somehow my results are unsatisfying with stable diffusion automatic 1111 when trying to generate locally on my pc with my old gpu gtx 1080 ti 11gb, cant even get anything close to just even looking good or anything comparable, if i have to be honest automatic 1111 local generation cant even compare to the simple and basic generation of leonardo ai
Would love to see you do a new video for Pony models! Also, I'm curious how the 3M samplers work and your video's what I reference for the older models. <3
great vid..but after a few months of playing with Stable Diffusion, i think it should have been named "unstable illusion"...it has no idea what biological creatures are...like asking a Martian to describe a human...the key word is "artificial"...the misnomer or falsity is "intelligence"...artificial means fake..intelligence means the ability to think progressively...a 5yo can describe anatomy better than Stable diffusion..we humans are considered by A.I, to be nothing but static..i still enjoy messing around with it because it truly is in its infantcy and holds promise..but i am sorry..this does not compute..lol
man, i always had the trouble of not having script under controlnet like in all the videos i saw... but its literally just at the bottom, i just had other stuff before. I stupid, but glad i found it.
with all due respect, the narration goes into a solid C tier; I am absolutely sure you are able to pinpoint where it falls short when you review your commentary. Hint: Fast is not always better
According to Wikipedia, Leonhard Euler and Karl Heun are Germans, in their language EU reads as OY - OYLER and HOYN - it comes from pronunciation of Greek ϒυ - ύψιλον. It would make sense to pronounce the names based on the one principle, and the way their mom and dad called them.
I rarely subscribe anyone in RU-vid but i subscribed you because your videos were jam packed with info. i hope you're alright now that you are not uploading.
This is awesome! Would you also be able to turn all these matrices into a CivitAI article that could be quickly scrolled through? It would be great to be able to consult these via a page and scroll through them
Dude, I usually dont write comments, but this guide is awesome as hell. The explanation with the "a" in the name and the benchmarks PLUS your "good image" disclaimer were extremely well done and professional. (I am currently at minute 3, but had to post a comment first lol) I hope you get more subscribers and viewers. Thank you for your service!
Any insight or help with images made in defourm? Colors are never consistent as more images are made. I have color coherence set to LAB. I don’t know what to do. Cfg 7
It is sad that realistic models still trail behind anime/cartoon models. Like making something manga or waifu seems to be accepted in society then tasteful nudity and of course simple hands and feet.
I know this video is 1 year old, but I wonder of through a similar technique can you achieve similar results as Korea or Magnific. Have you tried something like that?
I think it's far more just getting lucky than people want to admit. I've masked out the person's shirt because it's just a t-shirt and I want the shirt to be a different style. I changed the prompt (haven't seen anything saying this won't work) to the specific clothing item and it doesn't even come close to getting it right.
Fantastic video! I have only been messing around in controlnet without really understanding the differences. This all makes so much more sense now. Thank you!
I came to similar conclusions with my own tips research and noob testing, as i have a 2070s im not going to make a big xyz grid so this video is good to see it all laid out. Wish i saw this earlier, would have saved me loads of time, but hey the experimenting was good for learning a1111, id still say im a noob though.
do you know if theres a way to use reference-only without using a prompt? i have an image and i want it to be replicated, but i don't want to prompt it
