rembg

If you don’t mind CLI, rembg is a good option for background removal. It lets you swap between different models depending on the type of image so you can use something like `birefnet` for photorealistic images and `toonout` for illustrations. https://github.com/danielgatis/rembg

It's a pretty well known problem in the generative image domain. GPT-image-1 (and gpt-image-1.5) are outliers in their ability to generate images with a proper alpha channel. You can still use other models (Flux, SDXL, NB, etc), you'll just need to request that the image be generated on a solid colored blackground. Then just run it through Rembg [1] or similar background removal tool. [1] - https://github.com/danielgatis/rembg

Yep. Your best bet is to ask for "solid white/black background" and then feed it into something like rembg [1]. It's an extra step but it'll get you partly there. On the OpenAI side, the gpt-image-1 model has actually had the ability to produce true alpha transparent images for a while now. Too bad quality-wise they're lagging pretty badly behind other models. [1] - https://github.com/danielgatis/rembg

It is a 2024 model, for comparison https://github.com/danielgatis/rembg/ uses U2-Net which is open source from 2022. There is also https://github.com/ZhengPeng7/BiRefNet (another 2024 model, also open source), it's not too late to switch.

I wouldn't blame apt-get, there are a lot of command-line tools nowadays. I don't usually install these if its not going to be a frequent task. Anyways, if you're looking for a cmd tool, rembg [0] is a pretty good one. [0]: https://github.com/danielgatis/rembg

Was searching for an equivalent for Linux, came across rembg. https://github.com/danielgatis/rembg

It is a classic computer vision problem: image segmentation. There are open source tools like rembg (https://github.com/danielgatis/rembg) which call into pre-trained models. It is also easy to train your own model, I've used code from https://github.com/SkyTNT/anime-segmentation with my own data to train an image segmentation model to separate objects with really good results.

Hey folks, I've built removebg.dev as a hobby app designed to quickly and easily remove image backgrounds for free. The app is built with the help of: - The rembg (https://github.com/danielgatis/rembg) ML model built by Daniel Gatis (https://github.com/danielgatis). - Replicate (https://replicate.com/) to interact with the ML model through an API. - Next.js for building the app and Vercel for deployment. The app is fully inspired by the restorephotos.io app built by @nutlope (https://twitter.com/nutlope) so a lot of credit goes his way for his tutorials. You can find the source code for the app here - https://github.com/djirdehh/removebg.

A fast Windows self-contained native DLL to input the path to a jpeg file and output the jpeg with background removed, like https://github.com/danielgatis/rembg does or https://www.adobe.com/express/feature/image/remove-backgroun...

>However, there isn't, and I don't think you'll find an offline tool that comes close in terms of quality of result. There is: https://github.com/danielgatis/rembg