This model is based on Animagine XL 4.0, merged with my own model OstAnderMix v1.0 and SDXL models including Illustrious-XL series.
I tried to create a model that can generate 2.25D illustrations, while maintaining the ability to generate animated characters, which is a selling point of Animagine XL 4.0, as much as possible.
License: Fair AI Public License 1.0-SD
The merging process doesn't take into account the creation of NSFW works. The author personally does not recommend it.
Unauthorized reproduction of this model on other sites is prohibited.
If you would like to use my Checkpoint Online Generation, please click here.
(Translated with DeepL.com)
Recommended Setting
Steps: 25-30
CFG scale: 5-7
Sampler : Euler a
Scheduler : Normal, Simple, SGM Uniform
Use ADetailer as needed
Positive Prompt
masterpiece, high score, great score, absurdresNegative Prompt
lowres, bad ???????, bad hands, text, error, missing finger, extra digits, fewer digits, cropped, worst quality, low quality, low score, bad score, average score, signature, watermark, username, blurryDescription
v1.0
About this version
# Checkpoints
6.9527 Detail Realistic XL v7.0
8.NoobAI-XL Epsilon-Pred 1.1 Version
9.copycat-noob MR_v1.0(v-pred)
10.NoobAI-XL V-Pred-1.0 Version
used supermerger
[A]:(1) + ((2) - (3)) x 1 Adddifference (trainDifference)
[B]:((4) x 0.5 + (5) x 0.5) x 0.8 + (6) x0.2 (sum Twice)
[C]:[A] + [B] base=0 weight=GRAD_V
[D]:(2) x 0.05 + [C] x 0.95 (cosineB),
[E]:(2) + ((7) - (8)) x 0.65 (trainDifference)
[F]:[D] + ((9) - (10)) x 0.45 (trainDifference)
[G]:[D] + [F] base=0 weight=SMOOTHSTEP
FAQ
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.