From f3d2470e84059e56dce24c5394d1e3788fb898a4 Mon Sep 17 00:00:00 2001 From: Artiprocher Date: Thu, 24 Jul 2025 19:02:08 +0800 Subject: [PATCH] update README --- examples/flux/README.md | 2 +- examples/flux/README_zh.md | 2 +- examples/wanvideo/README.md | 7 +++++-- examples/wanvideo/README_zh.md | 7 +++++-- 4 files changed, 12 insertions(+), 6 deletions(-) diff --git a/examples/flux/README.md b/examples/flux/README.md index b1451d1..32cce4a 100644 --- a/examples/flux/README.md +++ b/examples/flux/README.md @@ -105,7 +105,7 @@ ModelConfig(path=[ ]) ``` -The `from_pretrained` method also provides extra arguments to control model loading behavior: +The `ModelConfig` method also provides extra arguments to control model loading behavior: * `local_model_path`: Path to save downloaded models. Default is `"./models"`. * `skip_download`: Whether to skip downloading. Default is `False`. If your network cannot access [ModelScope](https://modelscope.cn/ ), download the required files manually and set this to `True`. diff --git a/examples/flux/README_zh.md b/examples/flux/README_zh.md index aeade8f..28f1e10 100644 --- a/examples/flux/README_zh.md +++ b/examples/flux/README_zh.md @@ -105,7 +105,7 @@ ModelConfig(path=[ ]) ``` -`from_pretrained` 还提供了额外的参数用于控制模型加载时的行为： +`ModelConfig` 还提供了额外的参数用于控制模型加载时的行为： * `local_model_path`: 用于保存下载模型的路径，默认值为 `"./models"`。 * `skip_download`: 是否跳过下载，默认值为 `False`。当您的网络无法访问[魔搭社区](https://modelscope.cn/)时，请手动下载必要的文件，并将其设置为 `True`。 diff --git a/examples/wanvideo/README.md b/examples/wanvideo/README.md index 1b78e78..2c811f5 100644 --- a/examples/wanvideo/README.md +++ b/examples/wanvideo/README.md @@ -121,11 +121,14 @@ ModelConfig(path=[ ]) ``` -The `from_pretrained` function also provides additional parameters to control the behavior during model loading: +The `ModelConfig` function provides additional parameters to control the behavior during model loading: -* `tokenizer_config`: Path to the tokenizer of the Wan model. Default value is `ModelConfig(model_id="Wan-AI/Wan2.1-T2V-1.3B", origin_file_pattern="google/*")`. * `local_model_path`: Path where downloaded models are saved. Default value is `"./models"`. * `skip_download`: Whether to skip downloading models. Default value is `False`. When your network cannot access [ModelScope](https://modelscope.cn/), manually download the necessary files and set this to `True`. + +The `from_pretrained` function provides additional parameters to control the behavior during model loading: + +* `tokenizer_config`: Path to the tokenizer of the Wan model. Default value is `ModelConfig(model_id="Wan-AI/Wan2.1-T2V-1.3B", origin_file_pattern="google/*")`. * `redirect_common_files`: Whether to redirect duplicate model files. Default value is `True`. Since the Wan series models include multiple base models, some modules like text encoder are shared across these models. To avoid redundant downloads, we redirect the model paths. * `use_usp`: Whether to enable Unified Sequence Parallel. Default value is `False`. Used for multi-GPU parallel inference. diff --git a/examples/wanvideo/README_zh.md b/examples/wanvideo/README_zh.md index d9cd43b..517cd9e 100644 --- a/examples/wanvideo/README_zh.md +++ b/examples/wanvideo/README_zh.md @@ -120,11 +120,14 @@ ModelConfig(path=[ ]) ``` -`from_pretrained` 还提供了额外的参数用于控制模型加载时的行为： +`ModelConfig` 提供了额外的参数用于控制模型加载时的行为： -* `tokenizer_config`: Wan 模型的 tokenizer 路径，默认值为 `ModelConfig(model_id="Wan-AI/Wan2.1-T2V-1.3B", origin_file_pattern="google/*")`。 * `local_model_path`: 用于保存下载模型的路径，默认值为 `"./models"`。 * `skip_download`: 是否跳过下载，默认值为 `False`。当您的网络无法访问[魔搭社区](https://modelscope.cn/)时，请手动下载必要的文件，并将其设置为 `True`。 + +`from_pretrained` 提供了额外的参数用于控制模型加载时的行为： + +* `tokenizer_config`: Wan 模型的 tokenizer 路径，默认值为 `ModelConfig(model_id="Wan-AI/Wan2.1-T2V-1.3B", origin_file_pattern="google/*")`。 * `redirect_common_files`: 是否重定向重复模型文件，默认值为 `True`。由于 Wan 系列模型包括多个基础模型，每个基础模型的 text encoder 等模块都是相同的，为避免重复下载，我们会对模型路径进行重定向。 * `use_usp`: 是否启用 Unified Sequence Parallel，默认值为 `False`。用于多 GPU 并行推理。