RuntimeError: self.size(-1) must be divisible by 4 to view Byte as Float (different element sizes), but got 4255598

[roenLSP]

Hi guys, anybody meet this error. please help.
No module 'xformers'. Proceeding without it.
Loading weights [298f2e0447] from D:\sd\stable-diffusion-webui\models\Stable-diffusion\v1-5-pruned-emaonly.safetensors
loading stable diffusion model: RuntimeError
Traceback (most recent call last):
File "D:\sd\stable-diffusion-webui\webui.py", line 111, in initialize
modules.sd_models.load_model()
File "D:\sd\stable-diffusion-webui\modules\sd_models.py", line 383, in load_model
state_dict = get_checkpoint_state_dict(checkpoint_info, timer)
File "D:\sd\stable-diffusion-webui\modules\sd_models.py", line 238, in get_checkpoint_state_dict
res = read_state_dict(checkpoint_info.filename)
File "D:\sd\stable-diffusion-webui\modules\sd_models.py", line 217, in read_state_dict
pl_sd = safetensors.torch.load_file(checkpoint_file, device=device)
File "D:\sd\stable-diffusion-webui\roman\lib\site-packages\safetensors\torch.py", line 100, in load_file
result[k] = f.get_tensor(k)
RuntimeError: self.size(-1) must be divisible by 4 to view Byte as Float (different element sizes), but got 4255598

[kenxing999]

hi, it's seem that the file "v1-5-pruned-emaonly.safetensors" is broken.
You can download it again from https://huggingface.co/runwayml/stable-diffusion-v1-5/blob/main/v1-5-pruned-emaonly.safetensors
to fix this error.
the file is localated in folder "..\stable-diffusion-webui\models\Stable-diffusion"

[fivenull]

loading stable diffusion model: RuntimeError

[fivenull]

Python 3.9.6 (default，0ct 18 222，12:41:4)[Clang 14.0.(clang-1400..29.22)]Commit hash:22bcc7be428c94e9408f589966c2040187245d81
Installing requirements for Web UILaunching Web UI with arguments: --skip-torch-cuda-test --upcast-sampling --no-half-vae --use-cpu interrogateWarning: caught exception 'Torch not compiled with CUDA enabled', memory monitor
disabled
No module 'xformers'.Proceeding without it.
You are running torch 1.12.1.
The program is tested to work with torch 1.13.1.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 asthere are reports of issues with training tab on the latest version.
Use --skip-version-check commandline argument to disable this check.Loading weights[d3c56b2016] from /Users/hello/stable-diffusion-webui/models/Stable-diffusion/v1-5-pruned-emaonly.safetensorsloading stable diffusion model: RuntimeErrorTraceback (most recent call last):File "/Users/hello/stable-diffusion-webui/webui.py"，line 139，in initializ
modules.sd_models.load model()File"/Users/hello/stable-diffusion-webui/modules/sd_models.py"，line 415
in load model
state_dict = get_checkpoint_state_dict(checkpoint_info, timer)File"/Users/hello/stable-diffusion-webui/modules/sd_models.py"，line 262in get_checkpoint_state_dict
res = read_state_dict(checkpoint info.filename)File"/Users/hello/stable-diffusion-webui/modules/sd_models.py"，line 241in read_state_dict
pl_sd = safetensors,torch.load file(checkpoint file, device=device)File"/Users/hello/stable-diffusion-webui/venv/lib/python3.9/site-packages/safetensors/torch.py"，line 101， in load file
result[k] =f.get tensor(k)RuntimeError: self.size(-1) must be divisible by 4 to view Byte as Float (different element sizes)， but got 12928314
Stable diffusion model failed to load，exiting

[soueer]

Maybe effective, I'm trying

[soueer]

Thx!!! Successfullly!!

[Oooer8]

thx!!amazing!

[qiaowei361]

thx

[asheng77]

怎么搞的啊 老哥

[Marchccc]

If the model has not been downloaded and is interrupted, try deleting the/~/. cache/plugingface folder and try again