From e443e2032f7fb3889b261cbeb0173e93768153be Mon Sep 17 00:00:00 2001
From: Artiprocher <wangye87v5@hotmail.com>
Date: Thu, 4 Dec 2025 15:22:09 +0800
Subject: [PATCH] update docs

---
 README.md    | 13 +++++++++++--
 README_zh.md | 13 +++++++++++--
 2 files changed, 22 insertions(+), 4 deletions(-)

diff --git a/README.md b/README.md
index 89314de..9508526 100644
--- a/README.md
+++ b/README.md
@@ -209,12 +209,21 @@ If you meet problems during installation, they might be caused by upstream depen
 
 DiffSynth-Studio redesigns the inference and training pipelines for mainstream Diffusion models (including FLUX, Wan, etc.), enabling efficient memory management and flexible model training.
 
-> Before using model inference or training, you can configure the model download source via [environment variables](/docs/en/Pipeline_Usage/Environment_Variables.md). By default, this project downloads models from ModelScope. Users outside China can switch the download source to Hugging Face:
+<details>
+<summary>Environment Variable Configuration</summary>
+
+> Before running model inference or training, you can configure settings such as the model download source via [environment variables](/docs/en/Pipeline_Usage/Environment_Variables.md).
+>
+> By default, this project downloads models from ModelScope. For users outside China, you can configure the system to download models from the ModelScope international site as follows:
 >
 > ```python
 > import os
-> os.environ["DIFFSYNTH_DOWNLOAD_SOURCE"] = "huggingface"
+> os.environ["MODELSCOPE_DOMAIN"] = "www.modelscope.ai"
 > ```
+>
+> To download models from other sources, please modify the environment variable [DIFFSYNTH_DOWNLOAD_SOURCE](/docs/en/Pipeline_Usage/Environment_Variables.md#diffsynth_download_source).
+
+</details>
 
 ### Image Synthesis
 
diff --git a/README_zh.md b/README_zh.md
index 2c327be..d24f408 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -209,12 +209,21 @@ pip install diffsynth
 
 DiffSynth-Studio 为主流 Diffusion 模型（包括 FLUX、Wan 等）重新设计了推理和训练流水线，能够实现高效的显存管理、灵活的模型训练。
 
-> 在进行模型推理和训练前，可通过[环境变量](/docs/zh/Pipeline_Usage/Environment_Variables.md)配置模型下载源，本项目默认从魔搭社区下载模型，非中国用户可将模型下载源修改为 Huggingface：
+<details>
+<summary>环境变量配置</summary>
+
+> 在进行模型推理和训练前，可通过[环境变量](/docs/zh/Pipeline_Usage/Environment_Variables.md)配置模型下载源等。
+> 
+> 本项目默认从魔搭社区下载模型。对于非中国区域的用户，可以通过以下配置从魔搭社区的国际站下载模型：
 > 
 > ```python
 > import os
-> os.environ["DIFFSYNTH_DOWNLOAD_SOURCE"] = "huggingface"
+> os.environ["MODELSCOPE_DOMAIN"] = "www.modelscope.ai"
 > ```
+> 
+> 如需从其他站点下载，请修改[环境变量 DIFFSYNTH_DOWNLOAD_SOURCE](/docs/zh/Pipeline_Usage/Environment_Variables.md#diffsynth_download_source)。
+
+</details>
 
 ### 图像生成模型