StableDiffusion WebUI 训练过程四个问题和解决过程
快快一姐
2022年10月19日 15:05

训练步骤参考:

网页链接​

 网页链接​

问题1:创建embedding 失败

日志:

Create a new embedding gives error

File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/sparse.py", line 160, in forward

    return F.embedding(

  File "/opt/conda/lib/python3.8/site-packages/torch/nn/functional.py", line 2206, in embedding

    return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)

RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument index in method wrapper__index_select)

解决方法:

https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/2208

去掉命令行中的--medvram

问题2:创建的embeddings 训练之前时候加载失败

失败日志

Error verifying pickled file

Error verifying pickled file from /root/stable-diffusion-webui/embeddings/handanyang.pt:

Traceback (most recent call last):

  File "/root/stable-diffusion-webui/modules/safe.py", line 97, in load

    check_pt(filename)

  File "/root/stable-diffusion-webui/modules/safe.py", line 77, in check_pt

    check_zip_filenames(filename, z.namelist())

  File "/root/stable-diffusion-webui/modules/safe.py", line 69, in check_zip_filenames

    raise Exception(f"bad file inside {filename}: {name}")

Exception: bad file inside /root/stable-diffusion-webui/embeddings/handanyang.pt: handanyang/data.pkl

解决方法:

命令行中加上--disable-safe-unpickle

https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/2235

问题3:刚开始训练时候,失败

 失败日志

    return forward_call(*input, **kwargs)

  File "/root/stable-diffusion-webui/repositories/stable-diffusion/ldm/models/diffusion/ddpm.py", line 879, in forward

    return self.p_losses(x, c, t, *args, **kwargs)

  File "/root/stable-diffusion-webui/repositories/stable-diffusion/ldm/models/diffusion/ddpm.py", line 1030, in p_losses

    logvar_t = self.logvar[t].to(self.device)

RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)

解决方法:

将出问题的变量t,存到CPU里面

编辑代码stable-diffusion/ldm/models/diffusion/ddpm.py第1030行上面,加上一行代码 t = t.to('cpu')

https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/2685

问题4:

训练了4%的时候失败;

失败日志

_imagingft C module is not installed

    font = ImageFont.truetype(textfont, fontsize)

  File "/opt/conda/lib/python3.8/site-packages/PIL/ImageFont.py", line 844, in truetype

    return freetype(font)

  File "/opt/conda/lib/python3.8/site-packages/PIL/ImageFont.py", line 841, in freetype

    return FreeTypeFont(font, size, index, encoding, layout_engine)

  File "/opt/conda/lib/python3.8/site-packages/PIL/ImageFont.py", line 169, in __init__

    if core.HAVE_RAQM:

  File "/opt/conda/lib/python3.8/site-packages/PIL/ImageFont.py", line 43, in __getattr__

    raise ImportError("The _imagingft C module is not installed")

ImportError: The _imagingft C module is not installed

解决方法:

重新安装pillow

apt-get install libfreetype6-dev

====================

pip uninstall pillow

pip install --no-cache-dir pillow

https://stackoverflow.com/questions/4011705/python-the-imagingft-c-module-is-not-installed

这样就可以开始训练了;