search

lshqqytiger / stable-diffusion-webui-amdgpu

Stable Diffusion web UI
GNU Affero General Public License v3.0
1.8k stars 186 forks source link

[Bug]:fatal: No names found, cannot describe anything. #245

Closed skywizeskychan closed 7 months ago

skywizeskychan commented 1 year ago

Is there an existing issue for this?

What happened?

Running with AMD, after a while I will run out of memory, and have to close and restart my computer to clear this.

Sometimes, (not always) when I then run my webui.settings.bat I will get the error message fatal: No names found, cannot describe anything.

And of course then nothing will work.

Steps to reproduce the problem

  1. Go to .... After having run out of memory close all windows and restart
  2. Press .... run the webui.bat file
  3. ... get the warning message as part of the resulting text in the cmd window

What should have happened?

It should run normally?

Version or Commit where the problem happens

Commit hash: 8ea37a924696435e1d777a2d5ab2909d64ce8975

What Python version are you running on ?

Python 3.10.x

What platforms do you use to access the UI ?

Windows

What device are you running WebUI on?

AMD GPUs

Cross attention optimization

Automatic

What browsers do you use to access the UI ?

Microsoft Edge

Command Line Arguments

@echo off

set PYTHON=
set GIT=
set VENV_DIR=
set COMMANDLINE_ARGS=--opt-sub-quad-attention --lowvram --disable-nan-check
call webui.bat

List of extensions

no

Console logs

venv "C:\Users\skywi\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
NVIDIA driver was found. Automatically changed backend to 'cuda'. You can manually select which backend will be used through '--backend' argument.
fatal: No names found, cannot describe anything.
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: ## 1.4.1
Commit hash: 8ea37a924696435e1d777a2d5ab2909d64ce8975
Installing requirements
Launching Web UI with arguments: --opt-sub-quad-attention --lowvram --disable-nan-check
No module 'xformers'. Proceeding without it.
Loading weights [9c59842129] from C:\Users\skywi\stable-diffusion-webui-directml\models\Stable-diffusion\dosmix_.safetensors
preload_extensions_git_metadata for 7 extensions took 0.00s
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Startup time: 22.7s (import torch: 6.3s, import gradio: 2.7s, import ldm: 2.2s, other imports: 7.2s, list SD models: 0.1s, load scripts: 1.6s, create ui: 1.5s, gradio launch: 0.7s).
Creating model from config: C:\Users\skywi\stable-diffusion-webui-directml\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying attention optimization: sub-quadratic... done.
Textual inversion embeddings loaded(0):
Model loaded in 44.0s (load weights from disk: 2.6s, create model: 4.5s, apply weights to model: 23.5s, apply half(): 12.2s, load textual inversion embeddings: 0.1s, calculate empty prompt: 0.9s).

Additional information

No response

Sparks72 commented 1 year ago

I found that to run sd with AMD I needed to uninstall all the nvidia drivers, as it led to conflict