Waifu2x-Extension-GUI VS multidiffusion-upscaler-for-automatic1111

The software in question is on Github called Waifu2x-Extension-GUI https://github.com/AaronFeng753/Waifu2x-Extension-GUI

Waifu2x GUI

I used a program called Waifu2x-Extension-GUI. It’s fantastic for upscaling animation shows (and yes it supports video upscales too)! There are web-app versions out there with the same name, but the results I get from those are nowhere near as good. If anyone’s unable to download or figure it out, I’d be happy to upscale any images you want!

I heard topaz may be the best but you can try bsrt, video2x and waifu2x ext gui.

I do my upscaling with Waifu2x, specifically with this really well made GUI https://github.com/AaronFeng753/Waifu2x-Extension-GUI

se descargan este archivo (Waifu2x-Extension-GUI).

4090 is very fast in this regard. It takes about 6 hours or so for a film that is 1.5 hours. The software is called Waifu2x Extension GUI by Aaron Feng. It's free to use, but you'll get a pop-up asking to donate. It gets constant updates, which is always a major plus. Here's the GitHub: https://github.com/AaronFeng753/Waifu2x-Extension-GUI I used the RealCugan AI Model since I found it yields the best results in terms of speed and quality. You can use RealESRGAN for Live works, but it will take significantly longer. Sidenote: You can use it on blurry pictures as well (Since videos are simply a series of frames/still images)

Use tiled VAE, it will save VRAM: pkuliyi2015/multidiffusion-upscaler-for-automatic1111: Tiled Diffusion and VAE optimize, licensed under CC BY-NC-SA 4.0 (github.com)

My favorite solution is to not use ultimate Sd upscale and instead use multidiffusion-upscaler.

sure, i personally use 'tiled diffusion' https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111, works like charm also use adetailer for faces if its needed.

What worked for my 1080 was using TiledVAE and turning down the quality of my previews - I don't pay much attention to it/s but it's definitely faster than using --medvram, and now I can handle batches and large resolutions without things exploding on me.

I would highly recommend adding https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111 to your A1111 installation, TiledVAE is enabled automatically under the hood in A8R8; this will allow you to get even larger generations before getting an out of memory error. You'll get a Tiled Diffusion checkbox with some reasonable hardcoded defaults as well.

Use Tiled VAE https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111

That's weird. 10GB should allow you to hires to 2048x2048 at least. Use Tiled VAE extension https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111 that will allow you to go even beyond that.