Angel of Death - SDXL
Palabras Clave y Etiquetas Relacionadas
Prompts Recomendados
score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, score_anime, score_realstic
UHD, 4k, ultra detailed, cinematic, a photograph of Grim Reaper a person in a hoodie with a skull on his face, horror movie themed, sharp, detailed, epic photography, artistic, creative, dramatic light, cinematic style, film style, Grim Reaper style, solo, simple background, 1boy, monochrome, greyscale, male focus, teeth, hood, from side, profile, mask, black background, hood up, upper body, skull mask, epic, beautiful lighting, inpsiring
Prompts Negativos Recomendados
(EasyNegative:0.8), (worst quality, low quality:1.2), blurry, bokeh, dof, fog
easynegative, civit_nsfw, 3d, safe_neg, rendering, bad eyes, shadowed eyes, cross, bad anatomy, score_4, score_5, score_6, signature, patreon, censored, deformed fingers, sweat, fused fingers, lipstick, flat chest, water, anime
Parámetros Recomendados
samplers
steps
cfg
clip skip
resolution
vae
Parámetros Recomendados de Alta Resolución
upscaler
steps
Consejos
Use danbooru tagging for prompts
Don't use a lot negative embeddings at the same time to avoid ruining outputs.
If using negative embeddings, use one for quality and optionally one for hands as placebo.
Patrocinadores del Creador
EasyNegative embedding recommended to improve output quality, best used at 0.8 weight.
Introduction:
The "Angle of Death" Model is inspired by the reality of life, which is death. This Model is trained on SDXL / Pony, This is a SFW Model, Any Kind of NSFW is strictly Not Allowed.
A Quote by me Shido :
Its not the darkness i fear, but light that deceives. For in darkness lies the truth of life, while light shines bright with glory of false life.
Recommendations Model :
Perfect pony
AAM XL (Anime Mix)
Note : Can use Any SDXL model with recommended hires. For Anime kind of Art I recommend Perfect Pony or AAM XL(Anime).
Recommendations :
Use danbooru tagging for prompts
Sampler: "Euler a" at / 25 steps
Cfg scale: 6.5
Clip Skip: 2 <---- VERY IMPORTANT
VAE : sdxl_vae
Add Before Prompt :
score_9,score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, score_anime, score_realsticNegatives:
(EasyNegative:0.8), (worst quality, low quality:1.2), blurry, bokeh, dof, fog
Recommendations (Hires Fix):
Upscaler: latent
Hires steps: 10-15
Denoising strength: 0.45
Upscale by: 1.2
If you want to get mostly the same results, you definitely will need negative embedding:
EasyNegative, it's better to use it at 0.8 weight.
Don't use a lot negative embeddings at the same time. It definitely will ruin any possible output on all models! If you want to use negative embeddings - use one for quality, and one for hands (if you want a placebo for hands).
Detalles del Modelo
Tipo de modelo
Modelo base
Versión del modelo
Hash del modelo
Discusión
Por favor log in para dejar un comentario.



