Joined Jul 2022
doggel
boosted
The world is full of things that do not work properly. Therefore the world is full of opportunities. The trick is finding which battle you want to fight, and then actually fighting it.
doggel
boosted
@shedinja Jap women display significantly more feminine grace and warmth than their White Western counterparts. When they're in the eyes of the public, that is. Behind the closed doors of family life they're vicious cunts, they routinely cheat on and divorce their husbands, use their children as weapons against the father, etc. The Japanese constitution was written by a jewish woman after ww2. Japan is a ZOG colony so it makes sense that their women have been infected by feminist narcissism
doggel
boosted
There has to be a reason japbros won't fuck their women outside of the usual porn and video games excuse, those bitches are probably crazy
🇵🇸 🇮🇷 🇰🇵
doggel
boosted
People misunderstand the Reform Jews as worse than orthodox because they push "liberalism" up front
The Orthodox Jews covertly teach these things in their scriptures but pretend to oppose them
The reform Jews learned these corrupt value systems from the orthodox but are just more vocal about it and do not use scriptures to justify them
Because the reform Jews are more willing to talk to people from other religions & do not cling to the post christian scriptures
There is more hope for them
doggel
boosted
doggel
boosted
doggel
boosted
doggel
boosted
AAAAAAAA IT'S ALMOST CHRISTMAS
doggel
boosted
@thor Almost forgot, nowadays, every single model out there is a merge of some damaged model, if you want to get something good and update, you may have to do weighted u-net layer merging of older models with new models and pray that it comes all right or at the very least you get more insight in what exactly you are doing.
@thor Lose of information also gets passed down when merging.
@thor (2/2) re-train a working model with not-properly tagged pictures of corgis, now all dogs are going to start looking a little more like corgis
@thor (1/2) That depends heavily on what model you are using, most models out there are merges, when you merge a model, defects in one model get passed down. A very common defect is ignoring the tokens in the prompt, like for example, ignoring the second token, or the fifth. This is lowkey intentional. Also, moving up the cfg scale a little will also help. Another problem is that retraining models make the model lose info, for example, if you...
@thor (2/2) In the negative prompt "more than 2 hands", the model will find it hard to generate good hands, since it is both being instructed to generate hands (2) and to not generate hands, and pictures with 2 hands and pictures with more than 2 hands share way too many similarities (the presence of hands). This will result in an increased rate of deformities in the hands. To properly add negative prompt is best to keep things short and precise, or use embeddings.
@thor (1/2) Simply put, if you type "anime girl" in the prompt, the diffusion model will generate something, anything, that could fit the "anime girl" tag, that may include missing limbs or deformities. Because of this, you could either add "cute" in the prompt or "zombie" in the negative prompt and it will try to generate something that fits those characteristics.
With that been said, blindly adding negative prompts will backfire, let's say you put in the prompt "2 hands" and...
Joined Jul 2022
