[Release/Web-App] EbookCC: AI-Powered Comic Translation & Batch Processing Tool

[kollo]

Hi everyone,

I’d like to share a new tool I’ve been working on called EbookCC, designed for comic enthusiasts and translators who want to streamline their editing workflow. It’s a web-based application that leverages the latest AI (Google Gemini) to detect, OCR, and translate speech bubbles in batch.

What is EbookCC?
EbookCC is an open-source (or free-to-use) web application that automates the tedious parts of comic editing. Instead of manually cleaning bubbles and re-typing text, EbookCC uses AI to "see" the comic panels and handle the heavy lifting.

Key Features:

Batch Processing: Drag and drop an entire folder of images, or your .ZIP / .CBZ comic files, and the app will queue them for processing.

AI-Powered OCR: Powered by the gemini-2.0-flash-lite model, it features incredibly accurate text detection even in stylized comic fonts.

Automatic Cleaning: The app attempts to detect bubble boundaries and can provide "cleaned" versions of the pages.

Built-in Translation: Support for over 100 languages. You can batch-translate an entire volume with one click.

Text Overlays: View the translated or OCR’ed text directly over the original comic page using selectable overlays.

Privacy-Focused: The app runs in your browser. While it uses the Gemini API for analysis, your files are processed locally in your session.

How it works:

Upload: Drop your comic pages (ZIP/CBZ/JPG/PNG) into the dashboard.

Analyze: The AI scans for text bubbles and panels.

Translate/Edit: Select your target language and refine the detected text in the built-in editor.

Export: Export your findings as a text file or use the snapshots for further editing.

Why use it?
If you’ve ever tried to translate a manga or digital comic manually, you know how much time goes into "redrawing" and re-typesetting. EbookCC aims to reduce that time significantly by providing a smart starting point.

Get Started:
You can try the demo here: https://ebookcc.cptd.workers.dev/

Note: The app includes a generous free tier via Gemini's API (up to 1,500 requests per day), but you can also plug in your own API key in the settings for higher throughput.

I'd love to hear your feedback or feature requests!

[GigaCat]

This looks promising. But I figured that people might not be comfortable inserting their API key since the app is not local. Is this app's code open-sourced? That would certainly help a lot.

Alternatively, you can charge them according to requests. Like most other apps.

[kollo]

Originally Posted by GigaCat

This looks promising. But I figured that people might not be comfortable inserting their API key since the app is not local. Is this app's code open-sourced? That would certainly help a lot.

Alternatively, you can charge them according to requests. Like most other apps.

Thanks for the feedback, GigaCat! I totally understand the security concerns regarding API keys.

Security: To address this, the app is designed so that your API key is only stored in your browser's local storage and is sent directly to the AI provider via encrypted HTTPS. It never touches our servers.

Open Source: Yes, transparency is key! I am currently adding a new feature to create comic panel collages and cleaning up the codebase. I plan to host it on GitHub very soon so everyone can audit the code or host it locally.

Local Processing: I am also looking into supporting local models (like Gemma/Ollama) in the future to keep everything 100% offline.

Stay tuned for the repo link!

[kollo]

Originally Posted by kollo

Hi everyone,

I’d like to share a new tool I’ve been working on called EbookCC, designed for comic enthusiasts and translators who want to streamline their editing workflow. It’s a web-based application that leverages the latest AI (Google Gemini) to detect, OCR, and translate speech bubbles in batch.

What is EbookCC?
EbookCC is an open-source (or free-to-use) web application that automates the tedious parts of comic editing. Instead of manually cleaning bubbles and re-typing text, EbookCC uses AI to "see" the comic panels and handle the heavy lifting.

Key Features:

Batch Processing: Drag and drop an entire folder of images, or your .ZIP / .CBZ comic files, and the app will queue them for processing.

AI-Powered OCR: Powered by the gemini-2.0-flash-lite model, it features incredibly accurate text detection even in stylized comic fonts.

Automatic Cleaning: The app attempts to detect bubble boundaries and can provide "cleaned" versions of the pages.

Built-in Translation: Support for over 100 languages. You can batch-translate an entire volume with one click.

Text Overlays: View the translated or OCR’ed text directly over the original comic page using selectable overlays.

Privacy-Focused: The app runs in your browser. While it uses the Gemini API for analysis, your files are processed locally in your session.

How it works:

Upload: Drop your comic pages (ZIP/CBZ/JPG/PNG) into the dashboard.

Analyze: The AI scans for text bubbles and panels.

Translate/Edit: Select your target language and refine the detected text in the built-in editor.

Export: Export your findings as a text file or use the snapshots for further editing.

Why use it?
If you’ve ever tried to translate a manga or digital comic manually, you know how much time goes into "redrawing" and re-typesetting. EbookCC aims to reduce that time significantly by providing a smart starting point.

Get Started:
You can try the demo here: https://ebookcc.cptd.workers.dev/

Note: The app includes a generous free tier via Gemini's API (up to 1,500 requests per day), but you can also plug in your own API key in the settings for higher throughput.

I'd love to hear your feedback or feature requests!

Hi everyone, I've just pushed a significant update to EbookCC with features for both collectors and creators:

🖼️ Create Your Own Comics: You can now use your own photos or sketches! I've added various Templates to automatically handle perfect multi-panel layouts.

🌑 E-Ink Optimization: Added better background handling for transparent images and enhanced rendering logic to ensure manual text is sharp and legible on e-ink screens.

📖 Reflowable Export: Export to EPUB and TXT now fully supports manually added text. In EPUBs, the text is placed as a real layer behind the images, making your comics searchable and compatible with text-to-speech!

⚖️ Balanced AI usage: Reminder that AI (Gemini) is only required for OCR and Translation. Layout detection and formatting are handled locally for speed and privacy.

Check out the updated demo here: https://ebookcc.cptd.workers.dev/
I’d love to hear what features you want to see next!

[kollo]

For security and stability, I have purchased a new domain name. Please visit the new website: https://ebookcc.com

[kollo]

Originally Posted by kollo

For security and stability, I have purchased a new domain name. Please visit the new website: https://ebookcc.com

Hello everyone,

I wanted to share a major update regarding EbookCC, the browser-based tool designed to detect, translate, and overlay selectable text onto comic speech bubbles. Thanks for all the initial thoughts and interest!

Here is what is new in the latest version:
📂 1.Open Source!
https://github.com/PP002/ebookcc
EbookCC is now fully open source and hosted on GitHub. You can check out the source code, run it locally on your machine, or contribute directly to the repository. Running it locally completely bypasses any cloud network restrictions, letting you hook up your tools with zero delay.

Try the Cloud Version: https://ebookcc.com/

💻 2. Full Local Model Support (Ollama & LM Studio)

You can now run EbookCC entirely offline and privately using standard self-hosted APIs on your computer:

LM Studio & Ollama Integrations: Simply plug in your local URL (like http://127.0.0.1:1234/v1 or http://127.0.0.1:11434/v1). EbookCC connects to them directly inside your browser so it is incredibly fast and completely secure.

CORS & Connection Guidance: We have integrated friendly setup checklists directly into the settings window to guide you through environment setups (such as setting OLLAMA_ORIGINS="*").

⚡ 3. Gemini Context Caching for Speed and Savings

For those using the cloud API, I have introduced Gemini Context Caching. Because comic books contain consistent panel contexts, caching previous translation templates saves up to 50–80% on token overhead and optimizes response latency.

👥 4. Direct Feedback & Local Model Recommendations

I have been testing local setups with lightweight models like Gemma 4B / Gemma 2, which perform excellently for language translation steps! However, smaller 4B-8B quantized weights sometimes lose a bit of spatial/multimodal coordinate precision for OCR bubble-finding compared to giant cloud APIs.

I need your feedback: If you are testing local workflows, please let me know which models are working best for you!

Are you using llama3.2-vision, qwen2.5-vision, or something else? I would love to hear your recommendations on a solid local model that strikes a great balance between text recognition and speed on consumer GPUs.

Thank you all for the support. I look forward to hearing your thoughts!