α1.0 is better at reproducing a specific art style. In contrast, α2.0, in its pursuit of realistic depiction, has reduced its ability to replicate specific styles. This is a trade-off relationship　Let me know if you’d like me to refine the translation or adjust the nuance.

boobAI α_v1.0

リアルさを減らしオリジナルのnoobAIに近づけ絵柄を変えやすくMANGAの質感を増やしました。

Reduced realism, brought the style closer to the original NoobAI, and increased the manga-like texture to make it easier to change the art style.

リアルさを求めるならv4.0を絵柄やMANGAらしさを求めるならα1.0をおすすめします

If you’re looking for realism, we recommend v4.0. If you’re after a distinct art style or a more manga-like feel, we suggest α1.0."

boobAI v4.0

はv2.1の発展モデルです。

最も破綻が少ないです。

v2.1はv2.0の破綻を抑えたversionで、3.0は従来のboobaiを含まない新しいモデルです,

モデル毎に違う個性があるので比べて見ることおすすめします

絵柄の効きやすさ 1 > 2.1 ≧ 3.0

破綻の少なさ 3.0 ≧ 2.1 > 1

--------------------------------------------------------------------------------

NoobIEater_v3.0 ＋ T-illunai3_v2 repeatedly merged.

v2.0 +NTR MIX

--------------------------------------------------------------------------------

Recommended parameters:

Sampler: euler a

schedule: Karras

steps: 20 to 30

CFG Scale: 5 to 7

EasyReforge (Reforge + dmd2_sdxl_4ste)

<lora:dmd2_sdxl_4step:1.0>

Sampler:LCM

schedule: Karras

steps: 8

CFG Scale: 1

--------------------------------------------------------------------------------

NoobIEater_v3.0 ＋ T-illunai3_v2 merge

base_alpha=0

Weight_values=0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5

model α

NoobIEater_v3.0 ＋ T-illunai3_v2 merge

base_alpha=0

Weight_values=1,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,1,1,1

model β

model α + model β

base_alpha=0

Weight_values=0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5

boobai