SD xl train_textual_inversion.py，训练的时候，会默认去链接hugging face。

/home/wangjintang/mindone/examples/stable_diffusion_xl/gm/modules/embedders/modules.py class FrozenOpenCLIPEmbedder2_CLIPTokenizer(FrozenOpenCLIPEmbedder2): """ A wrapper over FrozenOpenCLIPEmbedder2 to use the CLIPTokenizer (from transformer library) instead of SimpleTokenizer clip tokenizer from 'openai/clip-vit-large-patch14' is the same as the tokenizer from 'laion/CLIP-ViT-H-14-laion2B-s32B-b79K' """

def __init__(self, *args, **kwargs):
    super().__init__(*args, **kwargs)
    self.tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-large-patch14")

报错在这里。

Thanks for sending an issue! Here are some tips for you:

If this is your first time, please read our contributor guidelines: https://github.com/mindspore-ai/mindspore/blob/master/CONTRIBUTING.md

Hardware Environment | 硬件环境

please tell us what kind of hardware can reproduce your error? 请告诉我们您报错的后端类型
- [x] Ascend
- [ ] GPU
- [ ] CPU

Software Environment | 软件环境

MindSpore version: 请告诉我们您正在使用的MindSpore版本：
- [ ] 2.1
- [ ] 2.0.0
- [x] other (please state here): _____
Python version(e.g., 3.7.5):
OS(e.g., Linux Ubuntu 16.04)
GCC/Compiler version:

Describe the current behavior | 目前输出

e.g. the current output is xxx/ the error is xxx/ 目前的输出是xx 、目前的报错是关于xx

Describe the expected behavior | 期望输出

please describe expected outputs or functions you want to have: 请告诉我们您期望得到的结果或功能

Steps to reproduce the issue | 复现报错的步骤

code url | 代码链接:
command that can reproduce your error | 可以复现报错的命令 e.g. cd xx -> bash scripts/xx.sh --config xx
xx

mindspore-lab / mindone