yfszzx / stable-diffusion-webui-inspiration Goto Github PK

I learned a lot from your code I want to say thank you ♥ and I made this https://github.com/camenduru/stable-diffusion-webui-artists-to-study 🎉

When I run the create inspiration images script with the artists.txt file, I get this:

artists
Error completing request
Arguments: ('', '', 'None', 'None', 28, 0, False, False, 1, 1, 12, -1.0, -1.0, 0, 0, 0, False, 768, 512, False, 0.7, 0, 0, 12, 0.9, 5, '0.0001', False, 'None', '', 0.1, False, 'Not set', 'Not set', 'Not set', 'Not set', 'No focus', 'None', False, '\n            <h3><strong>Combinations</strong></h3>\n            Choose a number of terms from a list, in this case we choose two artists\n            <code>{2$$artist1|artist2|artist3}</code>\n            If $$ is not provided, then 1$$ is assumed.\n            <br>\n            A range can be provided:\n            <code>{1-3$$artist1|artist2|artist3}</code>\n            In this case, a random number of artists between 1 and 3 is chosen.\n            <br/><br/>\n\n            <h3><strong>Wildcards</strong></h3>\n            <p>Available wildcards</p>\n            <ul>\n        <li>__body__</li><li>__eye_color__</li></ul>\n            <br/>\n            <code>WILDCARD_DIR: scripts/wildcards</code><br/>\n            <small>You can add more wildcards by creating a text file with one term per line and name is mywildcards.txt. Place it in scripts/wildcards. <code>__mywildcards__</code> will then become available.</small>\n        ', '', False, False, False, False, False, False, '<p style="margin-bottom:0.75em">Keyframe Format: <br>Seed | Prompt or just Prompt</p>', '', 25, True, 5.0, False, None, '', False, 4.0, '', 10.0, False, False, True, 30.0, True, False, False, 0, 10.0, True, 30.0, True, '', False, [], [], [], [], [], [], [], [], [], 1, '', 0, '', True, False, False, 4.0, 1.0, 'a painting in', 'style', 'picture frame, portrait photo', [<tempfile._TemporaryFileWrapper object at 0x000002B57E952560>]) {}
Traceback (most recent call last):
  File "D:\dev\stable-diffusion\stable-diffusion-webui\modules\ui.py", line 221, in f
    res = list(func(*args, **kwargs))
  File "D:\dev\stable-diffusion\stable-diffusion-webui\webui.py", line 63, in f
    res = func(*args, **kwargs)
  File "D:\dev\stable-diffusion\stable-diffusion-webui\modules\txt2img.py", line 45, in txt2img
    processed = modules.scripts.scripts_txt2img.run(p, *args)
  File "D:\dev\stable-diffusion\stable-diffusion-webui\modules\scripts.py", line 286, in run
    processed = script.run(p, *script_args)
  File "D:\dev\stable-diffusion\stable-diffusion-webui\extensions\stable-diffusion-webui-inspiration\scripts\inspiration.py", line 45, in run
    line = f.readline()
  File "C:\Users\user one\AppData\Local\Programs\Python\Python310\lib\encodings\cp1252.py", line 23, in decode
    return codecs.charmap_decode(input,self.errors,decoding_table)[0]
UnicodeDecodeError: 'charmap' codec can't decode byte 0x81 in position 5514: character maps to <undefined>

I git pulled the extension from this repository and checked the Inspiration tab was present in the web-ui, then I went to the txt2img tab > scripts > "create inspiration images" and hit the Generate button, but this is what I got:

Error completing request
Arguments: ('', '', 'None', 'None', 20, 0, False, False, 1, 1, 7, -1.0, -1.0, 0, 0, 0, False, 512, 512, False, 0.7, 0, 0, 10, 0.9, 5, '0.0001', False, 'None', '', 0.1, False, False, False, False, None, '', '', '', False, 4.0, '', 10.0, False, False, True, 30.0, True, False, False, False, 1, '', 0, '', True, True, False, 1.0, 2.0, 'a painting in', 'style', 'picture frame, portrait photo', None) {}
Traceback (most recent call last):
  File "C:\Users\username\Downloads\generative-nn-models\stable-diffusion-webui\modules\ui.py", line 221, in f
    res = list(func(*args, **kwargs))
  File "C:\Users\username\Downloads\generative-nn-models\stable-diffusion-webui\webui.py", line 63, in f
    res = func(*args, **kwargs)
  File "C:\Users\username\Downloads\generative-nn-models\stable-diffusion-webui\modules\txt2img.py", line 45, in txt2img
    processed = modules.scripts.scripts_txt2img.run(p, *args)
  File "C:\Users\username\Downloads\generative-nn-models\stable-diffusion-webui\modules\scripts.py", line 286, in run
    processed = script.run(p, *script_args)
  File "C:\Users\username\Downloads\generative-nn-models\stable-diffusion-webui\extensions\stable-diffusion-webui-inspiration\scripts\inspiration.py", line 39, in run
    for file in files:
TypeError: 'NoneType' object is not iterable

What am I doing wrong?

invalid link: https://github.com/pharmapsychotic/clip-interrogator/tree/main/data

Traceback (most recent call last):
File "C:\stable-diffusion-webui\venv\lib\site-packages\gradio\routes.py", line 414, in run_predict
output = await app.get_blocks().process_api(
File "C:\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 1321, in process_api
inputs = self.preprocess_data(fn_index, inputs, state)
File "C:\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 1159, in preprocess_data
self.validate_inputs(fn_index, inputs)
File "C:\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 1146, in validate_inputs
raise ValueError(
ValueError: An event handler (select_click) didn't receive enough input values (needed: 2, got: 1).
Check if the event handler calls a Javascript function, and make sure its return value is correct.
Wanted inputs:
[textbox, state]
Received inputs:
["NaN"]

use dataset
(https://huggingface.co/datasets/yfszzx/inspiration/blob/main/inspiration.zip)

Microsoft Edge
版本 113.0.1774.57 (正式版本) (64 位)

Hey hey,
I've installed items here:

I have a tab, but not acknowledging assets

Any ideas?

Thanks in advance!

I might just be goofing somewhere but anytime I get to a flavor with a " / " in it my image generation crashes. Here is the error.

Error completing request[55:51,  5.15it/s]
Arguments: ('', '', 'None', 'None', 20, 0, False, False, 1, 1, 7, -1.0, -1.0, 0, 0, 0, False, 512, 512, False, 0.7, 0, 0, 4, 0.9, 5, '0.0001', False, 'None', '', 0.1, False, False, False, None, '', 1, '', 0, '', True, False, False, 1.0, 1.0, 'a painting in', 'style', 'picture frame, portrait photo', [<tempfile._TemporaryFileWrapper object at 0x0000016D0B4B9180>]) {}
Traceback (most recent call last):
  File "C:\Users\Name\stable-diffusion-webui\modules\ui.py", line 221, in f
    res = list(func(*args, **kwargs))
  File "C:\Users\Name\stable-diffusion-webui\webui.py", line 63, in f
    res = func(*args, **kwargs)
  File "C:\Users\Name\stable-diffusion-webui\modules\txt2img.py", line 45, in txt2img
    processed = modules.scripts.scripts_txt2img.run(p, *args)
  File "C:\Users\Name\stable-diffusion-webui\modules\scripts.py", line 286, in run
    processed = script.run(p, *script_args)
  File "C:\Users\Name\stable-diffusion-webui\extensions\stable-diffusion-webui-inspiration\scripts\inspiration.py", line 52, in run
    os.mkdir(artist_path)
FileNotFoundError: [WinError 3] The system cannot find the path specified: 'C:\\Users\\Name\\stable-diffusion-webui\\extensions\\stable-diffusion-webui-inspiration\\inspiration\\flavors\\f/1.4'

I am using the new v2 list as well if that matters.

I clicked a left image of inspiration tab page in Stable Diffusion WebUI, right of the page show Error button.
And cmd console said like below,

Traceback (most recent call last):
File "F:\AI\WebUI\stable-diffusion-webui\venv\lib\site-packages\gradio\routes.py", line 394, in run_predict
output = await app.get_blocks().process_api(
File "F:\AI\WebUI\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 1075, in process_api
result = await self.call_function(
File "F:\AI\WebUI\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 884, in call_function
prediction = await anyio.to_thread.run_sync(
File "F:\AI\WebUI\stable-diffusion-webui\venv\lib\site-packages\anyio\to_thread.py", line 31, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "F:\AI\WebUI\stable-diffusion-webui\venv\lib\site-packages\anyio_backends_asyncio.py", line 937, in run_sync_in_worker_thread
return await future
File "F:\AI\WebUI\stable-diffusion-webui\venv\lib\site-packages\anyio_backends_asyncio.py", line 867, in run
result = context.run(func, *args)
File "F:\AI\WebUI\stable-diffusion-webui\extensions\stable-diffusion-webui-inspiration\scripts\inspiration.py", line 158, in select_click
name = name_list[int(index)]
ValueError: invalid literal for int() with base 10: 'NaN'

How can I fix it ?

Few suggestions of features to add:

*Top 50 Artists

*More artists in the style of "XXX"
XXX is a artist we put in favorites

You can add the display of all pictures with a scroll instead of 24 as now.

First of all, thanks for this neat extension. I have been looking for a visual way of remembering some of the artists and styles I like to use.
I have about 70 artists listed in my styles sheet with descriptions to try to remember, but as a visual person, this extension is a vast improvement.

I think this type of extension serves two purposes.

1. To discover or stumble upon new artists or ideas. Hence the name inspiration.

2. To store or organize artists or styles that you want to commonly use for a quick call-back.

There are some features I would love to see added to help with these goals.

Discovery

Artist Tags
On the stumbling-upon side of things, I would love to see Artist Categories or Tags.
Instead of pulling from 5000+ artists 24 at a time. I would like to select comic-book, or renounce, and have it filter the list.

Adjustable pool size and views
I would also love to be able to set a higher number than 24 in the pool.

Varying pool views
Also maybe a list option with small thumbnails. Especially with the flavors or mediums. I would like to see all of those at once and click on one for details on what it could look like. Only seeing 24 makes me feel like it's withholding something.

Pool sorting
I would also very much like to be able to sort the pool alphabetically. When I am searching for an artist by name, having it display a group of artists in random order can be frustrating. A button to change from random to alphabetically would be nice.

Organizing

Custom Checkbox Groups
I would like the option to create my own checkbox groups. I would love to be able to sort and organize different styles or artists in ways to make it easier to visualize.

Custom Source Items
Similarly, I would like to be able to make custom Source dropdown items. I could filter my top favorites, or maybe custom categories.

Pool sorting
As mentioned above the ability to sort the pool alphabetically is essential for custom-organized collections.

Settings

There are also some settings would love to see, such as:
Choosing which checkbox groups are checked by default.
Choosing what prefix to put in front of an artist's name when sending to txt2img such as "art style as"

Again, thanks for the awesome extension. I am happy to provide better explanations or feedback.

inspiration.py

p.n_iterint = int(batch_count)
->
p.n_iter = int(batch_count)

Recreate by loading a file with quotation marks. Test "Bug" case. The destination path has double slashes for directory marks, which obviously fails on windows. I'm not sure about Linux.

great extension !

those additional images on the lower right side, after you click an artist, doesnt work anymore since the last update of stable diffusion.

Would be nice if this could get fixed.

Best...

After following the instructions; uploading a list of artist, let it run through and generate the images, I returned to the Inspiration tab, reloaded the webUI, but it still shows the default start message:
"To activate inspiration function, you need get "inspiration" images first"...

I know it generated a ton of images and placed them in a gradio folder in the /var directory.
Ex.
/private/var/folders/6v/y4fwz7292l1gghszgc9j6x240000gn/T/gradio/

I'm sure I'm missing some step, but not sure what it is?

Edit: I should add that I installed it via the webui extensions tab.

Version:
[0f3f699 (Fri Dec 9 03:50:47 2022)]

Can we change this line https://github.com/yfszzx/stable-diffusion-webui-inspiration/blob/main/scripts/inspiration.py#L47 to

            while len(line) > 0 and shared.state.interrupted == False:

so if the generation is interrupted we do not continue reading from the file?

And this line https://github.com/yfszzx/stable-diffusion-webui-inspiration/blob/main/scripts/inspiration.py#L53 to

                if len(os.listdir(artist_path)) > (batch_count-1)*batch_size:

in such a way that if we generate a batch_size lot it will not go over the batch_size * batch_count. So if you want to make 2 batches of 5 you can. or 5 batches of 2. and finally 10 batches of 1 and you will be sure that the ending folders will have 10 files each at least.

I would love this line https://github.com/yfszzx/stable-diffusion-webui-inspiration/blob/main/scripts/inspiration.py#L58 to be nested inside a if shared.state.interrupted == False: so if I cancel a batch the partially generated images are not written and I do not have to go clean up the folder the execution was stopped at.

I am loving the generation script, have not tried the browser yet.

Hello, I tried to use the extension but when launching the webui it spits out this error:

I'm not the only one getting this, here's an issue on the webui repo: AUTOMATIC1111/stable-diffusion-webui#3552

Windows 11. Getting permission error when clicking on "Get inspiration".

PermissionError: [Errno 13] Permission denied: 'D:\AI-Software\stable-diffusion-webui\extensions\stable-diffusion-webui-inspiration\inspiration\inspiration\artists\Torii Kiyonaga'
Traceback (most recent call last):
File "D:\AI-Software\stable-diffusion-webui\venv\lib\site-packages\gradio\routes.py", line 284, in run_predict
output = await app.blocks.process_api(
File "D:\AI-Software\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 983, in process_api
data = self.postprocess_data(fn_index, result["prediction"], state)
File "D:\AI-Software\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 930, in postprocess_data
prediction_value = block.postprocess(prediction_value)
File "D:\AI-Software\stable-diffusion-webui\venv\lib\site-packages\gradio\components.py", line 3313, in postprocess
file = processing_utils.create_tmp_copy_of_file(
File "D:\AI-Software\stable-diffusion-webui\venv\lib\site-packages\gradio\processing_utils.py", line 341, in create_tmp_copy_of_file
shutil.copy2(file_path, file_obj.name)
File "C:\Users\Usuario\AppData\Local\Programs\Python\Python39\lib\shutil.py", line 444, in copy2
copyfile(src, dst, follow_symlinks=follow_symlinks)
File "C:\Users\Usuario\AppData\Local\Programs\Python\Python39\lib\shutil.py", line 264, in copyfile
with open(src, 'rb') as fsrc:
PermissionError: [Errno 13] Permission denied: 'D:\AI-Software\stable-diffusion-webui\extensions\stable-diffusion-webui-inspiration\inspiration\inspiration\artists\Ásgrímur Jónsson'

Installed like proposed:

Content of the file "artist.txt":

Loading script:

Result:

TypeError: Script.run() missing 2 required positional arguments: 'prompt_placeholder' and 'files'
Time taken: 0.0 sec.

readme.md with:

• Run the "Create inspiration images" script inside the "txt2img" page to create images.

Does not tell how ... using the "Generate" button?

Look here for more install details

does not really tell me more about the installation.
I do know now, something is missing. But what exactly and where?
'prompt_placeholder' and 'files' are defined in the script placeholders. So why this error?

When extracting inspiration.zip on windows 10 using 7-Zip I get this error:

Cannot set file attribute : Wrong parameter. : C:\Users\username\AppData\Local\Temp\7zE8E2DD456\artists\Edward P. Beard Jr
Cannot set file attribute : Wrong parameter. : C:\Users\username\AppData\Local\Temp\7zE8E2DD456\artists\George Barret, Jr
Cannot set file attribute : Wrong parameter. : C:\Users\username\AppData\Local\Temp\7zE8E2DD456\artists\George Barret, Sr
Cannot set file attribute : Wrong parameter. : C:\Users\username\AppData\Local\Temp\7zE8E2DD456\artists\Henriett Seth F
Cannot set file attribute : Wrong parameter. : C:\Users\username\AppData\Local\Temp\7zE8E2DD456\artists\Henry Ives Cobb, Jr
Cannot set file attribute : Wrong parameter. : C:\Users\username\AppData\Local\Temp\7zE8E2DD456\artists\John Frederick Herring, Jr
Cannot set file attribute : Wrong parameter. : C:\Users\username\AppData\Local\Temp\7zE8E2DD456\artists\John Frederick Herring, Sr

When clicking on any image the images displayed are not the correct ones, they are offset by one square showing the previous artist.

I love using this extension to showcase various models and styles, but I find it annoying that every check box is checked every time I load up SD.

Because it tries to load and sort on every check box change, not only do I have to uncheck a dozen check boxes, but I also have to wait and let it load each combination of groups as I uncheck them.

• Could you ad an option to have every group unchecked by default.

Thanks for your hard work.

HI,
when I run the script and follow the instructions, everything works correctly, the snapshots are generated based on the text, but they are not saved anywhere, no folders are created. Do you know where the problem is.

I want to create my own inspiration database, and I also want to ask why the data from the PNG images that I insert into the folder manually are not displayed (see screenshot), and when I use txt2img or img2img, only a comma (,) is sent to the prompt.

Kind regards
Martin

Allow writing artist/style in a text box on the go. Text box works but why can't it also be a text field instead?

I successfully installed inspiration extension and loaded artists images on inspiration tab in webui.
But I clicked an image and then webui say red colored error.
I use inspiration in vladmandic/automatic webui.

cmd console says :

File "F:\AI\Vlad1111\automatic\venv\lib\site-packages\gradio\routes.py", line 408, in run_predict
output = await app.get_blocks().process_api(
File "F:\AI\Vlad1111\automatic\venv\lib\site-packages\gradio\blocks.py", line 1313, in process_api
inputs = self.preprocess_data(fn_index, inputs, state)
File "F:\AI\Vlad1111\automatic\venv\lib\site-packages\gradio\blocks.py", line 1151, in preprocess_data
self.validate_inputs(fn_index, inputs)
File "F:\AI\Vlad1111\automatic\venv\lib\site-packages\gradio\blocks.py", line 1138, in validate_inputs
raise ValueError(
ValueError: An event handler (select_click) didn't receive enough input values (needed: 2, got: 1).
Check if the event handler calls a Javascript function, and make sure its return value is correct.
Wanted inputs:
[textbox, state]
Received inputs:
["NaN"]

Of cause, I saw No #34 issue.
I fix the code that [stable-diffusion-webui-inspiration]/javascript/inspiration.js
like this
From :
var imgs = gallery.querySelectorAll("img.h-full")
To This :
var imgs = gallery.querySelectorAll("img")

But the upper error massages occurs on cmd.
What is my problem ?
What should I do ?

( my runtime environment )
Python 3.10.10 on Windows
Version: a2485cf7 Fri May 12 21:12:24 2023 -0400
Setting environment tuning
nVidia CUDA toolkit detected
Torch 2.0.0+cu118
Torch backend: nVidia CUDA 11.8 cuDNN 8700

all works well starts to populate, until this issue occurs when it reaches the same name each time

Error completing request[3:37:46, 5.28it/s] Arguments: ('', '', 'None', 'None', 20, 0, False, False, 1, 1, 7, -1.0, -1.0, 0, 0, 0, False, 512, 512, False, 0.7, 0, 0, 7, 0.9, 5, '0.0001', False, 'None', '', 0.1, False, 1, 0, 0.25, False, False, False, None, '', False, 4.0, '', 10.0, False, False, True, 30.0, True, False, False, 0, 0.0, 1, '', 0, '', True, False, False, '<div id="dynamic-prompting">\n <h3><strong>Combinations</strong></h3>\n\n Choose a number of terms from a list, in this case we choose two artists: \n <code class="codeblock">{{2$artist1|artist2|artist3}}</code>\n\n If $ is not provided, then 1$ is assumed.\n\n A range can be provided:\n <code class="codeblock">{{1-3$artist1|artist2|artist3}}</code>\n\n In this case, a random number of artists between 1 and 3 is chosen.\n\n <br/><br/>\n\n <h3><strong>Wildcards</strong></h3>\n \n\n <br/>\n If the groups wont drop down click <strong onclick="check_collapsibles()" style="cursor: pointer">here</strong> to fix the issue.\n\n <br/><br/>\n\n <code class="codeblock">WILDCARD_DIR: E:\\Artificial-Inteligence\\Ai-Image-Gen\\Automatic-1111-GUI\\stable-diffusion-webui\\extensions\\sd-dynamic-prompts\\wildcards</code><br/>\n <small onload="check_collapsibles()">You can add more wildcards by creating a text file with one term per line and name is mywildcards.txt. Place it in E:\\Artificial-Inteligence\\Ai-Image-Gen\\Automatic-1111-GUI\\stable-diffusion-webui\\extensions\\sd-dynamic-prompts\\wildcards. <code class="codeblock">__&#60;folder&#62;/mywildcards__</code> will then become available.</small>\n</div>\n\n', False, 1, False, False, 4.0, 1.0, 'a painting in', 'style', 'picture frame, portrait photo', [<tempfile._TemporaryFileWrapper object at 0x000002338C6FE800>]) {} Traceback (most recent call last): File "E:\Artificial-Inteligence\Ai-Image-Gen\Automatic-1111-GUI\stable-diffusion-webui\modules\ui.py", line 185, in f res = list(func(*args, **kwargs)) File "E:\Artificial-Inteligence\Ai-Image-Gen\Automatic-1111-GUI\stable-diffusion-webui\webui.py", line 55, in f res = func(*args, **kwargs) File "E:\Artificial-Inteligence\Ai-Image-Gen\Automatic-1111-GUI\stable-diffusion-webui\modules\txt2img.py", line 45, in txt2img processed = modules.scripts.scripts_txt2img.run(p, *args) File "E:\Artificial-Inteligence\Ai-Image-Gen\Automatic-1111-GUI\stable-diffusion-webui\modules\scripts.py", line 282, in run processed = script.run(p, *script_args) File "E:\Artificial-Inteligence\Ai-Image-Gen\Automatic-1111-GUI\stable-diffusion-webui\extensions\stable-diffusion-webui-inspiration\scripts\inspiration.py", line 52, in run os.mkdir(artist_path) OSError: [WinError 123] The filename, directory name, or volume label syntax is incorrect: 'E:\\Artificial-Inteligence\\Ai-Image-Gen\\Automatic-1111-GUI\\stable-diffusion-webui\\extensions\\stable-diffusion-webui-inspiration\\inspiration\\artists\\Ettore "Ted" DeGrazia

I downloaded the inspiration zip and found a lot of the artists I like to use are not included. I thought I would share the missing ones.

Adam Hughes
Albert Lynch
Arnold Armitage
Arthur Sarnoff
Charles Binger
Daniela Uhlig
Dave Stevens
Dean Yeagle
Enoch Bolles
Hajime Sorayama
J. Scott Campbell
Joe Chiodo
Jovana Rikalo
Mel Ramos
Milo Manara
Rossdraws
Vaughan Alden Bass

Also, I noticed that a bunch of the folders have commas on the file name.

And finally, I noticed there are two Alphonse Mucha the second one being spelled "Alfonse Mucha" with an F

When trying to make inspiration images if the .txt file has "<" it throws an error. It probably errors ">" as well. And maybe even ":"

OSError: [WinError 123] The filename, directory name, or volume label syntax is incorrect:

Would be great if I could make inspiration images for my lora since the built in preview feature only supports a single picture. I really like the randomization and selectability of inspiration.