3d-photo-inpainting VS arXiv2021-RIFE

If you are looking to create actual 3d models, the DepthMap extension does have a function to create PLY models with vertex color information, and to render clips with simple camera moves from that extracted 3d scene, including inpainting (as per the 3d-photo-inpainting paper)

The depthmap extension for A1111 has implemented the 3d-photo-inpainting code that is doing that kind of thing. That's what I used to use, first on a Colab, and then adapted for windows so I could run it locally. But it's much more convenient to do it directly from the Automatic1111 WebUI.

But things are even older than stable diffusion.

It's a slightly modified version of https://shihmengli.github.io/3D-Photo-Inpainting/

Thanks! I barely did anything though, just took a deep dream'ed photo made by another artist (Daniel Ambrosi) and passed it through this: https://shihmengli.github.io/3D-Photo-Inpainting/ (github and colab at bottom). Didn't even have to come up with the camera trajectory, was one of the presets in the repo

pretty sure it's this: https://github.com/vt-vl-lab/3d-photo-inpainting

RIFE Link - https://github.com/hzwer/arXiv2020-RIFE

Now I see that a new model called RIFE is available: https://github.com/hzwer/arXiv2020-RIFE but I'm not sure of there are any open source frontends for it.

You might be able to clean up your video frames with something like RIFE and/or Real-ESRGAN.

You mean RIFE. Dang swipe/voice dictation!

That is already quickly becoming a thing. There is an AI called RIFE, which is publicly accessible for free (github repo), if you know how to use the terminal/command line, and some python you can get it working fairly easily, and it interpolates video with really good quality and efficiency.

The video was interpolated to 60 fps using RIFE (which explains any artifacts or distortions)