SDXL

MFCG Squish Mix v2.0

#Video Game
MFCG Squish Mix v2.0 - AI Model cover image
Przesłano
12 cze 2024, 02:10
Użycia
4.5k
Opinie
Doskonały  (1)
Kroki próbkowania

25

Metoda próbkowania

Euler a

Skala CFG

7

Uprawnienia
  • Allow image generation & sharing
  • Zezwól użytkownikom pobierać Twój model
  • Zastosowania komercyjne

Opis

As this is a merge based off PonDiffusion v6 I HIGHLY recommend you read the description of that model for information regarding prompting, tags, and baked in characters.TL;DR Generation Settings:Sampler - Euler a / Euler a SGMUniformSampling Steps - 25I upscale to 4x using this process and the upscaler below:4x_foolhardy_RemacriDimensions - 832x1216, 1216x832, or 1024x1024CFG Scale - 7 or higherOne or more passes of ADetailerSome combination of the following for faces and eyesFacesv1.2Anzhc's Face Seg PrototypeAnzhc's BeautifEYErI use the following positive and negative prompt. I DO NOT USE ANY SOURCE TAGS (source_anime, source_furry etc) :score_9, score_8_up, score_7_up, BREAK {prompt}NO NEGATIVE PROMPT OR EMBEDDINGS REQUIREDsimply prompt for what you don't want to see as it comes upSee sample images for examples.Another personal merge, meant to generate bright, cartoony, and squishy characters. Like most of my models, this is intended to produce female characters and leans towards NSFW.V2:Rebaked many underlying models and remerged with different weights. This should hopefully increase the flexibility of the model.The baked-in artist styles for PD should work, but as this is effectively a style merge, they will defeat the purpose of this model.

Pos: score_9,score_8_up,score_7_up BREAK

Komentarze

Stworzono przez MFCG Squish Mix v2.0