-
Notifications
You must be signed in to change notification settings - Fork 175
Issues: KUR-creative/SickZil-Machine
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
Will it be better to detect text first then gen the mask?
Enhancement
Performance optimization, Edit typos, good things etc...
#59
opened Sep 5, 2019 by
xulihang
hello,can you provide UNET and Deepfill v2 training model source code?thanks!
#58
opened Sep 2, 2019 by
zhangyanbo2007
Hello, I would like to ask why the text mask does not directly use text area detection technology, such as the CTPN model? This mask is a regular rectangle, is it simpler than the U-net model? Then does subsequent Deepfill v2 have an advantage over irregular masks in dealing with rectangular boxes? Looking forward to your answer, thank you!
#55
opened Aug 27, 2019 by
zhangyanbo2007
"Open manga project directory" button
New Feature
New feature
#54
opened Aug 27, 2019 by
KUR-creative
虽然对于小范围修图效果尚可,但对于大范围的修图效果较差(Although it is acceptable for small-scale retouching, it is not effective for large-scale retouching.)
Enhancement
Performance optimization, Edit typos, good things etc...
#52
opened Aug 24, 2019 by
BearManlc
Previous Next
ProTip!
Updated in the last three days: updated:>2024-12-31.