23-25.2.21-文生图相关练习-林方老师 #695

New Issue

Zxl_15810225315 · 2025-04-17T00:02:10+08:00

Zxl_15810225315 commented

2025-04-17 00:02:10 +08:00

在autodl中部署完下载完文件后按python app.py --output_dir="resource/demo/output" --mixed_precision="bf16" --allow_tf32命令启动报错：An error occurred while trying to fetch booksforcharlie/stable-diffusion-inpainting: booksforcharlie/stable-diffusion-inpainting does not appear to have a file named diffusion_pytorch_model.safetensors.
Defaulting to unsafe serialization. Pass allow_pickle=False to raise an error instead.
/root/CatVTON-edited/CatVTON-edited/model/SCHP/init.py:93: FutureWarning: You are using torch.load with weights_only=False (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for weights_only will be flipped to True. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via torch.serialization.add_safe_globals. We recommend you start setting weights_only=True for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
state_dict = torch.load(ckpt_path, map_location='cpu')['state_dict']
Traceback (most recent call last):
File "/root/CatVTON-edited/CatVTON-edited/app.py", line 373, in
app_gradio()
File "/root/CatVTON-edited/CatVTON-edited/app.py", line 356, in app_gradio
submit.click(
File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/site-packages/gradio/blocks.py", line 2089, in exit
self.config = self.get_config_file()
File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/site-packages/gradio/blocks.py", line 2061, in get_config_file
config.update(self.default_config.get_config()) # type: ignore
File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/site-packages/gradio/blocks.py", line 887, in get_config
block_config["api_info"] = block.api_info() # type: ignore
File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/site-packages/gradio/components/base.py", line 325, in api_info
schema = self.data_model.model_json_schema()
File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/site-packages/pydantic/main.py", line 555, in model_json_schema
return model_json_schema(
File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/site-packages/pydantic/json_schema.py", line 2404, in model_json_schema
schema_generator_instance = schema_generator(by_alias=by_alias, ref_template=ref_template)
File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/site-packages/pydantic/json_schema.py", line 278, in init
self.schema_type_to_method = self.build_schema_type_to_method()
File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/site-packages/pydantic/json_schema.py", line 317, in build_schema_type_to_method
method_name = f'{key.replace("-", "")}_schema'
File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/typing.py", line 647, in getattr
return getattr(self.origin, attr)
AttributeError: '_SpecialForm' object has no attribute 'replace'
请老师帮忙看下是什么原因，我自己登录https://huggingface.co/booksforcharlie/stable-diffusion-inpainting 确实没找到对应的模型文件，gradio的版本也是一直提示要升级，升级完成后也一直报不兼容

在autodl中部署完下载完文件后按python app.py --output_dir="resource/demo/output" --mixed_precision="bf16" --allow_tf32命令启动报错：An error occurred while trying to fetch booksforcharlie/stable-diffusion-inpainting: booksforcharlie/stable-diffusion-inpainting does not appear to have a file named diffusion_pytorch_model.safetensors. Defaulting to unsafe serialization. Pass `allow_pickle=False` to raise an error instead. /root/CatVTON-edited/CatVTON-edited/model/SCHP/__init__.py:93: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. state_dict = torch.load(ckpt_path, map_location='cpu')['state_dict'] Traceback (most recent call last): File "/root/CatVTON-edited/CatVTON-edited/app.py", line 373, in <module> app_gradio() File "/root/CatVTON-edited/CatVTON-edited/app.py", line 356, in app_gradio submit.click( File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/site-packages/gradio/blocks.py", line 2089, in __exit__ self.config = self.get_config_file() File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/site-packages/gradio/blocks.py", line 2061, in get_config_file config.update(self.default_config.get_config()) # type: ignore File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/site-packages/gradio/blocks.py", line 887, in get_config block_config["api_info"] = block.api_info() # type: ignore File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/site-packages/gradio/components/base.py", line 325, in api_info schema = self.data_model.model_json_schema() File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/site-packages/pydantic/main.py", line 555, in model_json_schema return model_json_schema( File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/site-packages/pydantic/json_schema.py", line 2404, in model_json_schema schema_generator_instance = schema_generator(by_alias=by_alias, ref_template=ref_template) File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/site-packages/pydantic/json_schema.py", line 278, in __init__ self._schema_type_to_method = self.build_schema_type_to_method() File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/site-packages/pydantic/json_schema.py", line 317, in build_schema_type_to_method method_name = f'{key.replace("-", "_")}_schema' File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/typing.py", line 647, in __getattr__ return getattr(self.__origin__, attr) AttributeError: '_SpecialForm' object has no attribute 'replace' 请老师帮忙看下是什么原因，我自己登录https://huggingface.co/booksforcharlie/stable-diffusion-inpainting 确实没找到对应的模型文件，gradio的版本也是一直提示要升级，升级完成后也一直报不兼容

wsh1061368159 commented

2025-04-17 10:04:39 +08:00

可以去modelscope上找到这个预训练模型，下载到本地，再修改代码中加载模型的地址。gradio版本升级提示，如果不是报错可以忽略

Zxl_15810225315 commented

2025-04-17 22:08:20 +08:00

可以去modelscope上找到这个预训练模型，下载到本地，再修改代码中加载模型的地址。gradio版本升级提示，如果不是报错可以忽略

第一、自行下载模型后，报缺失scheduler_config.json
Traceback (most recent call last):
File "/root/CatVTON-edited/CatVTON-edited/app.py", line 106, in
pipeline = CatVTONPipeline(
File "/root/CatVTON-edited/CatVTON-edited/model/pipeline.py", line 39, in init
self.noise_scheduler = DDIMScheduler.from_pretrained(base_ckpt, subfolder="scheduler")
File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
return fn(*args, **kwargs)
File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/site-packages/diffusers/schedulers/scheduling_utils.py", line 150, in from_pretrained
config, kwargs, commit_hash = cls.load_config(
File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
return fn(*args, **kwargs)
File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/site-packages/diffusers/configuration_utils.py", line 373, in load_config
raise EnvironmentError(
OSError: Error no file named scheduler_config.json found in directory
第二、自己创建这个文件并添加完参数后，又报错：
Traceback (most recent call last):
File "/root/CatVTON-edited/CatVTON-edited/app.py", line 106, in
pipeline = CatVTONPipeline(
File "/root/CatVTON-edited/CatVTON-edited/model/pipeline.py", line 42, in init
self.feature_extractor = CLIPImageProcessor.from_pretrained(base_ckpt, subfolder="feature_extractor")
File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/site-packages/transformers/image_processing_base.py", line 206, in from_pretrained
image_processor_dict, kwargs = cls.get_image_processor_dict(pretrained_model_name_or_path, **kwargs)
File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/site-packages/transformers/image_processing_base.py", line 335, in get_image_processor_dict
resolved_image_processor_file = cached_file(
File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/site-packages/transformers/utils/hub.py", line 374, in cached_file
raise EnvironmentError(
OSError: /root/good does not appear to have a file named feature_extractor/preprocessor_config.json. Checkout 'https://huggingface.co//root/good/tree/main' for available files.
老师，我想咨询下，完全按照文档走下来的，您那边没遇到这个问题吗？还是说您下载的版本和我下载的git版本不一样导致的？https://github.com/Zheng-Chong/CatVTON 您能明确下到底是哪个分支或版本吗？实在不行我重新下载一版也可以，我登录了这个项目的git，查了下他们的问题列表中2024年就有这个问题，并且没有结论

> 可以去modelscope上找到这个预训练模型，下载到本地，再修改代码中加载模型的地址。gradio版本升级提示，如果不是报错可以忽略第一、自行下载模型后，报缺失scheduler_config.json Traceback (most recent call last): File "/root/CatVTON-edited/CatVTON-edited/app.py", line 106, in <module> pipeline = CatVTONPipeline( File "/root/CatVTON-edited/CatVTON-edited/model/pipeline.py", line 39, in __init__ self.noise_scheduler = DDIMScheduler.from_pretrained(base_ckpt, subfolder="scheduler") File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/site-packages/diffusers/schedulers/scheduling_utils.py", line 150, in from_pretrained config, kwargs, commit_hash = cls.load_config( File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/site-packages/diffusers/configuration_utils.py", line 373, in load_config raise EnvironmentError( OSError: Error no file named scheduler_config.json found in directory 第二、自己创建这个文件并添加完参数后，又报错： Traceback (most recent call last): File "/root/CatVTON-edited/CatVTON-edited/app.py", line 106, in <module> pipeline = CatVTONPipeline( File "/root/CatVTON-edited/CatVTON-edited/model/pipeline.py", line 42, in __init__ self.feature_extractor = CLIPImageProcessor.from_pretrained(base_ckpt, subfolder="feature_extractor") File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/site-packages/transformers/image_processing_base.py", line 206, in from_pretrained image_processor_dict, kwargs = cls.get_image_processor_dict(pretrained_model_name_or_path, **kwargs) File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/site-packages/transformers/image_processing_base.py", line 335, in get_image_processor_dict resolved_image_processor_file = cached_file( File "/root/autodl-tmp/conda/envs/cat/lib/python3.9/site-packages/transformers/utils/hub.py", line 374, in cached_file raise EnvironmentError( OSError: /root/good does not appear to have a file named feature_extractor/preprocessor_config.json. Checkout 'https://huggingface.co//root/good/tree/main' for available files. 老师，我想咨询下，完全按照文档走下来的，您那边没遇到这个问题吗？还是说您下载的版本和我下载的git版本不一样导致的？https://github.com/Zheng-Chong/CatVTON 您能明确下到底是哪个分支或版本吗？实在不行我重新下载一版也可以，我登录了这个项目的git，查了下他们的问题列表中2024年就有这个问题，并且没有结论

Zxl_15810225315 commented

2025-04-17 22:09:04 +08:00

@wsh1061368159 老师帮忙看下，谢谢