So the crash actually happened right after I hit the 'Blast' button. I'm not sure what the error was because I didn't see any signs. But what I do know is, when I executed the blast, Python stopped responding and eventually crashed. By the way, I'm not using a GPU.

what is the allowed image size?
Like i have a image file of 1080x37890 px
Will this work?

Hi ,
I want to remove only some text parts instead of all , I already have co-ordinates for the OCR boxes I would like to remove from images, can you please tell what changes do we make to apply it

PS E:\BubbleBlaster> python bubbleblaster.py
Traceback (most recent call last):
File "E:\BubbleBlaster\bubbleblaster.py", line 281, in
app = App()
File "E:\BubbleBlaster\bubbleblaster.py", line 31, in init
self.checkUpdate()
File "E:\BubbleBlaster\bubbleblaster.py", line 274, in checkUpdate
if latest_tag > self.tag:
TypeError: '>' not supported between instances of 'NoneType' and 'str'
PS E:\BubbleBlaster>

The console show this message

ERROR: Ignored the following versions that require a different python version: 1.21.2 Requires-Python >=3.7,<3.11; 1.21.3 Requires-Python >=3.7,<3.11; 1.21.4 Requires-Python >=3.7,<3.11; 1.21.5 Requires-Python >=3.7,<3.11; 1.21.6 Requires-Python >=3.7,<3.11
ERROR: Could not find a version that satisfies the requirement numpy==1.21.2 (from versions: 1.3.0, 1.4.1, 1.5.0, 1.5.1, 1.6.0, 1.6.1, 1.6.2, 1.7.0, 1.7.1, 1.7.2, 1.8.0, 1.8.1, 1.8.2, 1.9.0, 1.9.1, 1.9.2, 1.9.3, 1.10.0.post2, 1.10.1, 1.10.2, 1.10.4, 1.11.0, 1.11.1, 1.11.2, 1.11.3, 1.12.0, 1.12.1, 1.13.0, 1.13.1, 1.13.3, 1.14.0, 1.14.1, 1.14.2, 1.14.3, 1.14.4, 1.14.5, 1.14.6, 1.15.0, 1.15.1, 1.15.2, 1.15.3, 1.15.4, 1.16.0, 1.16.1, 1.16.2, 1.16.3, 1.16.4, 1.16.5, 1.16.6, 1.17.0, 1.17.1, 1.17.2, 1.17.3, 1.17.4, 1.17.5, 1.18.0, 1.18.1, 1.18.2, 1.18.3, 1.18.4, 1.18.5, 1.19.0, 1.19.1, 1.19.2, 1.19.3, 1.19.4, 1.19.5, 1.20.0, 1.20.1, 1.20.2, 1.20.3, 1.21.0, 1.21.1, 1.22.0, 1.22.1, 1.22.2, 1.22.3, 1.22.4, 1.23.0rc1, 1.23.0rc2, 1.23.0rc3, 1.23.0, 1.23.1, 1.23.2, 1.23.3, 1.23.4, 1.23.5, 1.24.0rc1, 1.24.0rc2, 1.24.0, 1.24.1, 1.24.2, 1.24.3, 1.24.4, 1.25.0rc1, 1.25.0)
ERROR: No matching distribution found for numpy==1.21.2
[end of output]

note: This error originates from a subprocess, and is likely not a problem with pip.
error: subprocess-exited-with-error

× pip subprocess to install build dependencies did not run successfully.
│ exit code: 1
╰─> See above for output.

Maybe i´m not doing something right, but i downloaded the latest release and when i try to open it just pops up a CMD window for half a second and then closes. Just that :,^

I tried run BubbleBlaster.bat but a black screen appeared and closed immediately. I also tried the exe file, but I got the error below and could not install it.

Downloading detection model, please wait. This may take several minutes depending upon your network connection.
Progress: |██████████████████████████████████████████████████| 100.0% CompleteDownloading recognition model, please wait. This may take several minutes depending upon your network connection.
Progress: |██████████████████████████████████████████████████| 100.0% CompleteException in Tkinter callback
Traceback (most recent call last):
File "C:\Users\dansa\AppData\Local\Programs\Python\Python310\lib\tkinter_init_.py", line 1921, in call
return self.func(*args)
File "C:\Users\dansa\AppData\Local\Programs\Python\Python310\lib\site-packages\easyocr\easyocr.py", line 456, in readtext
result = self.recognize(img_cv_grey, horizontal_list, free_list,
File "C:\Users\dansa\AppData\Local\Programs\Python\Python310\lib\site-packages\easyocr\easyocr.py", line 379, in recognize
image_list, max_width = get_image_list(h_list, f_list, img_cv_grey, model_height = imgH)
File "C:\Users\dansa\AppData\Local\Programs\Python\Python310\lib\site-packages\easyocr\utils.py", line 540, in get_image_list
maximum_y,maximum_x = img.shape
AttributeError: 'NoneType' object has no attribute 'shape'

such as ahhh.......

If you can please make it become window tool, so can easy import multi images and control files more easy, thank you so much for tool!

it says ERROR: No matching distribution found for numpy==1.21.2
[end of output]

I am in a dilemma that wether it would work on Mac or not.
I just recently bought new macbook and don't want to mess with it.

I installed your program, but does not initialize
How I can use ?

i have rtx 40x series card, i don't have this problem when i use manga-image-translator from zyddnys with gpu that requires cuda, so i installed cuda like in tutorial and it douesn't fixed

Something wrong can you help me?
Neither CUDA nor MPS are available - defaulting to CPU. Note: This module is much faster with a GPU.
Exception in Tkinter callback
Traceback (most recent call last):
File "C:\Users\NIK\AppData\Local\Programs\Python\Python311\Lib\tkinter_init_.py", line 1948, in call
return self.func(args)
^^^^^^^^^^^^^^^^
File "C:\Users\NIK\AppData\Local\Programs\Python\Python311\Lib\site-packages\customtkinter\windows\widgets\ctk_button.py", line 553, in _clicked
self._command()
File "C:\Users\NIK\Downloads\BubbleBlaster\bubbleblaster.py", line 155, in blast
result = reader.readtext(image)
^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\NIK\AppData\Local\Programs\Python\Python311\Lib\site-packages\easyocr\easyocr.py", line 464, in readtext
result = self.recognize(img_cv_grey, horizontal_list, free_list,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\NIK\AppData\Local\Programs\Python\Python311\Lib\site-packages\easyocr\easyocr.py", line 383, in recognize
image_list, max_width = get_image_list(h_list, f_list, img_cv_grey, model_height = imgH)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\NIK\AppData\Local\Programs\Python\Python311\Lib\site-packages\easyocr\utils.py", line 613, in get_image_list
crop_img,ratio = compute_ratio_and_resize(crop_img,width,height,model_height)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\NIK\AppData\Local\Programs\Python\Python311\Lib\site-packages\easyocr\utils.py", line 576, in compute_ratio_and_resize
img = cv2.resize(img,(int(model_heightratio),model_height),interpolation=Image.ANTIALIAS)
^^^^^^^^^^^^^^^
AttributeError: module 'PIL.Image' has no attribute 'ANTIALIAS'

For work I need to remove from the pictures the text that is written in Russian. Could you please add it? I need it very much! Thank you in advance!

I installed all the dependencies but when I try to open the bat file it starts for a second and disappears

Hey i am a huge fan of your work and i wanted to find the best way to contact you to talk. Do you have discord?

I'm having this issue:

  ERROR: No matching distribution found for numpy==1.21.2
  [end of output]

note: This error originates from a subprocess, and is likely not a problem with pip.
error: subprocess-exited-with-error

I'm using python3.11.2 and numpy = 1.24.2

Traceback (most recent call last):
File "D:\PythonProjects\MangoEditer\BubbleBlaster\bubbleblaster.py", line 265, in
app = App()
File "D:\PythonProjects\MangoEditer\BubbleBlaster\bubbleblaster.py", line 39, in init
self.inputFrame = ctk.CTkFrame(self, width=500, fg_color="transparent")
File "D:\PythonProjects\MangoEditer\venv\lib\site-packages\customtkinter\widgets\ctk_frame.py", line 52, in init
self.draw()
File "D:\PythonProjects\MangoEditer\venv\lib\site-packages\customtkinter\widgets\ctk_frame.py", line 92, in draw
self.canvas.itemconfig("inner_parts",
File "D:\PythonProjects\MangoEditer\venv\lib\site-packages\customtkinter\widgets\ctk_canvas.py", line 94, in itemconfig
super().itemconfigure(configure_id, *args, **kwargs_except_outline)
File "C:\Program Files\Python38\lib\tkinter_init_.py", line 2898, in itemconfigure
return self.configure(('itemconfigure', tagOrId), cnf, kw)
File "C:\Program Files\Python38\lib\tkinter_init.py", line 1627, in _configure
self.tk.call(_flatten((self._w, cmd)) + self._options(cnf))
_tkinter.TclError: unknown color name "transparent"

The error is :

Traceback (most recent call last): File "C:\Users\33682\Desktop\AI\bubbleblaster.py", line 128, in <module> OCR() File "C:\Users\33682\Desktop\AI\bubbleblaster.py", line 44, in OCR result = reader.readtext(IMAGE) File "C:\Users\33682\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\easyocr\easyocr.py", line 442, in readtext img, img_cv_grey = reformat_input(image) File "C:\Users\33682\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\easyocr\utils.py", line 699, in reformat_input img = loadImage(image) # can accept URL File "C:\Users\33682\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\easyocr\imgproc.py", line 12, in loadImage img = io.imread(img_file) # RGB order File "C:\Users\33682\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\skimage\io\_io.py", line 53, in imread img = call_plugin('imread', fname, plugin=plugin, **plugin_args) File "C:\Users\33682\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\skimage\io\manage_plugins.py", line 207, in call_plugin return func(*args, **kwargs) File "C:\Users\33682\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\skimage\io\_plugins\imageio_plugin.py", line 15, in imread return np.asarray(imageio_imread(*args, **kwargs)) File "C:\Users\33682\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\imageio\v2.py", line 226, in imread with imopen(uri, "ri", **imopen_args) as file: File "C:\Users\33682\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\imageio\core\imopen.py", line 298, in imopen raise err_type(err_msg) ValueError: Could not find a backend to open test.jpg`` with iomode ri.`

Is there anything I can do to make this work ?

I'd really like to be able to use this in the terminal instead of using a GUI. How difficult would that be?

If you can give instructions on how you'd implement it, I can try to do that work myself (and do a PR once done)

Thanks!

torchvision\io\image.py:13: UserWarning: Failed to load image Python extension: ''If you don't plan on using image functionality from torchvision.io, you can ignore this warning. Otherwise, there might be something wrong with your environment. Did you have libjpeg or libpng installed before building torchvision from source?
torch_jit_internal.py:857: UserWarning: Unable to retrieve source for @torch.jit._overload function: <function _DenseLayer.forward at 0x000001D0F4762E80>.
warnings.warn(
torch_jit_internal.py:857: UserWarning: Unable to retrieve source for @torch.jit._overload function: <function _DenseLayer.forward at 0x000001D0F4763EC0>.
warnings.warn(
Neither CUDA nor MPS are available - defaulting to CPU. Note: This module is much faster with a GPU.
Downloading recognition model, please wait. This may take several minutes depending upon your network connection.
Progress: |██████████████████████████████████████████████████| 100.1% CompleteNeither CUDA nor MPS are available - defaulting to CPU. Note: This module is much faster with a GPU.

It would be helpful to me if the Italian and spanish languages could be added.
On the other hand, an improvement could be to allow to select also the language to which you want to translate.
A question, is there any tool that I can download to generate an executable from the script? Or is it necessary to have Python installed? I ask because I do not use Python but this tool would be very useful!
Best regards.

Error

it gives an error when converting this jpg

json array for
removed text.
start x y, end x y for the bubble xy

eg.
[
{
"text": "..."
"start_x": 200,
"start_y": 200,
"end_x": 1000,
"end_y": 1000
},
....
]