Ejecutar en local
juliachang_classic.safetensors
36 MB · SafeTensor
Las descargas las sirve Civitai. Algunos creadores piden iniciar sesión en Civitai primero.
Sobre este modelo
STABLE DIFFUSION 1.5 · LoRAs
__html__Lora trained on Julia Chang from Tekkentags: juliaclassic, 1girloptional: twin braids, headband, crop top, denim skirt, feather hair ornamentmodels used:anime: CoffeeMix, PrimeMix2,5D: MeinaUnreal - V3, majicMIX fantasy - v2.0, PsyGon Animerge - v1.1, CamelliaMIx_2.5D_V2realistic: fantasticmix_real, henmix_realnegative embeddings: embedding:bad-hands-5, embedding:ng_deepnegative_v1_75t, embedding:bad-artist, embedding:EasyNegativeRecommended settings:Make sure you are aware on the usage instructions of LORAVAE: vae-ft-mse-840000-ema-pruned, kl-f8-anime2, blessed2.vae (for anime models)Sampler: DPM++ SDE Karras or DPM++ 2M KarrasSteps: 20Clipskip: 2Upscaler : img2img in comfyui using 4x-UltraMix_SmoothCFG Scale : 5 to 9 (mostly 7 and 8)LORA weight for txt2img: 0.6-1 (0.8 used in the pictures)Denoise strength for img2img: 0.4 to 0.7If you want the exact same settings, just drag and drop the picture into ComfyUIfor the pictures i used comfyui
Notas del creador
Lora trained on Julia Chang from Tekken
tags: juliaclassic, 1girl
optional: twin braids, headband, crop top, denim skirt, feather hair ornament
models used:
anime: ,
2,5D: , , ,
realistic: ,
negative embeddings: , , ,
Recommended settings:
-
Make sure you are aware on the usage instructions of LORA
-
VAE: , , (for anime models)
-
Sampler: DPM++ SDE Karras or DPM++ 2M Karras
-
Steps: 20
-
Clipskip: 2
-
Upscaler : img2img in comfyui using 4x-UltraMix_Smooth
-
CFG Scale : 5 to 9 (mostly 7 and 8)
-
LORA weight for txt2img: 0.6-1 (0.8 used in the pictures)
-
Denoise strength for img2img: 0.4 to 0.7
If you want the exact same settings, just drag and drop the picture into ComfyUI
for the pictures i used
Palabras de activación
juliaclassic
SHA256
DC87278DE4E6F862516080FEE18F3DAF1EA432E56D0A0FDBD263436E5E1F14D1
ID de modelo de ModelTrends.ai
#2658
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++ 2M Karras
Pasos
40
Guidance
16
Semilla
2880991170
Tamaño
512x768
Clip skip
2
Prompt
cinematic:1.5,from above,1 girl,studly,good,toothsome,
as juliaclassic, twin braids, headband, crop top, denim skirt, feather hair ornament,<lora:juliachang_classicV3:0.9>,
nude:0.2,,very happy smile ,teeth,show pussy,<lora:Pussy_Spread_v01:0.3>,necklace,<lora:GoodHands-beta2:1>,
ultra high quality,(sharp focus),Fujifilm, 50mm lens, F/2.8, HDR, 8k resolution, cinematic film still,reflection,<lora:epi_noiseoffset2:0.6>,
<lora:eye_size_slider_v1:-1>
<lora:curly_hair_slider_v11:0>
<lora:eyelashes_slider_v3:-2>
<lora:forehead_slider_v2:-1>
<lora:freckle_slider_v1:0.5>
<lora:time_slider_v1:0.3>,
<lora:skin_tone_slider_v1:-2>
<lora:muscle_slider_v1:0.5>
<lora:lip_slider_v21:0>
Prompt negativo
(worst quality:2),(low quality:2), (normal quality:2),lowres,pixels,blurry,(((hands on legs))):1.5, ((3d)),((monochrome)), ((grayscale)),((catoon)),
anorexic, skin distortion, (ribs), thin, skinny, hungry, chest bones, rib cage, skin bones, skindentation, scrawny, starving
sketches,logo, watermark,signature,(white letters:1),(jpeg artifacts), (( cropped head )),backlight,(morbid:1.21), (mutilated:1.4),
(bad anatomy:1.5), (bad proportions:1.5), (disfigured:1.331), fused, contorted, conjoined, deformed, caricature, body horror, mutant,(((futa))):1.5,
skin spots, acnes, skin blemishes, age spot,skin folds, asymetric eyes, asymetric face, wrinkle,skin bump, mutated hands, mutated feet,
((extra limbs)), (extra nipples:1.331),(missing limbs:1.331),(bad limbs:1.331), (fused fingers), (extra fingers:1.61051), (unclear eyes:1.331), bad hands,
missing fingers, extra digit,(((extra hands))),
easynegative,bad_prompt_version2,badhandv4, NegfeetV2
Ajustes
Sampler
DPM++ 2M Karras
Pasos
25
Guidance
7
Semilla
1702693136
Tamaño
512x768
Clip skip
1
Peso usado
0.85
Prompt
masterpiece, realistic, hyperrealistic, best quality, mature female, juliaclassic, twin braids, headband, crop top, denim skirt, feather hair ornament, looking at viewer, cowboy shot, bottom-heavy, pear-shaped, sidewalk, public park, pond
Prompt negativo
(worst quality, low quality:1.4), monochrome, blurry, missing fingers, extra digit, fewer digits, extra body parts, bad anatomy, censored, collage, logo, border, child, loli, easynegative, negative_hand, nipple
Modelos similares
Modelos de IA para generar imagen, vídeo y texto
tekken julia classic 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.
Más modelos Stable Diffusion 1.5Más LoRAs de Stable Diffusion 1.5gamingwomenanimefantasyclothingartstylestekkentekken 6
Explorar por familia de modelos
Modelos Text / LLM
411
Modelos Anima
509
Modelos Chroma
14
Modelos Flux
1,071
Modelos Flux 2 / Klein
1,237
Modelos MiniMax H3
331
Modelos Hunyuan
197
Modelos Ideogram
20
Modelos Krea2
674
Modelos Qwen
17
Modelos Qwen2
36
Modelos Ltx2
150
Modelos Stable Diffusion 1.5
6,465
Modelos Stable Diffusion XL 1.0
15,432
Modelos Zimage
804
Modelos Wan
919

Model
Trends
.ai
© ModelTrends.ai
|
Hecho en Japón
|
© 2026
