misobarisic / diffusion-ui

Anything 4.5, Anything 3.0, Waifu Diffusion, Stable Diffusion 2.1, H Diffusion, Midjourney, Redshift

Introduction

Languages and Tools

Spotify

Now Playing on Spotify

diffusion-ui's Issues

Yet another error has occurred...

Again, I'm reaching up to you for yet another issue that popped up out of nowhere...

I think I'll just leave this image here and it should tell you enough about the error... at least I hope it will.

It shows up almost towards the end of the booting sequence.

P.S.: I'm sorry for having so many issues... >.>

SyntaxError: invalid syntax

File "", line 338
if vae == "Anime (Orangemix)"
^
SyntaxError: invalid syntax

Maybe this doesn't violate the treaty

Maybe this doesn't violate the treaty, but I hope to keep updating it I especially like the code of this notebook

After a day and night of battling with Google I purchased the pro+ and Tesla V100S 32G.

Even when I'm on the road or using my phone and tablet I can hope to still use the more convenient sd-webui-additional.

so,I don't want Google to overuse the sd-webui-additional restriction for free users this time, thus affecting the continuous updates of the notebook

However, this time Google's behavior is itself a restriction of excessive account use for free users, so the sd-webui-additional paragraph is pulled into the offending code, but the use itself does not have too much impact. Perhaps this is just a warning.
But if there are still a large number of free users using sd-webui-additional, Google may take the ban or more extreme measures.

There are still ways to bypass the warning by changing the name, but it's only temporary.

In my review of some of the literature. pro+, although it may involve code violations, does not affect the next and future use. After all, you paid for it.
On the contrary, the use of sd-webui-additional code usage statistics for free users, thus reducing the free gpu usage is perhaps Google's goal.

So, please don't give up updating plz

You may be executing code that is disallowed, and this may restrict your ability to use Colab in the future. Please note the prohibited actions specified in our FAQ.

TheLastBen/fast-stable-diffusion#2013

https://github.com/TheLastBen/fast-stable-diffusion

Someone has solved this problem

SyntaxError: invalid syntax

Error loading script: loopback.py
Traceback (most recent call last):
File "/content/stable-diffusion-webui/modules/scripts.py", line 256, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
File "/content/stable-diffusion-webui/modules/script_loading.py", line 11, in load_module
module_spec.loader.exec_module(module)
File "", line 846, in exec_module
File "", line 983, in get_code
File "", line 913, in source_to_code
File "", line 228, in _call_with_frames_removed
File "/content/stable-diffusion-webui/scripts/loopback.py", line 57
match denoising_curve:
^
SyntaxError: invalid syntax

After loading everything An error, Does it have an impact?

RunTime Error

Yet again, I'm getting an error, this time however, everything runs as it should but when I am about to generate a batch, this pops up:

I can tell I need to switch something from false to true but I can't figure out what and how exactly... I searched for that argument there but couldn't find it in the notebook... -__-"

Cannot add middleware after an application has started

This share link expires in 72 hours. For free permanent hosting and GPU upgrades (NEW!), check out Spaces: https://huggingface.co/spaces
Traceback (most recent call last):
File "launch.py", line 361, in
start()
File "launch.py", line 356, in start
webui.webui()
File "/content/stable-diffusion-webui/webui.py", line 232, in webui
app.add_middleware(GZipMiddleware, minimum_size=1000)
File "/usr/local/lib/python3.8/dist-packages/starlette/applications.py", line 135, in add_middleware
raise RuntimeError("Cannot add middleware after an application has started")
RuntimeError: Cannot add middleware after an application has started
Killing tunnel 127.0.0.1:7860 <> https://76dc6223-199c-46e3.gradio.live/

fastapi to 0.90 and it works fine.

Can you repair this problem?

Cell to download extensions

Sice we cant use the "Install from URL" tab (when the --share command are active, the function to download from URL get disabled), would be extremely useful to have a cell to download the extensions.

Xformers error fixed pleasee

Error: Your local changes to the following files would be overwritten by checkout: train.py

Hi, I have the following options checked, and I keep getting the error below

-run in gdrive
-xformers
-tag complete
-hypernetworks
-anything 3
-all the lora

Also, can I leave the lora unchecked on subsequent runs? New ones kept getting downloaded with a number suffix to Google Drive.

2023-02-07 08:27:35 (57.0 MB/s) - ‘/content/drive/MyDrive/AI/stable-diffusion-webui/models/Stable-diffusion/anything-v4.0.vae.pt’ saved [822802803/822802803]

/content/drive/MyDrive/AI/stable-diffusion-webui
Python 3.8.10 (default, Nov 14 2022, 12:59:47)
[GCC 9.4.0]
Commit hash: b915325c1eb5f8d8e9e22d156c9e9869e47c8ddf
Cloning Stable Diffusion into repositories/stable-diffusion-stability-ai...
Cloning Taming Transformers into repositories/taming-transformers...
Cloning K-diffusion into repositories/k-diffusion...
Traceback (most recent call last):
File "launch.py", line 360, in
prepare_environment()
File "launch.py", line 302, in prepare_environment
git_clone(k_diffusion_repo, repo_dir('k-diffusion'), "K-diffusion", k_diffusion_commit_hash)
File "launch.py", line 162, in git_clone
run(f'"{git}" -C "{dir}" checkout {commithash}', None, "Couldn't checkout {name}'s hash: {commithash}")
File "launch.py", line 105, in run
raise RuntimeError(message)
RuntimeError: Couldn't checkout {name}'s hash: {commithash}.
Command: "git" -C "repositories/k-diffusion" checkout 5b3af030dd83e0297272d861c19477735d0317ec
Error code: 1
stdout:
stderr: error: Your local changes to the following files would be overwritten by checkout:
train.py
Please commit your changes or stash them before you switch branches.
Aborting

How can i use Ngrok

Hello, i'm kinda new to this topic, and i have some issues with gradio... So i decided to use Ngrok, i followed the instructions, i created an auth token and authenticate it, but, when i start, it says ''auth token invalid''

Idk what i'm doing wrong, could you help me with this by giving me some instructions or smt pls?

Pd: My computer has AMD's, idk it is related or not

Error: train.py

/content/drive/MyDrive/AI/stable-diffusion-webui
Python 3.8.10 (default, Nov 14 2022, 12:59:47)
[GCC 9.4.0]
Commit hash: 44de47784af1fb12cb1cb17b8ea0a983d4ece977
Installing gfpgan
Installing clip
Installing open_clip
Cloning Stable Diffusion into repositories/stable-diffusion-stability-ai...
Cloning Taming Transformers into repositories/taming-transformers...
Cloning K-diffusion into repositories/k-diffusion...
Traceback (most recent call last):
File "launch.py", line 360, in
prepare_environment()
File "launch.py", line 302, in prepare_environment
git_clone(k_diffusion_repo, repo_dir('k-diffusion'), "K-diffusion", k_diffusion_commit_hash)
File "launch.py", line 162, in git_clone
run(f'"{git}" -C "{dir}" checkout {commithash}', None, "Couldn't checkout {name}'s hash: {commithash}")
File "launch.py", line 105, in run
raise RuntimeError(message)
RuntimeError: Couldn't checkout {name}'s hash: {commithash}.
Command: "git" -C "repositories/k-diffusion" checkout 5b3af030dd83e0297272d861c19477735d0317ec
Error code: 1
stdout:
stderr: error: Your local changes to the following files would be overwritten by checkout:
train.py
Please commit your changes or stash them before you switch branches.
Aborting

What can i do for solve this problem?, thanks for your attention

Progress Bar being interrupted

Hello again. I came across this strange issue just now. I'm not sure what could be the cause for it but this time, the progress bar while it's generating images is getting interrupted repeatedly. I tried closing all programs and everything cause I thought it might be an issue with my RAM usage or something that hinders performance... but it didn't work. I haven't changed anything in the settings, still using everything as always... it just suddenly started to freeze while generating images.

For reference, this is the progress bar I'm talking about:

What do you think could be the issue?

No display of the generated images

Days ago I can not see the images when I finish generating them, if you generate a single one if you can see but when you generate multiple images no longer, also the generate button does not respond after all the above, also in the colab you can see this error.

LOGIN

i cant find how to open the ui

im kinda new to this, but how can i open the "gradio link", i ran the unified code but i cant find how to open the actual ai

"NameError: name 'Nitro_Diffusion' is not defined"

Please, can somebody help me? I keep getting this error shortly after I run the diffusion in the collab... I have no idea what am I supposed to do, I tried updating to python 3.10 but that didn't help, I also tried running the first command paragraph that says you are supposed to run it if you get any errors, but that didn't help either... it just suddenly stopped working... if someone had an answer it would be most appreciated! Thank you very much!😖☹️

Here is a link to the Error Message that I'm getting:

"No checkpoints found"

When I tried to launch the diffusion today, this is what it showed after a couple of minutes.

Can you please direct me on how to set up the checkpoint?.. Because unfortunately, I have no clue...

Another RunTime Error...

I've just encountered this error randomly now... I believe it's somehow related to xformers again...

I tried running it without xformers enabled and it worked normally... so yeah, something is wrong with xformers again I'm afraid...

The gradio link is not appearing

When the code on the "Run this" cell finishes loading, the gradio link doesn't appear, just the local link

SyntaxError: invalid syntax

File "", line 282
custom_model("https://huggingface.co/SG161222/Realistic_Vision_V1.4/resolve/main/Realistic_Vision_V1.4.safetensors","Realistic_Vision_V1.4" 1)
^
SyntaxError: invalid syntax

Using a different VAE

Hi, is it possible to use a different VAE?

I'd like to try using orangemix.vae.pt since it's in the "How to use" section of AbyssOrangeMix2 (AOM2). What do I need to edit if it's possible?

Low quality pictures...

I'm truly sorry about posting these issues here left and right... but there is no one other I turn for help...

So as of late, that means like two days ago, since the newest update to the collab, I tried to generate images again with the same settings as usual, however for some odd reasons that I do not understand, it's been giving me much lower quality images... to be specific, they are really low saturated for some reason... I will attach two pictures for close comparison, one will be before and the other after... And yes, I tried to tinker with the settings, even used other models and parameters but nothing worked... I use Anything3 model, if that helps but it did with the others when I tried them out as well...

Here are the images: The upper one is BEFORE (good one) and the bottom one is AFTER (bad one)

I'm not sure if it's just me but to me it seem like the bottom one has much less gloss and saturation then the first one... I tried all the settings but nothing seems to fixed it, I even tried different sampling methods but that didn't work either... I know I'm probably doing something wrong but I'm clueless as to what...

The problem sometimes does not show photos

Sorry if the wrong position
i make pictures with lora
it works great your model is great
However, I don't know why your model is so good that it doesn't show the image even though in colab finished creating the image, but in the web, there is no image, hope you can help me
https://colab.research.google.com/drive/1iwLtfEeoUTTVFZ08iVkvJ5jBhwKcspty?usp=sharing
I just tweaked it to make it easier for me but the picture doesn't show up

WebUI not working anymore

Hello, I made a copy of your notebook a few time ago to add controlNet and was working well, but today when i tried to launch, i get "504 bad get away" http err. So I tried to lauch your notebook to see if there is a similar issue and actually yes. Do you have any idea what's happening ? I'm a React/Node dev so my understanding of SD python code is very limited ^^

Using Google Drive for output only and saving web ui settings

Hi, it's me again. I tried selecting Anything v3 and Abyss Orange Mix 2 with the run in gdrive option checked, and I noticed that my free storage filled up quickly.

Since the model files are quite large, is there a way to save only the output to gdrive?

Also, is it possible to save the settings in the web ui so that they don't reset upon exiting?

Localtunnel option

WOuld be possible to add a option to use the LocalTunnel too? Since the Gradio are having a lot of 504 problems this past days.
Thanks so much for your work!

i cant choose the model

when im in the ui and i try to change the checkpoint, it does an error, how can i solve this?