CODEWITHSUNDEEP
pythonartificial-intelligencestable-diffusion
newbie
newbie

Reputation: 57

Unable to run stable diffusion correctly

I'm new to SD, Ive installed required software and copied the model.ckpt to models\Stable-diffusion folder. theres no error in running "webui-user.bat" but Stable diffusion checkpoint takes forever to load that is why i'm unable to generate img.

What can possibly wrong with my setup?

Model is forever loading, tried replacing it with different model but no luck. enter image description here

setup details enter image description here

Here's my cmd logs when running webui-user.bat

Version: v1.4.0
Commit hash: 394ffa7b0a7fff3ec484bcd084e673a8b301ccc8
Installing requirements
Launching Web UI with arguments:
No module 'xformers'. Proceeding without it.
Loading weights [6ce0161689] from D:\stable\sd.webui\webui\models\Stable-diffusion\v1-5-pruned-emaonly.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: 8.9s (import torch: 3.1s, import gradio: 1.7s, import ldm: 0.7s, other imports: 1.5s, setup codeformer: 0.1s, load scripts: 0.9s, create ui: 0.4s, gradio launch: 0.4s).
Creating model from config: D:\stable\sd.webui\webui\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying attention optimization: Doggettx... done.
Textual inversion embeddings loaded(0):
Model loaded in 6.4s (load weights from disk: 0.9s, create model: 0.5s, apply weights to model: 1.1s, apply half(): 1.0s, move model to device: 2.2s, calculate empty prompt: 0.6s).

Upvotes: 0

Views: 4891

Answers (2)

user25216980
user25216980

Reputation: 1

For me, it ended up being Malwarebytes extension in Chrome. After disabling it for the local URL, the issue was resolved.

Upvotes: 0

Ghost.Idle
Ghost.Idle

Reputation: 79

It does seem rather odd as it has said your model is loaded so im confused as to why you are seeing a loading time on the checkpoint via your web UI. I can only think of a few reasons why this is happening

Low System Spec

Could it be that your system spec is too low? Lowest system I managed to get this running on was GTX 1650 4gb of VRAM and 8GB of ram on windows 10. It does generate images but not video.

File Corruptions

Maybe your model file is corrupted have you tried other files? I have had issues with models taking forever to load in the past. Python would use way too much ram an the system would hang for a few minutes. I managed to fix this by cleaning up memory dump files and temporary files.

Edit Your Command Line Arguments

Head over to your stable diffusion webui folder edit the webui-user.bat file (use a text editor)

change the line

set COMMANDLINE_ARGS=

to

set COMMANDLINE_ARGS=--lowvram --precision full --no-half

See if it makes any difference at all. Good luck, stable diffusion can be a bit of a pain to get running on systems, but your issues seems a little bit unique to me. I can't say I've had it not throw an error on the command line, when it has issues with the browser.

Upvotes: 0

Related Questions