[a / b / c / d / e / f / g / gif / h / hr / k / m / o / p / r / s / t / u / v / vg / vm / vmg / vr / vrpg / vst / w / wg] [i / ic] [r9k / s4s / vip / qa] [cm / hm / lgbt / y] [3 / aco / adv / an / bant / biz / cgl / ck / co / diy / fa / fit / gd / hc / his / int / jp / lit / mlp / mu / n / news / out / po / pol / pw / qst / sci / soc / sp / tg / toy / trv / tv / vp / vt / wsg / wsr / x / xs] [Settings] [Search] [Mobile] [Home]
Settings Mobile Home
/w/ - Anime/Wallpapers

4chan Pass users can bypass this verification. [Learn More] [Login]
  • Please read the Rules and FAQ before posting.
  • Maximum file size allowed is 6144 KB.
  • Images smaller than 480x600 pixels are not allowed.
  • There are 6 posters in this thread.

08/21/20New boards added: /vrpg/, /vmg/, /vst/ and /vm/
05/04/17New trial board added: /bant/ - International/Random
10/04/16New board for 4chan Pass users: /vip/ - Very Important Posts
[Hide] [Show All]

Happy 19th Birthday 4chan!

the /g/tard who's making the stable diffusion guide was able to incorporate an A.I. image upscaler.

Dev-anon's main guide for getting the A.I. installed in 5 steps

His script page for the GUI. Use this for grabbing new webgui.py and such

realESRGAN is the upscaler, follow git instructions or do like me and just extract the downloaded zip into it's own folder within the stable-diffusion-main, and then install the pip dependency things via the conda window CD'd into whatever ESRGAN folder you've made

It's wallpaper time, boys.
those upscales always look like total ass.
throw some spaghetti into a room and push it around until it creates the monalisa. lots of """detail""" but it's actually just garbled nonsense up close.
What is the best way to make a wallpaper with stable diffusion? Should I make 512x320, then scale up to 1920x1200? Then crop to 1920x1080?
File: tmpob0c58wp.png (1.66 MB, 1920x1088)
1.66 MB
1.66 MB PNG
Here are 2 wallpapers I made with Stable diffusion, directly from the webui, in 1920*1088 (coesn't accept 1080)
File: tmphpwpcei1.png (2.1 MB, 1920x1088)
2.1 MB
2.1 MB PNG

Why would you upscale when it looks like shit and you can do it directly in highres from the webui?
The Stable Diffusion upscaler works differently.
In a typical case you don't want the upscaler making things up or adjusting the image, since you just want a higher-resolution version of what you have. But with an already-AI generated image, it makes no difference if that happens, so it's what the SD upscaler does. It's not "fake" details since it's coming from the same source as the original. The upscaler actually does make a higher-resolution version of the image, with real details generated to fill it in, to the extent that any details are "real" in an AI image.
Of course, it still has all the flaws of AI-generated images in general, and it's also not perfect, but in enough cases to be worth it, an SD-upscale of an SD image is at least as good as if it had been created in that resolution to begin with. And in many cases better, since re-running the image can tidy up flaws with fiddly areas like hands and faces.

Assuming the Automatic1111 UI:
Generate in the largest resolution of appropriate ratio you can handle, with the Highres fix on. Then run it through the SD upscaler script (not the extras tab, but the one at the bottom of the img2img tab). It may take multiple runs, with different prompts (since it works in chunks, you might need to do some runs with a prompt that emphasizes the foreground, and others that emphasize the background, etc), and you'll very likely need to stitch multiple versions together. And it'll take experimenting with different samplers, pre-upscalers, etc.

Because that takes a lot of VRAM. Meanwhile the SD upscaler runs in more manageable chunks, so larger images only take longer time without consuming more resources.

Delete Post: [File Only] Style:
[Disable Mobile View / Use Desktop Site]

[Enable Mobile View / Use Mobile Site]

All trademarks and copyrights on this page are owned by their respective parties. Images uploaded are the responsibility of the Poster. Comments are owned by the Poster.