Update guide_zh.md

guide_zh.md

@@ -1,4 +1,7 @@
-# Nieta Lumina2.0 ComfyUI User Manual (Internal Test Version)
+# Nieta Lumina2.0 ComfyUI 使用手册 (Lumina2.0 ComfyUI User Manual) - guide_zh.md
+
+本手册旨在帮助用户快速上手 Nieta Lumina2.0 ใน ComfyUI。原始文档信息来源于QQ群，现已适配为Hugging Face Markdown格式。
+(This manual aims to help users quickly get started with Nieta Lumina2.0 in ComfyUI. The original document information came from a QQ group and has now been adapted to Hugging Face Markdown format.)
 
 ## 一、环境准备 (Environment Preparation)
 
@@ -7,13 +10,16 @@
 | 组件类型 (Component Type) | 下载地址 (Download Address)                               | 备注 (Remarks)                                  |
 | :------------------------ | :-------------------------------------------------------- | :---------------------------------------------- |
 | Lumina DIT 模型          | [NebulaeWis/NietaAniLumina_Alpha · Hugging Face](https://huggingface.co/NebulaeWis/NietaAniLumina_Alpha) | 后缀为 `.pth` 的模型文件 (Model file with .pth extension) |
-| Text Encoder              | Gemma2 FP16                                               | 需下载 `gemma_2_2b_fp16.safetensors` (Need to download gemma_2_2b_fp16.safetensors) |
-| VAE                       | Flux 16ch VAE                                             | 需下载 `ae.safetensors` (Need to download ae.safetensors) |
+| Text Encoder              | [gemma_2_2b_fp16.safetensors](https://huggingface.co/Comfy-Org/Lumina_Image_2.0_Repackaged/blob/main/split_files/text_encoders/gemma_2_2b_fp16.safetensors) | `gemma_2_2b_fp16.safetensors` 文件                   |
+| VAE                       | [ae.safetensors](https://huggingface.co/Comfy-Org/Lumina_Image_2.0_Repackaged/blob/main/split_files/vae/ae.safetensors) | `ae.safetensors` 文件                             |
 
-### 2. 软件要求 (Software Requirements)
+### 2. 软件与工作流 (Software and Workflow)
 
-* ComfyUI 最新版（必须更新至最新版本）。(Latest version of ComfyUI - must be updated to the latest version).
-* 工作流文件（可通过导入群内官方工作流快速配置）。(Workflow file - can be quickly configured by importing the official workflow from the group).
+* **ComfyUI**: 必须更新至最新版本。(Must be updated to the latest version).
+* **工作流文件 (Workflow File)**:
+    * 推荐使用官方优化参数的JSON工作流文件。 (It is recommended to use the official JSON workflow file with optimized parameters.)
+    * 示例工作流文件(The example workflow file ) [lumina_workflow.json](./lumina_workflow.json) 
+    * 通过 ComfyUI 的 "Load" 功能导入工作流文件即可快速配置。(Quickly configure by importing the workflow file through ComfyUI's "Load" function.)
 
 ## 二、模型加载配置 (Model Loading Configuration)
 
@@ -21,11 +27,11 @@
 
 | 节点名称 (Node Name)       | 参数设置 (Parameter Settings)             | 示例值 / 备注 (Example Value / Remarks)                                  |
 | :------------------------- | :---------------------------------------- | :----------------------------------------------------------------------- |
-| UNETLoader                 | 模型路径选择 (Model path selection)       | `lu2/results_cosine_2e-4_bs64_infallssssuum/checkpoint-e4_s68300/consolidated.00-of-01.pth` |
-| ModelSamplingAuraFlow      | 移位值 (Shift) (Shift value)             | `6.00`（官方推荐值）(Official recommended value)                         |
-| VAELoader                  | VAE 文件选择 (VAE file selection)         | `ae.safetensors`                                                         |
-| CLIPLoader                 | Text Encoder 选择 (Text Encoder selection) | `gemma_2_2b_fp16.safetensors`，预设选 `lumina2` (preset select lumina2) |
-| EmptySD3LatentImage        | 分辨率设置 (Resolution settings)          | 默认 `1024x1552`（支持 `1024 - 1280` 分辨率）(Default 1024x1552, supports 1024 - 1280 resolution) |
+| UNETLoader                 | 模型路径选择 (Model path selection)       | `lu2/results_cosine_2e-4_bs64_infallssssuum/checkpoint-e4_s68300/consolidated.00-of-01.pth` (请根据实际下载路径修改 Please modify according to your actual download path) |
+| ModelSamplingAuraFlow      | 移位值 (Shift) (Shift value)             | `6.00`（官方推荐值 Official recommended value）                         |
+| VAELoader                  | VAE 文件选择 (VAE file selection)         | `ae.safetensors` (请确保已下载并放置到ComfyUI的VAE目录下 Please ensure it's downloaded and placed in ComfyUI's VAEs directory) |
+| CLIPLoader                 | Text Encoder 选择 (Text Encoder selection) | `gemma_2_2b_fp16.safetensors`，预设选 `lumina2` (preset select lumina2; 请确保已下载并放置到ComfyUI的CLIP目录下 Please ensure it's downloaded and placed in ComfyUI's CLIPs directory) |
+| EmptySD3LatentImage        | 分辨率设置 (Resolution settings)          | 默认 `1024x1552`（支持 `1024 - 1280` 分辨率 Default 1024x1552, supports 1024 - 1280 resolution) |
 
 ## 三、提示词规范 (Prompt Specification)
 
@@ -77,10 +83,8 @@ UNET → AuraFlow采样 (AuraFlow Sampling) → KSampler → VAE解码 (VAE Deco
 ## 六、注意事项 (Precautions)
 
 1.  括号权重需转义：`\(word\)`。(Parentheses for weights need to be escaped: `\(word\)`).
-2.  官方 JSON 工作流已优化参数，建议直接导入使用。(The official JSON workflow has optimized parameters; it is recommended to import and use it directly).
+2.  官方 JSON 工作流 (如 `lumina_workflow.json`) 已优化参数，建议直接导入使用。(The official JSON workflow (like `lumina_workflow.json`) has optimized parameters; it is recommended to import and use it directly).
 3.  多语言提示词效果需自行测试。(The effect of multilingual prompts needs to be tested by yourself).
-4.  目前lumina推荐的提示词格式是，tag+自然语言，但也支持纯tag和纯自然语言，大家可以多试试。(Currently, Lumina's recommended prompt format is tag + natural language, but it also supports pure tags and pure natural language. Everyone is encouraged to try them out).
-
-可通过导入群内相关json快速复现完整流程。(The complete process can be quickly reproduced by importing relevant JSON files from the group).
+4.  目前Lumina推荐的提示词格式是 "tag + 自然语言"，但也支持纯tag和纯自然语言，大家可以多试试。(Currently, Lumina's recommended prompt format is "tag + natural language", but it also supports pure tags and pure natural language. Everyone is encouraged to try them out).
 
 **注：本手册基于内测版本编写，部分参数可能随版本更新调整。** (Note: This manual is based on the internal test version, and some parameters may be adjusted with version updates.)