Detalhes
Recomendado
v1.0
Glass Jaw Mix

Glass Jaw Mix

329
16
4
#horror
#Modelo Base
#Fantasia

I'm uploading this mix at the request of user 'robotfromspace' who wanted it to recreate a certain style of image that I shared awhile back.

This is a merge I did back in February on a relatively ancient version of auto1111, so those original images may be hard to recreate exactly now.

The basic style is still there though! This model may or may not be good for other purposes, there are probably better mixes for general use these days.

NOTE: To recreate this style you will also need 5 embeddings, 1 hypernetwork, and 1 (optional) LoRa. I will link to them below.

You'll also want to use my prompt and settings to get started.

Prompt: (don't question it, lol)

A 3d render of a [woman::creepy alien:8], highly detailed, 8K, stunning, hdr, subsurface scattering, global illumination, film still, Film-like, bokeh, 3d, RTX, insanely detailed, ornate pattern, fire, inferno, insect macro, ((very pose)), volumetric lighting, caustics, 512paintstyle1, Style-Glass, Style-Necromancy, eonn2

Negative prompt: neg_realism512, lowres, poorly drawn, sloppy, over , over saturated, burnt image, sloppy, broken, fuzzy, aliasing, cheap, oldschool, poor quality, pixelated, sleepy, closed-eyes

Settings:

Sampler: UniPC

Steps: 20

CFG scale: 7

Size: 512x768

Hi-res fix: 2x Latent

Denoising strength: 0.6

Clip skip: 1

VAE: vae-ft-mse-840000-ema

Required Add-ons:

512paintstyle1 by uluk

Style-Glass by theally

Style-Necromancy by theally

Neon Diffusion 500-steps by junglerally_

neg_realism512 by socalguitarist

pain_ hypernetwork by Ayoni (set to strength 0.7>

(optionally) epiNoiseoffset_v2 LoRa by epinikion (set to strength 0.7)

Merge Info:

This mix started as an add difference merge of Dreamshaper and Realistic Vision, then a 50/50 weighted sum merge with Project Cryengine. It also contains Jim Poison's eidoMode, 3dkx v2 by UNVAILai, and Noise offset for true darkness.

Feel free to share your results, I'd love to see them!

Ver tradução

Classificação e Avaliação

-- /5
0 classificação(ções)

Sem classificações ou avaliações suficientes

no-data
Sem dados
W
Conversar com o modelo
Anúncio
2024-04-02
Publicar Modelo
2023-06-26
Atualizar info do modelo
Detalhes do modelo
Tipo
Checkpoint
Tempo de Publicação
2023-06-26
Modelo básico
SD 1.5
Escopo da licença
Fonte: civitai

1. Os direitos dos modelos repostados pertencem aos criadores originais.

2. Criadores originais que desejam reivindicar seus modelos devem contatar a equipe do SeaArt AI pelos canais oficiais. Clique para reivindicar

Escopo da licença de criação
Transmissão ao vivo
Fusão
Permitir download
Licença comercial
Imagens geradas podem ser vendidas ou usadas para fins comerciais
Permitir revenda de modelos ou sua venda após a combinação
QR Code
Baixar App SeaArt
Continue sua jornada de criação com IA no celular