Train
discard-icon
vip-icon
I
Creations Number
706.7K
Favorite
1.8K
Download
2.7K
Model Source:
-
Type:
Checkpoint
Base Model:
Illustrious
Trigger Words:
License Scope:
Creative License Scope
Online Image Generation
Merge
Allow Downloads
Commercial License Scope
Sale or Commercial Use of Generated Images
Resale of Models or Their Sale After Merging
Model Parameters:
Review:
4.9

Model was trained on more actual data, but only on a small dataset of 50k images (mostly mihoyo games). With a month of experimenting and a hard reset inbetween, because of better training settings. New characters are relative weak trained in and the style merge mostly erased details of them, in which mostly the clothing suffers. It is more or less a prototype to not make the same mistakes of V2.1, that resulted in sampler problems.

better (all in compare to 2.1fix)
- Less orange looking images
- Style is overall more even torwards anime
- Model is a bit less restrictive and more expressive

worse for some
- more anime looking, which also makes backgrounds less detailed and less cohesive
- less mature looking faces
- Can be darker on some concepts (also more shadows on faces)
- Pupils are more filled out (less circle pupils)

worse
- hands
- text (model goes more towards japanese writing, when it wants to generate text, which is disjointed)

Can't say
- Loras should work better, because of a better inner style merge, with much less artifacts. But i can see that a strong style can backup loras to work better. It mostly depends of the loras itself.

2.1fix have a more 2.5d feel to it, like more details on bodys (like showing rips more often). Which also translate to backgrounds. If you like that, you can still use 2.1fix further.
If you question why i can't stay on the same qualitys of 2.1fix, its because i can't be more "reckless" in my mergin, without actual hurting the new knowledge in the model. Mergin another model in, erase every training I done on it, because all other models knowing less then my model. While every longer training on it, resets it to be like every other base model like noob or illustriuos, without style merge.

More
20 comment
D
Designer71370
めちゃくちゃいいから
03-22
View Translation
Like
Reply
D
Designer71370
綺麗ですね、とても美しい
03-21
View Translation
Like
Reply
D
Designer92270
Buenísimo, es el que más uso. Ojalá hagan mas de este tipo
02-23
View Translation
Like
Reply
G
GX05T
Holy moly this model looks better for anime than any other model I've ever seen.
02-15
View Translation
Like
Reply
N
nora
ポニーモデルのLoraを使っての生成が出来なくなっています。
01-30
View Translation
Like
Reply
N
nora
生成できなくなってませんか?
01-30
View Translation
Like
Reply
T
Tox Kasuya
nk
01-01
View Translation
Like
Reply
P
Premang Raithatha
dance
2024-12-25
View Translation
Like
Reply
avatar
Michael Galasso
(masterpiece), best quality, expressive eyes, perfect face, female, big bulge between her legs, have a huge penis under her jeans
2024-09-11
View Translation
Like
1
D
Designer19674
This is the comment section 💀
01-05
View Translation
1
Reply
avatar
Lidian
zoo
2024-07-27
View Translation
Like
Reply
1.8K
3.0K
20