[kollo]

Hi everyone,

I’ve been working on a web-based tool called EbookCC to help comic enthusiasts and creators manage their collections and projects more effectively. I wanted to share it with the community here to get your feedback!

The goal of EbookCC is to make creating and converting digital comics easy and accessible. Here’s what it can do:

    Create Your Own Comics: Turn your photos or sketches into a professional-looking digital comic book in minutes.

    AI-Powered OCR & Translation: Use AI for the heavy lifting. Automatically extract text from images or translate them into different languages.

    Smart Panel Splitting: To make reading on smaller screens easier, the tool can split full pages into individual panels.

    Manual Text Support: Add your own text overlays. These are handled as "real" text layers, which means they remain searchable and exportable.

    Reflowable & Fixed Layout Exports: Export your work to EPUB, PDF, HTML, or even plain TXT. When exporting to EPUB or PDF, the real text is placed underneath the image to ensure high-quality formatting and searchability.


The app is entirely web-based, so there is nothing to download or install. I’ve focused on making it "lightweight" where AI is used only for OCR and translation, keeping the rest of the workflow fast and manual where it counts.

You can try it out here:https://ebookcc.cptd.workers.dev/

I’d love to hear what you think! Whether you are a creator looking to digitize your sketches or a reader looking for a better way to format public domain scans, I hope you find it useful.

Best regards,
kollo

[kollo]

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

[kollo]

 :)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!

[kollo]

I’m really excited to share a massive new release for EbookCC! Since the last update opening up the source code and adding offline Ollama support, I’ve been working on transforming the app from a simple converter into a complete, end-to-end comic reading and creation suite.
Here is what is new in this latest version:
? 1. Dedicated "Read Mode" & Guided Panel Viewer
For manga collectors and serious readers, I’ve introduced a structured Read Mode optimized for digital screens and E-ink devices.
Guided Step-by-Step Panel Reading: You can now read complex manga or comic strips by focusing on split panels one by one. The viewer handles panel transitions in sequence, meaning you no longer have to squint, pinch-to-zoom, or scroll constantly on smaller mobile devices.
Aesthetic Layout Settings: Toggle optimized dark, light, and warm sepia reading modes instantly.
✍️ 2. Online "Create Mode" & WYSIWYG Story Writer
Need to write script treatments, localized dialogue translations, or design your own pages? I’ve added a beautiful web-authoring canvas.
WYSIWYG Rich Text Editor: Author graphic narratives, script outlines, and formatted eBook documents. It features a brand new minimalistic distraction-free design with logical inline indicators (like "Start writing your story...") to keep you focused.
Online Comic Strip Designer: Plan multi-panel templates, input custom graphics, overlay action-style dialogue balloons, and export high-res graphic novel layouts.
⚡ 3. Under-the-Hood Efficiency Upgrades
Built-in optimizations have significantly lowered image rendering overhead.
Responded to UI feedback with slicker side-panels, wider fluid header canvas grids, and streamlined desktop-to-mobile navigation flows.
?️ Future Roadmap & What's Next (To-Do List)
I have big plans to keep expanding EbookCC, and I’m focusing hard on two primary features next:
Interactive AI Agents: Integrate a cooperative assistant inside the Workspace to act as a co-creator for suggesting dialogue pacing, formatting scripts, and helping readers dynamically summarize complex storylines.
Smarter YOLO Layout detection: Training an upgraded, highly specialized YOLO computer vision model capable of detecting and segmenting extremely complex, modern, or avant-garde panel layouts with high structural accuracy.
? I Need Your Feedback!
This tool is shaped entirely by how the community uses it. If you’re a reader, collector, Webtoon translator, or independent creator, I’d love for you to put the new capabilities through their paces and let me know:
How is the guided view reading flow feeling on your tablets or phones?
What additional layout configurations or styling features would you want in the Create mode?
Any general bugs or performance bottlenecks you run into.
Try out the new features live: https://ebookcc.com
Browse the code or self-host it locally: https://github.com/PP002/ebookcc
Thank you all for the incredible continued support, testing, and feedback!
— Pierre Kollo

[paw broon]

Thanks for your posts Pierre.  I'm sure they are of interest to our members. Unfortunately and despite having read through  the tech details in your posts, I understand very little of them.
But keep posting, and any comments you  might like to make on any aspects on the forum will be most welcome.

[kollo]

Hi Paw,

Haha, no worries at all! I totally get it—sometimes I get a bit too excited and start speaking fluent "nerd." Let me translate all that tech jumbo into plain English:

Basically, you can now use EbookCC to read manga on your phone panel-by-panel without constantly pinching and zooming (no more squinting!). And if you are feeling creative, you can even write and design your own comic strips right on the website.

Thank you so much for the warm encouragement and for keeping this space so welcoming. I promise to keep my future posts a bit more human-friendly! ?

? Have feedback or ideas?
Drop me a line at: support@ebookcc.com

Best,
Pierre