不想分享就别分享，藏着掖着的

[CoderXiaopang]

首先，requirements 里面的版本号是冲突的，如果按照这个来安装报错一大堆；
其次，代码依赖很多本地文件运行，“/home/amax/workspace/ruixie/SeeSR/**”

有什么意思呢？ 发仓库的目的是啥呢？

Traceback (most recent call last):
File "/root/autodl-tmp/AddSR/test_addsr.py", line 22, in
from pipelines.pipeline_addsr import StableDiffusionControlNetPipeline
File "/root/autodl-tmp/AddSR/pipelines/pipeline_addsr.py", line 57, in
RAM = ram(pretrained='/home/amax/workspace/ruixie/SeeSR/preset/ram_swin_large_14m.pth',
File "/root/autodl-tmp/AddSR/ram/models/ram_lora.py", line 319, in ram
model = RAMLora(**kwargs)
File "/root/autodl-tmp/AddSR/ram/models/ram_lora.py", line 107, in init
self.tokenizer = init_tokenizer()
File "/root/autodl-tmp/AddSR/ram/models/utils.py", line 131, in init_tokenizer
tokenizer = BertTokenizer.from_pretrained('/home/amax/workspace/ruixie/SeeSR/ram/bert')
File "/root/miniconda3/envs/addsr/lib/python3.9/site-packages/transformers/tokenization_utils_base.py", line 1760, in from_pretrained
resolved_vocab_files[file_id] = cached_file(
File "/root/miniconda3/envs/addsr/lib/python3.9/site-packages/transformers/utils/hub.py", line 409, in cached_file
resolved_file = hf_hub_download(
File "/root/miniconda3/envs/addsr/lib/python3.9/site-packages/huggingface_hub/utils/_validators.py", line 106, in _inner_fn
validate_repo_id(arg_value)
File "/root/miniconda3/envs/addsr/lib/python3.9/site-packages/huggingface_hub/utils/_validators.py", line 154, in validate_repo_id
raise HFValidationError(
huggingface_hub.errors.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '/home/amax/workspace/ruixie/SeeSR/ram/bert'.

[CSRuiXie]

Sorry for the inconvenience. Regarding the requirements, some packages may have been updated, leading to compatibility issues. We now provide detailed version information for each package. Since package dependencies can vary across different devices, you can follow the error messages to adjust and install the correct packages.

As for the paths, some model weight paths were previously hard-coded and required manual configuration. We have now replaced these with clearer instructions. You can follow the provided guide to download the weight files and set the path to your locally downloaded files, and the setup should work as expected.