tachiyomiJ2K
tachiyomiJ2K copied to clipboard
Speech Bubble Zoom
Describe your suggested feature
There's only one thing that wish TACHIJ2K had and it's Google's BUBBLE SPEECH ZOOM. It uses machine learning to recognise speech bubbles and intelligently zoom into them for easier reading. Move from bubble to bubble one tap at a time, and still allows to keep the full-page experience. This vastly improves the reading experience and allows to enjoy the comic without zooming anywhere, especially on devices with smaller screens, like phones. The difference is night and day.
Here's a demo. https://www.theverge.com/platform/amp/2016/7/21/12229074/google-play-books-bubble-zoom-machine-learning-sdcc-2016
Bubble Zoom on Google Play Books: https://youtu.be/1v7dS8i5G9U
Seems like the guys over at Seeneva have built an open source manga/comic reader with this feature. Maybe there is a way to work with them to include such features into Tachiyomi :)
Other details
I requested the exact same thing about 2 years ago but was declined due to lack of open source ML models. But now that some folks have already done the heavy lifting and made the ML models open source, I am hoping it should be easier to implement.
Acknowledgements
- [X] I have searched the existing issues and this is a new ticket, NOT a duplicate or related to another open issue.
- [X] I have written a short but informative title.
- [X] If this is an request for a feature in the original Tachiyomi, I am opening because multiple versions of TachiyomiJ2K have been released without this feature.
- [X] If this is an issue with an extension, or a request for an extension, I should be opening an issue in the extensions repository.
- [X] I have updated the app to version 1.6.6.
- [X] I have checked through the app settings for my feature.
- [X] I have admitted that I am a clown by having checked this box, as I have not read these acknowledgements.
- [X] I will fill out all of the requested information in this form.
Perfect viewer have a speech bubble zoom and separate magnifier function. Its nice if someone can develop something similar in tachiyomi.
Couldn't have asked for a better suggestion
Is this being worked on? or not a priority as of now.