DeOldify VS Real-ESRGAN-ncnn-vulkan

The old method is simple. All you need to do is running DeOldify with a colab notebook. Then you can pick any neural networks you want for upscale and frame interpolation. A lot of people use dain-app, but I find rife faster and easier to use.

Today, we’re talking to a very special “Software Guy, currently digging deep into GANs” — The author of DeOldify: Jason Antic.

I think the novel and interesting tech is still happening, its just that without the colorful ads for it on TV, and without the software being packaged up and sold with pretty box art that you can physically hold, it doesn't feel as much like a capital-E Experience. It's probably the Internet's fault that we don't do things like that anymore, but the upside is that we now have access to so many ideas and applications from all over, even ones that aren't commercially viable.

Some that look exciting to me are: an AI that lets you animate still photos realistically [1], a simple website that guides you to discover new parks, eateries, and other places near you [2], an AI that colorizes old black-and-white photos/video [3], a Street View style map of the game world from "The Legend of Zelda: Breath of the Wild", with some 1st person 360 degree photos [4], and a tiny game engine that lets you distribute your whole game physically via printed QR codes [5].

If marketing and graphic design people ever felt like getting together to do some 'side projects', I vote that they should make print ads for apps/websites that they like :)

[1] https://github.com/AliaksandrSiarohin/first-order-model

[2] https://randomlocation.xyz (https://randomlocation.xyz/help.txt for customization)

[3] https://github.com/jantic/DeOldify

[4] https://nassimsoftware.github.io/zeldabotwstreetview/

[5] https://github.com/kesiev/rewtro

Don't even need topaz, there's plenty of free upscale models check the openmodeldb, and you have reve which is based on Real-ESRGAN-ncnn-vulkan.

Real-ESRGAN/GFPGAN https://github.com/xinntao/Real-ESRGAN (Real-ESRAN - Upscale images, facial restoration with GFPGAN setting) https://github.com/TencentARC/GFPGAN (GFPGAN - Facial restoration and Upscale) -------MATTE AND COMPOSITE--------

If you mean by free software, sure there are options. But you'll spend a lot of time to do that. You can try https://github.com/xinntao/Real-ESRGAN or similar tools

I’m actually on a Mac using the ncnn Vulkan binaries for Real ESRGAN. It’s not all that flexible but it’s pretty quick. There are other options but I have not looked into it.

I personally use real esrgan and I think it's great. it requires manual work tho but it's easy once you do it a few times

REAL-ESRGAN was used for upscaling (using waifu2x-extension GUI) and can be found here.