rembg VS resynthesizer

A bit conflicted as the linked video is also linked from the actual rembg repo but it seems way faster and more detailed to just read the readme at that repo first, and maybe use a video if something doesn’t make sense.

There are open source tools like rembg (https://github.com/danielgatis/rembg) which call into pre-trained models.

You can use Rembg extension to remove background automatically: https://github.com/danielgatis/rembg

Hi guys 📷 I am new to ml deployment. Can anyone help about production deployment ? I made fastapi docker app which removes background from image (https://github.com/danielgatis/rembg). It uses u2net segmentation. I tried aws ec2, lambda, googld cloudrun and so far ec2(t2-large) is the fastest but still too slow. Also, it costs way more than I expected. Are there any other solution that I can deploy ml app with as low as possible? Where do you guys mostly deploy ml app?

I am currently using rembg https://github.com/danielgatis/rembg

rembg

A python script with rembg could work

4.) rembg -- backgrounds be gone. If there isn't an extension in Automatic1111 for this yet, there should be (I haven't checked recently). Same deal as midas, you can point it at a folder and zap the backgrounds off of all your images. Useful in combo with midas and imagemagick if, for instance, you want images of an object on a white background (Stable Diffusion training via LoRAs/Dreambooth may not benefit, but other things like GANs prefer that sort of training image). Useful if you want to "compose" a scene and you have images of dispirate objects/people you want in that scene.

Ran into another issue with " LoadLibrary failed with error 126 Here's the solution: https://github.com/danielgatis/rembg/issues/312

I have an old wacom tablet, so its painting masks mostly. back in the early days, I did all the things that photoshop 6 could do. Along with a brilliant plugin called resynthesiser[1] which I am horrified to find out is 23 years old.

I've never really used the scripting functions apart from applying global effects.

Nowadays I use it until I need illustrator hard enough to move to the mac downstairs. but most of my photo editing is now done in lightroom.

[1]https://github.com/bootchk/resynthesizer

GIMP has such a plugin. The package in the openSUSE repos is called gimp-plugin-resynthesizer You can read more about it here https://github.com/bootchk/resynthesizer

This is great for removing unwanted objects from any image: https://github.com/bootchk/resynthesizer

Install Resynthesizer: You can download the Resynthesizer plugin from the official website (https://github.com/bootchk/resynthesizer). Follow the installation instructions for your operating system.

A library implementing the "resynthesizer" algorithm for texture transfer among images.

You’re talking about resynthesizer from GitHub https://github.com/bootchk/resynthesizer and you have the latest ? I know it was last updated prior to the Ventura release, but you might try redownloading it again.

The sort of feature has been around for a long time. "Resynthisizer" is the name of one of the algorithms, and it's been around in Gimp for over a decade -- https://github.com/bootchk/resynthesizer -- no Tensor required.

if that's what's holding you back from just using linux by itself, then try out the resynthesizer plugin for gimp.

Parts of this collage were generated using Stable Diffusion. Includes elements of the original Bayeux Tapestry. Collage was done in GIMP, including Resynthesizer plugin to generate the background from parts of Stable Diffusion's output.