DIS VS canvas-zoom

Hello, I had some succes using this repo : https://github.com/xuebinqin/DIS

DIS

Rembg only adds to my frustration. It's a half-assed solution providing sub-par results and acting as a band-aid for the fundamental absence of any transparency handling in diffusion models. DIS is better, but it's a pain to set up and still often needs retouching. Trying to remove backgrounds post-generation will always be an uphill battle because the information just isn't there.

also try to look into https://github.com/xuebinqin/DIS cuz it may help to either achieve the result straight away, or to make a dataset for layering lora if each picture takes to much touch up

Also checkout https://github.com/xuebinqin/U-2-Net. They have a new version in this repo: https://github.com/xuebinqin/DIS

If you want some tricks to make this smoother, try masking the wolf upfront in each frame and then only replacing the wolf itself with the pixels from sd on the second frame and onward. Keep the first frame's sd output for the background stable or change it less quickly. I've found good results segmenting with this, but lots of good options on foreground segmentation are available.

For instance, click "open in colab" at the top of this Image Segmentation notebook

Yes! The Canvas Zoom extension.

Repository Canvas Zoom

Canvas Zoom (for inpainting): https://github.com/richrobber2/canvas-zoom.git

NP. As a bonus, an extension, that made inpainting in WebUI WAY easier is Canvas Zoom -> https://github.com/richrobber2/canvas-zoom. 🔥

Oh sorry, there is an extension for that https://github.com/richrobber2/canvas-zoom So please don't bother

There's an A1111 addon called Canvas Zoom that adds a bunch of functions to the inpainting UI, such as zooming and keyboard shortcuts. https://github.com/richrobber2/canvas-zoom