添加了ChilloutMix模型后，报错

hp_zerolan

安装完stable diffusion并成功启动
在“..\models\Stable-diffusion\”中放入“chilloutmixss_xss10.safetensors”后，重新启动webui-user.bat

结果如下报错，请问该如何解决？

venv "D:\AllProjects\GitHubProjects\stable-diffusion-webui\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Commit hash: 72cd27a13587c9579942577e9e3880778be195f6
Installing requirements
Launching Web UI with arguments:
No module 'xformers'. Proceeding without it.
==============================================================================
You are running torch 1.13.1+cu117.
The program is tested to work with torch 2.0.0.
To reinstall the desired version, run with commandline flag --reinstall-torch.
Beware that this will cause a lot of large files to be downloaded, as well as
there are reports of issues with training tab on the latest version.

Use --skip-version-check commandline argument to disable this check.
==============================================================================
Loading weights [7dc213110f] from D:\AllProjects\GitHubProjects\stable-diffusion-webui\models\Stable-diffusion\chilloutmixss_xss10.safetensors
Creating model from config: D:\AllProjects\GitHubProjects\stable-diffusion-webui\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Error verifying pickled file from C:\Users\hp_zerolan/.cache\huggingface\hub\models--openai--clip-vit-large-patch14\snapshots\8d052a0f05efbaefbc9e8786ba291cfdf93e5bff\pytorch_model.bin:
Traceback (most recent call last):
  File "D:\AllProjects\GitHubProjects\stable-diffusion-webui\modules\safe.py", line 132, in load_with_extra
    check_pt(filename, extra_handler)
  File "D:\AllProjects\GitHubProjects\stable-diffusion-webui\modules\safe.py", line 90, in check_pt
    unpickler.load()
  File "D:\AllProjects\GitHubProjects\stable-diffusion-webui\modules\safe.py", line 27, in persistent_load
    return TypedStorage(_internal=True)
TypeError: TypedStorage.__new__() got an unexpected keyword argument '_internal'


The file may be malicious, so the program is not going to read it.
You can skip this check with --disable-safe-unpickle commandline argument.


Failed to create model quickly; will retry using slow method.
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Error verifying pickled file from C:\Users\hp_zerolan/.cache\huggingface\hub\models--openai--clip-vit-large-patch14\snapshots\8d052a0f05efbaefbc9e8786ba291cfdf93e5bff\pytorch_model.bin:
Traceback (most recent call last):
  File "D:\AllProjects\GitHubProjects\stable-diffusion-webui\modules\safe.py", line 132, in load_with_extra
    check_pt(filename, extra_handler)
  File "D:\AllProjects\GitHubProjects\stable-diffusion-webui\modules\safe.py", line 90, in check_pt
    unpickler.load()
  File "D:\AllProjects\GitHubProjects\stable-diffusion-webui\modules\safe.py", line 27, in persistent_load
    return TypedStorage(_internal=True)
TypeError: TypedStorage.__new__() got an unexpected keyword argument '_internal'


The file may be malicious, so the program is not going to read it.
You can skip this check with --disable-safe-unpickle commandline argument.


loading stable diffusion model: AttributeError
Traceback (most recent call last):
  File "D:\AllProjects\GitHubProjects\stable-diffusion-webui\webui.py", line 195, in initialize
    modules.sd_models.load_model()
  File "D:\AllProjects\GitHubProjects\stable-diffusion-webui\modules\sd_models.py", line 447, in load_model
    sd_model = instantiate_from_config(sd_config.model)
  File "D:\AllProjects\GitHubProjects\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\util.py", line 89, in instantiate_from_config
    return get_obj_from_str(config["target"])(**config.get("params", dict()))
  File "D:\AllProjects\GitHubProjects\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 563, in __init__
    self.instantiate_cond_stage(cond_stage_config)
  File "D:\AllProjects\GitHubProjects\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 630, in instantiate_cond_stage
    model = instantiate_from_config(config)
  File "D:\AllProjects\GitHubProjects\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\util.py", line 89, in instantiate_from_config
    return get_obj_from_str(config["target"])(**config.get("params", dict()))
  File "D:\AllProjects\GitHubProjects\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\modules\encoders\modules.py", line 104, in __init__
    self.transformer = CLIPTextModel.from_pretrained(version)
  File "D:\AllProjects\GitHubProjects\stable-diffusion-webui\venv\lib\site-packages\transformers\modeling_utils.py", line 2258, in from_pretrained
    loaded_state_dict_keys = [k for k in state_dict.keys()]
AttributeError: 'NoneType' object has no attribute 'keys'


Stable diffusion model failed to load, exiting
请按任意键继续. . .

PhiltreX

从报错信息中可以看到，这个错误和模型没有任何关系，这是torch版本不兼容报错，你是不是pytorch_model.bin这个文件？

hp_zerolan

PhiltreX 发表于 2023-5-3 18:38
从报错信息中可以看到，这个错误和模型没有任何关系，这是torch版本不兼容报错，你是不是pytorch_model.bin ...

加入ChilloutMix模型后，确实提示下载“pytorch_model.bin”。但是已经下完了，下了好久。然后我把ChilloutMix新建个文件夹丢进去就能启动（“..\models\Stable-diffusion\新建文件夹”），放回“..\models\Stable-diffusion”就报错

hp_zerolan

不对。。我发现是个概率性问题？有时会有时又不报错。。。。

PhiltreX

hp_zerolan 发表于 2023-5-3 19:44
不对。。我发现是个概率性问题？有时会有时又不报错。。。。

我知道了，可能因为这个模型需要附加的VAE文件？

PhiltreX

可能因为pytorch_model文件需要PyTorch来加载，但是因为版本不一致，所以才会报错，建议尝试关闭自动加载VAE文件选项。