When will training code to be released?
Nobody has claimed this yet.
Assessment
- Difficulty
- 5/5
- Estimated time
- Over a week
- Newbie friendliness
- 18/100
- Issue type
- Feature
- Clarity
- Needs clarification
- Activity status
- Stale
- Tech stack
- python
- Domain
- computer-vision, machine-learning
Research direction
The issue names no files, tests, or entry points. First determine whether training code has been released elsewhere and clarify the intended training-data and color-tone scope; the request is complete only when the training code's release status and usage are documented or the requested release is provided.
Written by the indexing model from the issue text.
Description
Hi, I have tested this model with GrayImage(ScreenStyle) and Sketch with Shading
it seems that both will produce less color.
I belive its because in the training data that older manga seems to use less color.
When you apply to newer manga or doujin, over color tone will look very weird.
I would like to have training code to readjust color tone.
it become real bad when doing multiple sections. is it because some of your training data are partially colorized?
compare colorize done by chatgpt, though its more of regeneration than colorization
- Dominant language
- Python
- Stars
- 463
- Forks
- 44
- PR merge metrics
- No merged PRs in 30d
Getting set up
This project ships no dev container, Dockerfile or contributing guide, so setting up is up to you: start from its README, and see our first-contribution guide for the general steps.
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from TencentARC/ColorFlow
-
Difficulty 4/5 3-5 days Newbie friendliness 55/100
TencentARC/ColorFlow#22 ·
-
生成的图片为黑色Open
Difficulty 4/5 3-5 days Newbie friendliness 25/100
TencentARC/ColorFlow#20 ·
-
可以直出图片，不修改图片大小吗？Open
Difficulty 4/5 3-5 days Newbie friendliness 25/100
TencentARC/ColorFlow#19 ·
-
5090d用不了Open
Difficulty 3/5 1-2 days Newbie friendliness 25/100
TencentARC/ColorFlow#18 · 1 comment ·
-
Difficulty 4/5 3-5 days Newbie friendliness 25/100
TencentARC/ColorFlow#17 ·
All issues in TencentARC/ColorFlow
Similar issues
-
bug frontend
Difficulty 2/5 1-3 hours Newbie friendliness 85/100
PedestrianDynamics/pyFDS-Evac#552 ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 84/100
resend/resend-skills#144 ·
Maintainers usually reply within 1 day
-
good first issue
Difficulty 1/5 Under an hour Newbie friendliness 68/100
-
Bug
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
GNS3/gns3-server#2935 · 1 comment ·
Maintainers usually reply within 1 day
-
bug
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
TauricResearch/TradingAgents#1476 ·
Maintainers usually reply within 2 days