bytedance / bytedance/StyleSSP
Content structure not well preserved during style transfer
Open
- Dominant language
- Python
- Stars
- 92
- Forks
- 6
- PR merge metrics
- No merged PRs in 30d
Description
The style transfer from the style image is working well, but the content structure of the content image is not being properly preserved in the output.
Could you advise on what configurations or architectural changes would help better maintain the content structure of the content image during inference?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.