MCPcopy Index your code
hub / github.com/Aeonss/BubbleBlaster

github.com/Aeonss/BubbleBlaster @2.0.2

Chat with this repo
repository ↗ · DeepWiki ↗ · release 2.0.2 ↗ · + Follow
17 symbols 47 edges 3 files 0 documented · 0% updated 22mo ago2.0.2 · 2024-08-17★ 1383 open issues
What it actually does AI analysis from the code graph — generated when you open this
loading…
README

BubbleBlaster

Bubble Blaster is a python script that remove text from speech bubbles in mangas/manhwas with OCR.

🔨   Installation

Install python (Make sure your python version is NOT more than 3.11):

https://www.python.org/downloads/release/python-3119/

Download the latest release and unzip it.

https://github.com/Aeonss/BubbleBlaster/releases/latest/

If you have a compatible GPU, install CUDA for faster OCRs.

https://docs.nvidia.com/cuda/cuda-installation-guide-microsoft-windows/index.html

Run the "INSTALL_DEPENDENCIES.bat" file on the first run

Run the "BubbleBlaster.bat" file included in the release.

To install manually, git clone the repository, install dependencies and run bubbleblaster.py

git clone https://github.com/Aeonss/BubbleBlaster
pip install -r requirements.txt
python bubbleblaster.py

❤️   Examples

Program

Original Raw Manhwa

After BubbleBlaster

Raw Text

Translated Text vs Scanlation Translation

Preview Image

Files

🚀   Usage

  1. Click on the "Import Image(s)" button to select the images you want to OCR (remove the text of)
    • You can select 1 image, or multiple by ctrl + clicking the images or drag selecting them
  2. Select the language that the text is in
    • By default, the language is Korean, but Chinese, Japanese, and English is also supported.
    • Please request for more languages here
  3. Select the confidence level by dragging the slider
    • Confidence level is how "sure" the AI is that the text is the language you selected
    • By default, the confidence level is 0.4.
    • The higher the number, the less likely text is recognized and OCR'd, but the text is more likely to be the selected language
    • The lower the number, the more likely that more text is recognized and OCR'd, but the text may include symbols or parts of the art
  4. Select which texts to remove
    • You can select chosen outlined text or click the "select all" button to remove all chosen text
  5. Select any additional options
    • "Export raw text" option will give a text file (.txt) of the text that the program OCR'd
    • "Export translated text" option will give a text file (.txt) of the translated text that the program OCR'd

✅   Additional Information

🤖   To Do

  • Add a drag and select in the preview to manually select areas to inpaint
  • Add zoom feature for large images in preview
  • Add right click to move around in preview

📘   License

BubbleBlaster is released under the MIT license.

Core symbols most depended-on inside this repo

intersect
called by 1
util.py
checkUpdate
called by 0
util.py
setLog
called by 0
util.py
exportRaw
called by 0
util.py
sanitize_image_name
called by 0
util.py
importImages
called by 0
bubbleblaster.py
updateConfidenceLabel
called by 0
bubbleblaster.py
blast
called by 0
bubbleblaster.py

Shape

Method 11
Function 5
Class 1

Languages

Python100%

Modules by API surface

bubbleblaster.py12 symbols
util.py5 symbols

For agents

$ claude mcp add BubbleBlaster \
  -- python -m otcore.mcp_server <graph>

⬇ download graph artifact