \"CLIPTextEncode\", \"inputs\": {\"text\": \"正向提示词\"}},\n    {\"type\": \"CLIPTextEncode\", \"inputs\": {\"text\": \"负向提示词\"}},\n    {\"type\": \"LoadImage\", \"inputs\": {\"image\": \"face.png\"}},\n    {\"type\": \"InstantIDModelLoader\", \"inputs\": {}},\n    {\"type\": \"InstantIDApply\", \"inputs\": {\"strength\": 0.7}},\n    {\"type\": \"EmptyLatentImage\", \"inputs\": {\"width\": 1024, \"height\": 1024, \"batch_size\": 1}},\n    {\"type\": \"KSampler\", \"inputs\": {\"steps\": 28, \"cfg\": 7, \"sampler_name\": \"dpmpp_2m\", \"scheduler\": \"karras\"}},\n    {\"type\": \"VAEDecode\", \"inputs\": {}},\n    {\"type\": \"SaveImage\", \"inputs\": {\"filename_prefix\": \"instantid\"}}\n  ],\n  \"models_required\": [\"antelopev2\", \"ip-adapter-instantid-sdxl\"]\n}\n```\n\n### 5. 扩图 (Outpainting)\n\n```json\n{\n  \"name\": \"秋叶V8-智能扩图\",\n  \"nodes\": [\n    {\"type\": \"CheckpointLoaderSimple\", \"inputs\": {\"ckpt_name\": \"sdxl_base.safetensors\"}},\n    {\"type\": \"CLIPTextEncode\", \"inputs\": {\"text\": \"正向提示词\"}},\n    {\"type\": \"CLIPTextEncode\", \"inputs\": {\"text\": \"负向提示词\"}},\n    {\"type\": \"LoadImage\", \"inputs\": {\"image\": \"base.png\"}},\n    {\"type\": \"ImageResize\", \"inputs\": {\"width\": 2048, \"height\": 2048, \"method\": \"lanczos\"}},\n    {\"type\": \"VAEEncode\", \"inputs\": {}},\n    {\"type\": \"KSampler\", \"inputs\": {\"steps\": 28, \"cfg\": 7, \"sampler_name\": \"dpmpp_2m\", \"scheduler\": \"karras\"}},\n    {\"type\": \"VAEDecode\", \"inputs\": {}},\n    {\"type\": \"SaveImage\", \"inputs\": {\"filename_prefix\": \"outpaint\"}}\n  ]\n}\n```\n\n### 6. 局部重绘 (Inpainting)\n\n```json\n{\n  \"name\": \"秋叶V8-局部重绘\",\n  \"nodes\": [\n    {\"type\": \"CheckpointLoaderSimple\", \"inputs\": {\"ckpt_name\": \"sdxl_base.safetensors\"}},\n    {\"type\": \"CLIPTextEncode\", \"inputs\": {\"text\": \"正向提示词\"}},\n    {\"type\": \"CLIPTextEncode\", \"inputs\": {\"text\": \"负向提示词\"}},\n    {\"type\": \"LoadImage\", \"inputs\": {\"image\": \"base.png\"}},\n    {\"type\": \"LoadImage\", \"inputs\": {\"image\": \"mask.png\"}},\n    {\"type\": \"VAEEncodeForInpaint\", \"inputs\": {}},\n    {\"type\": \"KSampler\", \"inputs\": {\"steps\": 28, \"cfg\": 7, \"sampler_name\": \"dpmpp_2m\", \"scheduler\": \"karras\"}},\n    {\"type\": \"VAEDecode\", \"inputs\": {}},\n    {\"type\": \"SaveImage\", \"inputs\": {\"filename_prefix\": \"inpaint\"}}\n  ]\n}\n```\n\n## 常见报错修复 \u002F Common Error Fixes\n\n| 错误 | 修复方法 |\n|------|----------|\n| 缺少.NET | 安装.NET 6.0桌面运行时，绘世启动器会自动引导下载 |\n| 显存不足 | 启动器勾选低显存、4bit量化、减小尺寸 |\n| 节点缺失 | 绘世启动器 → 拓展管理 → 一键安装缺失节点 |\n| 模型加载失败 | 模型路径无中文\u002F空格，放到models\u002Fcheckpoints |\n| 中文乱码 | 秋叶V8已内置中文，无需修改，重启即可 |\n\n## 注意事项 \u002F Notes\n\n- 秋叶V8已内置中文界面，无需额外汉化\n- 模型建议放置在 `models\u002Fcheckpoints\u002F` 目录\n- FLUX 模型需要更多显存 (建议 16GB+)\n- 定期使用绘世启动器更新内核和插件\n- 工作流保存路径：`user\u002Fdefault\u002Fworkflows\u002F`\n\n## 秋叶V8专属增强功能 \u002F Aki V8 Exclusive Features\n\n| 功能 | 说明 |\n|------|------|\n| 绘世启动器 | 内核\u002F插件\u002F模型\u002F更新 一站式管理 |\n| 300+预装节点 | ControlNet\u002FInstantID\u002FLayerDiffusion\u002FIC-Light |\n| 中文界面 | 节点\u002F菜单\u002F提示\u002F日志 全汉化 |\n| 国内加速 | GitHub镜像 + 模型下载加速 |\n| 全模型支持 | FLUX \u002F SD3 \u002F SDXL \u002F SD1.5 |\n| 一键备份 | 工作流\u002F模型\u002F配置 备份还原 |\n\n## 机器人触发指令 \u002F Bot Commands\n\n| 指令 | 功能 |\n|------|------|\n| `ComfyUI检测` | 环境检测 |\n| `启动ComfyUI` | 一键启动 |\n| `生成文生图工作流` | 生成txt2img |\n| `生成ControlNet工作流` | 生成ControlNet |\n| `ComfyUI显存优化` | VRAM优化 |\n| `ComfyUI修复` | 报错修复 |\n| `ComfyUI增强功能` | 查看V8增强功能 |\n",{"name":5,"description":7},"master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fc\u002Fcomfyui-v8",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill comfyui-v8",{"tool":39,"command":40},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill comfyui-v8",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill comfyui-v8","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fc\u002Fcomfyui-v8\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]