Open sgpt55 opened 1 year ago
File "...\stable-diffusion-webui\modules\esrgan_model.py", line 24, in fix_model_layers raise Exception("The file is not a ESRGAN model.") Exception: The file is not a ESRGAN model.
have some other error but looks something big broke today.
I have had this issue also for two days now.
I'm seeing the exact same error. I tested by removing all my embeds and relaunching, no errors. Replacing my embeds and errors return.
All my embeds came from hugging face or my training on google colab
I found the problem.
>>> import zipfile
>>> [i for i in zipfile.ZipFile('./embeddings/sks.pt').namelist() if i.endswith("/data.pkl")]
['sks/data.pkl']
here is my quick hack:
diff --git a/modules/safe.py b/modules/safe.py
index 399165a..dd57f75 100644
--- a/modules/safe.py
+++ b/modules/safe.py
@@ -74,9 +74,10 @@ def check_pt(filename):
# new pytorch format is a zip file
with zipfile.ZipFile(filename) as z:
- check_zip_filenames(filename, z.namelist())
+# check_zip_filenames(filename, z.namelist())
- with z.open('archive/data.pkl') as file:
+ dpath = [i for i in z.namelist() if i.endswith("/data.pkl")][0]
+ with z.open(dpath) as file:
unpickler = RestrictedUnpickler(file)
unpickler.load()
@nazodane could you pls elaborate whats going on? i applied your patch and the error is no longer showing but i still cant see any embeddings in the train tab
i checked on colab, with current commit, --disable-safe-unpickle
still has the same issue
I'm seeing this today while trying to use the Train tab. I create the embedding and then it won't load. Same error.
i think this problem usually happen when you downloaded an embed from wrong/outdated links
Even adding --disable-safe-unpickle
still didn't solve the issue.I can still see the error code in cmd.
`*** Error loading embedding rabbit.pt
Traceback (most recent call last):
File "G:\stable-diffusion-webui-master\modules\textual_inversion\textual_inversion.py", line 219, in load_from_dir
self.load_from_file(fullfn, fn)
File "G:\stable-diffusion-webui-master\modules\textual_inversion\textual_inversion.py", line 178, in load_from_file
if 'string_to_param' in data:
^^^^^^^^^^^^^^^^^^^^^^^^^
File "G:\stable-diffusion-webui-master\venv\Lib\site-packages\torch_tensor.py", line 999, in contains
raise RuntimeError(
RuntimeError: Tensor.contains only supports Tensor or scalar, but you passed in a <class 'str'>.
*** Error loading embedding rabbit_optimized.pt Traceback (most recent call last): File "G:\stable-diffusion-webui-master\modules\textual_inversion\textual_inversion.py", line 219, in load_from_dir self.load_from_file(fullfn, fn) File "G:\stable-diffusion-webui-master\modules\textual_inversion\textual_inversion.py", line 178, in load_from_file if 'string_to_param' in data: ^^^^^^^^^^^^^^^^^^^^^^^^^ File "G:\stable-diffusion-webui-master\venv\Lib\site-packages\torch_tensor.py", line 999, in contains raise RuntimeError( RuntimeError: Tensor.contains only supports Tensor or scalar, but you passed in a <class 'str'>.
---`
Hi there, as long as I put an embedding file under /embeddings, the program will throw the info as follows:
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)] Commit hash: cc5803603b8591075542d99ae8596ab5b130a82f Installing requirements for Web UI Launching Web UI with arguments: LatentDiffusion: Running in eps-prediction mode DiffusionWrapper has 859.52 M params. making attention of type 'vanilla' with 512 in_channels Working with z of shape (1, 4, 32, 32) = 4096 dimensions. making attention of type 'vanilla' with 512 in_channels Loading weights [45dee52b] from C:\Users\sgpt5\stable-diffusion-webui\models\Stable-diffusion\model.ckpt Global Step: 487750 Applying cross attention optimization (Doggettx). Model loaded. **Error verifying pickled file from C:\Users\sgpt5\stable-diffusion-webui\embeddings\mignon-62500.pt: Traceback (most recent call last): File "C:\Users\sgpt5\stable-diffusion-webui\modules\safe.py", line 76, in check_pt with zipfile.ZipFile(filename) as z: File "C:\Users\sgpt5\AppData\Local\Programs\Python\Python310\lib\zipfile.py", line 1267, in init self._RealGetContents() File "C:\Users\sgpt5\AppData\Local\Programs\Python\Python310\lib\zipfile.py", line 1334, in _RealGetContents raise BadZipFile("File is not a zip file") zipfile.BadZipFile: File is not a zip file
During handling of the above exception, another exception occurred:
Traceback (most recent call last): File "C:\Users\sgpt5\stable-diffusion-webui\modules\safe.py", line 97, in load check_pt(filename) File "C:\Users\sgpt5\stable-diffusion-webui\modules\safe.py", line 89, in check_pt unpickler.load() _pickle.UnpicklingError: invalid load key, '\x0a'.
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. Error loading emedding mignon-62500.pt: Traceback (most recent call last): File "C:\Users\sgpt5\stable-diffusion-webui\modules\textual_inversion\textual_inversion.py", line 132, in load_textual_inversion_embeddings process_file(fullfn, fn) File "C:\Users\sgpt5\stable-diffusion-webui\modules\textual_inversion\textual_inversion.py", line 102, in process_file if 'string_to_param' in data: TypeError: argument of type 'NoneType' is not iterable
Loaded a total of 0 textual inversion embeddings.** Running on local URL: http://127.0.0.1:7860
To create a public link, set
share=True
inlaunch()
.I've been up-to-date and tried different embedding files, using Waifu Diffusion 1.2 weights and corresponding embedding file.