Ejecutar en local
forrealxlV10_v01.safetensors
12.92 GB · SafeTensor · fp32 · full
sdxl_vae.safetensors
319 MB · SafeTensor
Las descargas las sirve Civitai. Algunos creadores piden iniciar sesión en Civitai primero.
Sobre este modelo
STABLE DIFFUSION XL 1.0 · Modelos base
For Real 1.0 by AI digital media agency. Recommendations: /sampler: k_euler or dpm2m karras /steps: 10-50 /guidance: 1-4 (as you increase the guidance, increase the steps)
Notas del creador
Hello ♥
for whatever reason you want to show me appreciation, you can: ❤️❤️
Special Thanks to
Please take a look at their amazing work!
Update v1.0:
if you see when V0.5 was released, you can imagine how hard it was for me to create a better version that is really better in all areas.
This is the result of probably 100 different versions.
-
more Details
-
better colors at low cfg
-
better faces (and more variance) (not perfect)
For people and faces, you should not use DDPM. Use DPM++ 3M SDE or Euler
Update v0.5:
Small improvements
- better skin, teeth and eyes in humans
- more details
I am still working on the following improvements
- deformed faces / displaced eyes
- faces from a distance
- xxx
Update v0.3:
It's just a small update to fix some issues from v0.1.
It doesn't change every subject, but some improve.
I haven't had a picture in about 1000 pictures where v0.3 wasn't better, so the upgrade is definitely worth it.
I can notice the following improvements:
-
a bit sharper
-
more realistic
-
a bit more creative
-
a bit more possibilities to get nicer hands/faces on full body photos
________________________________________________________________________________
This is a merge of the following Models:
Recommended Settings:
Sampling Method: DDPM (my absolute favorite), Euler, DPM ++ 3M SDE
Sampling Steps: 10 (more very rarely make a difference.)
CFG Scale: 1-4 (lower, more realistic, i prefer 1-1.8)
Upscaler: SwinIR _4x (this is my all time favorite)
(Hires steps: 15; Denoise: 0.28, upscale by 1.5 - 4 (depends on your GPU))
📌 USE
All Images generated in SD Forge with Nvidia RTX 4090
Please test other Settings and share with the communty, so i will learn about the Settings and can optimize.
Recommended Loras:
Please experiment with the weights. Loras are really gamechanging in this Model!
TESTS
Here you can find and download my tests:
Thank you so much for using this Model. Hope you are get insane results and create some BANGERZ ♥
SHA256
91CE21E3FD2EB843D634B1EA4BD533CA283489F5E41B5793BCD4A0F44C1002D4
ID de modelo de ModelTrends.ai
#2749
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
DDPM
Pasos
13
Guidance
2
Semilla
2881538660
Tamaño
540x960
Clip skip
2
Prompt
A classic oil painting depicting a group of cats dressed in formal attire, attending a fancy dinner party and discussing the latest catnip gossip.
(masterpiece, award winning artwork)
many details, extreme detailed, full of details,
Wide range of colors, high Dynamic
<lora:MJ52:0.21>
<lora:SDXLFaeTastic2400:0.25> <lora:add-detail-xl:0.9> <lora:xl_more_art-full_v1:0.53>
Prompt negativo
bad quality, blurry
Ajustes
Sampler
DDPM
Pasos
10
Guidance
2
Semilla
2916612244
Tamaño
850x1280
Clip skip
2
Prompt
landscape of a Asmara and Homey Heisei Era Poppy field, Serene and Tropical, at Dawn, Princecore, Light and shadow plays, Calotype, epic, theatrical, complex, intricate artistic color, pure, background inspired, epic composition, perfect background, beautiful detailed, rich deep colors, holy Absurdres, ultra realistic, professional lightning
many details, extreme detailed, full of details,
Wide range of colors., Dramatic,Dynamic,Cinematic,Sharp details
Insane quality. Insane resolution. Insane details. Masterpiece. 32k resolution.
Prompt negativo
bad quality, blurry, worst quality
Ajustes
Sampler
DDPM
Pasos
10
Guidance
2
Semilla
1885815419
Tamaño
850x1280
Clip skip
2
Prompt
A frog wearing a crown and sitting on a makeshift throne of lily pads, with the caption: "When you're the ruler of the pond and it's time to dispense some royal decrees." Absurdres, ultra realistic, professional lightning
many details, extreme detailed, full of details,
Wide range of colors., Dramatic,Dynamic,Cinematic,Sharp details
Insane quality. Insane resolution. Insane details. Masterpiece. 32k resolution.
<lora:xl_more_art-full_v1:0.3> <lora:WildcardX-XL-Detail-Enhancer:0.8> <lora:ral-vlntxplzn:0.4> ral-vlntxplzn <lora:ral-pxlprtcl:0.25> ral-pxlprtcl <lora:MJ52:0.3>
Prompt negativo
bad quality, blurry, worst quality
Ajustes
Sampler
Euler
Pasos
18
Guidance
2
Semilla
2662250548
Tamaño
540x960
Clip skip
2
Prompt
stained glass style a slumbering dreamweaver reclines upon a moss covered islet, surrounded by a halo of soft luminescence that seeps from the wispy tendrils of fog curling around its form like a gentle lover's caress. the dreamer's eyes are half closed, their gaze drifting lazily towards the surface of a glassy lake, where ripples of gold and copper disturb the otherwise perfect reflection of the mist shrouded peaks rising in the distance. as the dreamweaver's hand darts across the water, a scattering of moon petaled flowers floats to the surface, releasing their sweet fragrance into the still air, while a office of silver tailed fish weave through the depths, their gentle splashing creating a soothing melody that seems to harmonize with the dreamer's very breath. . vibrant, beautiful, translucent, intricate, detailed
many details, extreme detailed, full of details,
Wide range of colors., Dramatic,Dynamic,Cinematic,Sharp details
Insane quality. Insane resolution. Insane details. Masterpiece. 32k resolution.
<lora:add-detail-xl:0.95> <lora:dvr-lnds-sdxl:0.3> dvr-lnds-sdxl <lora:MJ52:0.25> <lora:ral-apoctvisn-sdxl:0.3> ral-apoctvisn <lora:zavy-cntrst-sdxl:0.35> dark, chiaroscuro, low-key <lora:zavy-rmlght-sdxl:0.41> zavy-rmlght <lora:SDXLFaeTastic2400:0.225>
Prompt negativo
grotesque, unsightly, misshapen, deformed, mangled, awkward, distorted, twisted, contorted, misshapen, lopsided, malformed, asymmetrical, irregular, unnatural, botched, mangled, mutilated, disfigured, unsightly, ugly, repulsive, revolting, ghastly, hideous, unappealing, terrible, awful, frightful, odious, loathsome, revolting, obnoxious, detestable, hateful, repugnant, sickening, vile, abhorrent, contemptible, execrable, loathsome, detestable, repellent, disgusting, revolting, loathsome, distasteful, abominable, ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, extra limbs, disfigured, deformed, body out of frame, blurry, bad anatomy, blurred, watermark, grainy, signature, cut off, draft, amateur, multiple, gross, weird, uneven, furnishing, decorating, decoration, furniture, text, poor, low, basic, worst, unprofessional, failure, crayon, oil, label, thousand (hands:1.1), , straight stitch, monochromatic, plain, unpatterned
Ajustes
Sampler
DDPM
Pasos
150
Guidance
1.5
Semilla
2278193149
Tamaño
540x960
Clip skip
2
Prompt
Insane detailed 8-bit logo of a piece of cheesecake, white background, black outline, game design pixel art style
Wallpaper, Movie Style, cinematic Scene, Cinematic Lightning,
Wide range of colors., Dramatic,Dynamic,Cinematic,Sharp details
Insane quality. Insane resolution. Insane details. Masterpiece. 32k resolution.
<lora:add-detail-xl:0.9> <lora:MJ52:0.1> <lora:ral-apoctvisn-sdxl:0.2> <lora:zavy-cntrst-sdxl:0.45>
<lora:xl_more_art-full_v1:0.5> <lora:SDXLFaeTastic2400:0.5>
Prompt negativo
low detailed, deformed iris, deformed pupils, jpeg artifacts, ugly, duplicate, morbid, mutilated, too many fingers , mutated hands, poorly drawn hands, mutation, deformed, bad anatomy, bad proportions, extra limbs, cloned face, malformed limbs, extra arms, extra legs, fused fingers, text, signature, watermark, logo, autograph, trademark, cut off, censored, inaccurate body, inaccurate face, bad teeth, deformities, (boring, uninteresting:1.1)
Ajustes
Sampler
DDPM
Pasos
20
Guidance
2
Semilla
1378413741
Tamaño
540x960
Clip skip
2
Prompt
Lego batman ral-drp <lora:ral-drp:0.7>
many details, extreme detailed, full of details,
Wide range of colors., Dramatic,Dynamic,Cinematic,Sharp details
Insane quality. Insane resolution. Insane details. Masterpiece. 32k resolution.
<lora:ParchartXL_CODA:0.95> on parchment
<lora:add-detail-xl:1>
Ajustes
Sampler
DDPM
Pasos
18
Guidance
1.5
Semilla
926130783
Tamaño
540x960
Clip skip
2
Prompt
Act like you're watering a garden of giant mushrooms with a watering can the size of a house.
full body portrait
majestetic
(masterpiece, award winning artwork)
many details, extreme detailed, full of details,
Wide range of colors, high Dynamic
<lora:dvr-bzz:1> (dvr-bzz:1.1) buzz
<lora:xl_more_art-full_v1:0.3>
<lora:MJ52:0.28>
<lora:dvr-lnds-sdxl:0.25> dvr-lnds-sdxl
<lora:ral-decoznow:0.22> ral-decoznow
<lora:sss:1> sss, translucent, subsurface, scattering
<lora:add-detail-xl:1>
Prompt negativo
(phone, iphone, holding phone, holding iphone:1.2), bad quality, blurry
Ajustes
Sampler
DDPM
Pasos
15
Guidance
2
Semilla
3995355743
Tamaño
512x768
Clip skip
2
Prompt
A toaster popping out toast with a surprised expression, captioned: "When you're just trying to make breakfast, but life keeps toasting you."
many details, extreme detailed, full of details,
Wide range of colors. Insane quality. Insane resolution. Insane details. Masterpiece. 32k resolution.
<lora:MJ52:0.18>
<lora:xl_more_art-full_v1:0.35>
<lora:ral-cltc:0.1> ral-cltc <lora:ral-anmwrlds-sdxl:0.3> ral-anmwrlds <lora:SDXLFaeTastic2400:0.2> <lora:WildcardX-XL-Detail-Enhancer:0.5> <lora:zavy-mthcl-sdxl:0.2>
<lora:ral-dissolve:0.25> ral-dissolve <lora:ral-porcelain:0.4> ral-porcelain
Prompt negativo
deformed face, bad hands, bad face, deformed,
Modelos similares
Modelos de IA para generar imagen, vídeo y texto
forreal01 xl es un modelo base para la familia Stable Diffusion XL 1.0 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 XL 1.0, consulta su puntuación de calor para ver su tendencia y ábrelo en PirateDiffusion o BitVector para probarlo.
Más modelos Stable Diffusion XL 1.0Más Modelos base de Stable Diffusion XL 1.0fantasyrealisticbaselowstepsrealisitcsfwwomandetailed
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