Model
Trends
.ai
Model
Trends
.ai
los mejores modelos de IA de código abierto
Ejecutar en local
arcane_offset64dim.safetensors
70 MB · SafeTensor
Las descargas las sirve Civitai. Algunos creadores piden iniciar sesión en Civitai primero.
Sobre este modelo
STABLE DIFFUSION 1.5 · LoRAs
Creado por
Lykon
en Civitai
Arcane Style LoRA by Lykon Not to be confused with the older Arcane model, this is a new LoRA that can be combined with other base models. The model creator Lykon says he did not tag specific characters from the show, its simply an art style inspired by Arcane
Notas del creador
Arcane Style LoRA Making models can be expensive. Do you like what I do? Consider supporting me on 🅿️ or feel free to ☕ Greatest show of 2021, time to bring this style to 2023 Stable Diffusion with LoRA. This should be used with AnyLoRA (that's neutral enough) at around 1 weight for the offset version, 0.65 weight for the original one (with highres fix R-ESRGAN 0.4 denoise for better results). Trigger is arcane style but I noticed this often works even without it. Allow me to remind this is not a character LoRA (I didn't tag characters in the dataset). Still ,as you can see, it can get pretty close to the original characters with accurate prompting. This should also work with most of my character LoRA's (used Ahri and Lucy to test). Please enjoy. How to use LoRA's in auto1111: - Update webui (use git pull or redownload it) - Copy the file to stable-diffusion-webui/models/lora - Select your LoRA like in - Make sure to change the weight if needed (by default it's :1)
Palabras de activación
arcane style
997 descargas · 2,296 me gusta en Civitai
SHA256
F5E2C4A6C92C96BDB9DD41C738882CE24DBAA1EEBA7E8F677CD69062EADF26DD
ID de modelo de ModelTrends.ai
#5991
Denunciar contenido
Renders de ejemplo
Prompts y ajustes compartidos por quienes hicieron estos renders en Civitai. Elige un render para ver cómo se hizo.
Ajustes
Sampler
DPM++ SDE Karras
Pasos
20
Guidance
9
Semilla
3187489593
Tamaño
512x768
Clip skip
2
Prompt
arcane style, 1girl, arm tattoo, asymmetrical bangs, bangs, blue hair, braid, brown shirt, cloud tattoo, looking at viewer, laughing, crazy, uncontrollable laugh, mad look, night, city, green hair, long hair, midriff, pink eyes, red lips, shirt, solo, standing, tattoo, twin braids, upper body, arcane jinx, jinx \(league of legends\) <lora:arcane_offset:1>
Prompt negativo
(painting by bad-artist-anime:0.9), (painting by bad-artist:0.9), watermark, text, error, blurry, jpeg artifacts, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, artist name, (worst quality, low quality:1.4), bad anatomy
Ajustes
Sampler
Euler a
Pasos
20
Guidance
7
Semilla
3287965312
Tamaño
1536x1536
Clip skip
2
Prompt
masterpiece, best quality, arcane style, doomguy. fullbody, holding gun, fighting stance, hallway, solo, science fiction, <lora:arcane_offset64dim:1> <lora:doomguy-15:0.5>
Prompt negativo
bad-picture-chill-75v, badhandv4
Ajustes
Sampler
Euler a
Pasos
20
Guidance
7
Semilla
1856526446
Tamaño
1536x1536
Clip skip
2
Prompt
masterpiece, best quality, arcane style, doomguy. fullbody, navel, (blurry background:0.2), <lora:arcane_offset64dim:1> <lora:doomguy-15:0.5>
Prompt negativo
bad-picture-chill-75v, badhandv4, gun, holding,
Ajustes
Sampler
Euler a
Pasos
40
Guidance
7
Semilla
983700561
Tamaño
512x768
Prompt
1girl, <lora:arcane_offset64dim:0.8> arcane style, landscape of a Jungle, Fall, Wonder, CMYK Colors, stylized by Firmin Baes, Robert Vonnoh
Prompt negativo
bad-hands-5, FastNegativeV2
Ajustes
Sampler
Euler a
Pasos
40
Guidance
7
Semilla
983700556
Tamaño
512x768
Prompt
1girl, <lora:arcane_offset64dim:0.8> arcane style, portrait art by Gottfried Helnwein, photography art, Fabric art style, mundane Water color painting of a Stupid Iris, trees and Linden background, specular lighting, feminine
Prompt negativo
bad-hands-5, FastNegativeV2
Ajustes
Sampler
Euler a
Pasos
20
Guidance
7
Semilla
4157888311
Tamaño
1536x1536
Clip skip
2
Prompt
masterpiece, best quality, arcane style, doomguy. fullbody, running, fleeing, crossed legs, hallway, solo, science fiction, <lora:arcane_offset64dim:1> <lora:doomguy-15:0.5>
Prompt negativo
bad-picture-chill-75v, badhandv4
Ajustes
Sampler
Euler a
Pasos
20
Guidance
8
Semilla
3537776070
Tamaño
768x768
Clip skip
2
Prompt
masterpiece, best quality, arcane style, doomguy. fullbody, running, fleeing, crossed legs, hallway, solo, science fiction, <lora:arcane_offset64dim:1> <lora:doomguy-15:0.5>
Prompt negativo
bad-picture-chill-75v, badhandv4
Ajustes
Sampler
DPM++ 2M Karras
Pasos
25
Guidance
11
Semilla
3028757151
Tamaño
512x768
Clip skip
3
Peso usado
2
Prompt
Star Wars Ashoka tano wearing business clothes on. Smiling ((highly detailed))
Prompt negativo
Missing fingers disappearing lims
Modelos de IA para generar imagen, vídeo y texto
arcane es un LoRA para la familia Stable Diffusion 1.5 listado en ModelTrends.ai, un catálogo de solo lectura de modelos de IA de imagen, vídeo y texto de código abierto. Compáralo con otros modelos Stable Diffusion 1.5, consulta su puntuación de calor para ver su tendencia y ábrelo en PirateDiffusion o BitVector para probarlo.
Explorar por familia de modelos
Ver todos los modelos