This is the XL lora version of the Alkemanubis (Alke) Style, based in the model Pony XL V6 and Illustrious01. This should works with any merge or derivated models.
Illustrious01 v1
I know that Illustrious already have this style by default, but actually it looks pretty desaturated and the characters looks like deformed dolls. I imagine that it's due the existence of old works and sketches in the dataset. But with this lora you can get more vibrant results. Additionally, I've updated the dataset and pruned it a little.
Weight: .8 - 1
Pony6 v3: LoKr
After some tests, I don't want to know nothing about DoRA's for some months xD, they are rlly stranges and gens rlly weird results. Now I have to re-train the DoRA's that I published. Sorry for it -.-. I take advantage for change for a new tagger and prune some images from the dataset.
Weight: .8
Pony6 v2 (DoRA)
Maybe you'll need to update your Auto1111 to version 1.9.0 or take other steps to make it work in Forge/Confy.
This is my very first attempt at creating a Dora, so it might be a bit undercooked. What are my thoughts about it?
I'm pleased with how much I can increase the weight without changing the image, just the style.
It seems to require a higher learning rate than LoKr or LoRa. I'll experiment with other datasets to test this theory, but according to the paper, this type of Lora is supposed to train faster... I don't know xD.
By the moment, I still prefer the LoKrs, but I'll try again maybe other 2 or 3 times before abandon it.
Weight: 1 - 1.6
Pony6 v1
Trigger: by alkemanubis
Weight: .8 - 1
Description
FAQ
Comments (11)
Can you please tell me is illustrious better than Pony in all aspects? Or it has some weaknesses, like pony do with bug scenes?
Illustrious lacks in their prompt flexibility. It was trained just with tags, (Pony was trained with natural language and tags). But it still can mix tags and understand some natural language concepts, but it's a little limited in that side. By the other side, Illustrious has better understanding of the tags and includes every tag available without censor them (like pony that censored a lot of tags from characters or styles). Indeed, it can make characters that just had 40 images in the danbooru dataset xd. If still needs some loras for some styles or characters, it outperforms NAIv3 in several aspects. And the limbs are much better in illustrious than in Pony. And a lot of other things. Give it a try, is a little difficult at beginning, but just check some examples.
If you're only using tags in your prompts and avoid furry and bestiality, then Illustrious is better. Actually, Noobai-XL is even better. It has insane tags knowledge, needs less steps, and works best with Euler CFG++ normal and 1-2.5 CFG range. The booru tags understanding makes up for all shortcomings in my opinion.
@daxivi3 Awesome! I always use only tags, it seems so much easier to me coz English is not my first language and tags are much better tools imo
@KonokoNice , thanks for detailed answer
Turok64 filling up the gallery? must be a popular lora for pedophiles
Must be your favorite lora then.
Sorry for flooding this section, it will happen again.
Awesome style!
This is my favourite lora on this site. Would you consider doing a future version to include his most recent artworks?
Hi, I'm not sure. Adding just a few images will not make a big difference rlly. Something that can improve it is improve my training method. I'd worked on it since the last year but is still a work in progress. Anyway I'll see if I found an updated dataset (I depend on new works being published by others ; -;)