Skip to content
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

Please consider configuring rembg for Gimp (it doesn't reduce quality and works 100% offline) #5

Open
superdreamkilla opened this issue Jan 25, 2021 · 4 comments

Comments

@superdreamkilla
Copy link

superdreamkilla commented Jan 25, 2021

Many people who use Gimp on Linux do not like the concept of using a online tool that cannot be used locally offline, as they value privacy. You may not have known but https://github.com/danielgatis/rembg is a open source python neural network that works 100% offline and can be configured natively against ones system or a static miniconda environment profile. This allows the user to remove image backgrounds in high quality without sending their data to a foreign server.

please consider configuring rembg with Gimp. Below is a thread about it and some test I ran. I even made a bash script for myself to activate rembg from my start menu in a desired folder.

https://forums.linuxmint.com/viewtopic.php?f=42&t=339124

TEST
image

image

image

image

@manu12121999
Copy link
Owner

Nice, looks promising.
I was searching for an open source alternative to remove.bg (I have even begun to train a neural network by myself for this purpose), but I did not find this repo. I will definitely look into it and maybe integrating it into GIMP (but not in the next two or three months).

Anyway, thank you for mentioning it.

@superdreamkilla
Copy link
Author

yes, Thank you for consider.ing. It would be preferable if it worked with versions of rembg that run in isolated python environments and it will need to give the user an option to enter the local path URL to rembg.

@raniaamina
Copy link

rembg is awesome, currently i try to create the gui for this tool, hope it can help also

@Tarek-Hasan
Copy link

Tarek-Hasan commented Feb 7, 2023

There is also now DIS (v2 upcoming), Highly Accurate Dichotomous Image Segmentation from the maker of U2-Net. U2-Net is the AI model behind rembg.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants