- cross-posted to:
- hackernews@lemmy.smeargle.fans
- cross-posted to:
- hackernews@lemmy.smeargle.fans
Upscayl lets you enlarge and enhance low-resolution images using advanced AI algorithms. Enlarge images without losing quality, it’s almost like magic! 🎩🪄 Upscayl is a cross-platform application built with the Linux-first philosophy. This means that Linux users receive pre-release builds earlier but Upscayl itself is available on all major desktop operating systems :)
now look what this baby can do …
Huh? A sparkly fart in the sky? 🧐
Holy fuck, a Supernova! Cosmic spectacle of incomprehensible dimensions! 🤯
I wanted to implement the pics into the post via
![alt text](image url)
But it was not working for the upscayl version, sorry.
damn, the CSI enhance shit really was real
ENHANCE
That’s not CSI until it can zoom in from Google Earth to my living room!
And not that everything is a competition, but in my testing the results of upscayl always look a bit better than the ones from this web based non foss upscaler.
have you tried it against waifu2x ?
The tool Upscayl uses, RealESRGAN, is superior to waifu2x - waifu2x is really showing its age at this point. waifu2x is good if you want an upscale that basically retains the same level of fidelity while increasing the resolution (i.e., usually it’s blurry). Newer upscalers try to clean up the lines and make it look like it’s an original copy.
Edit: Just for fun, here’s some tests via downscaling a picture then re-upscaling it:
There are also other models available to test with beyond the stock RealESRGAN ones (I’m not sure if Upscayl can use them but they’re available for CLI use). I recommend using chaiNNer - e.g. you can use a setup like this
A couple extra models:
escale (probably the best for this picture)
just seen your edits, that is some SUPER COOL STUFF! definitely big improvements from waifu2x
waifu2x technology is the main part that’s old I think. There’s a lot of NCNN/etc. models to use now to try to tune for different details. My main problem with waifu2x is that it gives you roughly the exact same fidelity as the original picture, i.e. it’s only slightly sharper than using a generic zoom function on it. Newer upscalers try to make the image more realistic, as if it was the original in the first place. In a direct comparison with the original I think there’s a notable loss of detail in this method (not sure if it’s inherent or just based on how the model is tuned), but without the original to compare to I think the images that the newer ones generate look more pleasing/sharp.
nice!
I use Upscayl professionally and can confirm it beats out every proprietary alternative
How is it vs. Topaz Gigapixel AI or Photo AI?
Does it have a backend library for tools to link to? It’d be great to have this in the Image Magick convert tool pipeline.
it’s a gui for real-esrgan-ncnn-vulkan
I wanted to implement the pics into the post via
![alt text](image url)
But it was not working for the upscayl version, sorry.I just had to copy the link that the
Download original image
button pointed to and remove the?dl=1
from the end, and that gave me this URL which points to the image and can be embedded in the post.ah sweet, thanks
Going to check this out later today. Thanks so much for sharing!
deleted by creator
Ah good, I’ve been looking for something better than Waifu2x. Thanks!
How does this compare to waifu2x for anime-style images? Does it manage to beat it, or is this more for photos?
I always use this for my wallpapers
Nice, I have to check this out.