Model
Trends
.ai
Model
Trends
.ai
les meilleurs modèles d'IA open source
Exécuter en local
cyberrealisticXL_v20.safetensors
6.46 GB · SafeTensor · fp16 · pruned
Les téléchargements sont servis par Civitai. Certains créateurs demandent d'abord une connexion à Civitai.
AD
<cyberreal2-xl>
À propos de ce modèle
STABLE DIFFUSION XL 1.0 · Modèles de base
Créé par
Cyberdelia
sur Civitai
Notes du créateur
Join The Tinkerer on Whop. Membership gets you early releases, private tools and a bunch of extra stuff. 👉 💬 This is the model you reach for when you want super clean, photo-realistic results. It’s sharp, powerful, and somehow just nails gorgeous images every single time. ⚙️ Recommended Settings Sampling method: DPM++ 2M SDE Karras VAE: is already Baked In Sampling steps: 30+ Steps Resolution: 832x1216 / 896x1152 CFG: 3-5 Clip Skip: 1 Upscale: 1.5 upscale (0.3 - 0.35 denoise) Upscalers: 4x_NickelbackFS_72000_G / 4x_foolhardy_Remacri / 4x_NMKD-Siax_200k ⚙️ Recommended Settings DMD2 Sampler: LCM Schedule Type: Exponential Sampling Steps: 8/12 (12 for extra detail) CFG Scale: 1-1.5 ⚡ These settings are not the same as the standard SDXL workflow — be sure to adjust your pipeline! 💡 What’s the difference between FP16 and FP32 checkpoints? FP16 (half precision) uses 16-bit floating-point weights. It’s smaller in size, loads faster, and uses less VRAM - perfect for normal image generation. You won’t notice any visual difference for inference, so it’s ideal for everyday use. FP32 (full precision) uses 32-bit weights, which means it’s larger and heavier on resources. It doesn’t improve generation quality, but it’s better if you’re training, merging, or fine-tuning models, since it keeps the exact weight data without rounding loss. 🧠 Prompting Example negative prompt: cartoon, illustration, anime, painting, CGI, 3D render, low quality, watermark, logo, label or use ✨ Optional Adetailer Adetailer model: face_yolov9c.pt If you only want the main face being refined set 'Mask only the top k largest' to 1. 🔗 Links Backup location: ☕ Fuel the Project If this model gave you stellar results, . Or two. Or, you know… a GPU. ⚠️ Heads-Up This model can make mature or sensitive content. You’re fully responsible for what you create, so use it responsibly (or if you can’t resist, at least be artistically irresponsible). 💬 Want Better Prompts? Use this custom ChatGPT to auto-generate polished prompts for CyberRealistic XL: 🔗 []
5,095 téléchargements · 302 j'aime sur Civitai
SHA256
63FDB4849CB41A19B3DCA595F48CDB107C71CC8B98D756200B133826191F14FA
ID de modèle ModelTrends.ai
#10296
Signaler le contenu
Rendus d'exemple
Prompts et réglages partagés par les personnes qui ont réalisé ces rendus sur Civitai. Choisissez un rendu pour voir comment il a été fait.
Réglages
Sampler
Euler a
Étapes
32
Guidance
7
Seed
3542878920
Taille
816x1024
Prompt
cute baby otter wearing a comically ill-fitting striped fuzzy-bumblebee costume, large round clear glasses with wire frame, (holding sign with text:"fix buzz PLZ":1.4 ), <lora:text2:1.25>, standing on the sidewalk of a busy city, small jar of boney buy his feet,
Réglages
Sampler
DPM++ 3M SDE
Étapes
30
Guidance
7
Seed
456972836
Taille
768x1024
Prompt
1girl,mysterious girl with freckles,an exotic girl in off-shoulder sweater,fading backlit background,pastel colors,alluring goddess,amazing depth,double exposure,surreal,geometric patterns,intricately detailed,bokeh,perfect balanced,deep fine borders,artistic photorealism,smooth
Prompt négatif
(worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art:1.4)
Réglages
Sampler
DPM++ 2M
Étapes
30
Guidance
7
Seed
740565827
Taille
768x1024
Prompt
a beautiful college girl, brunette, close-up, girl next door, baggy clothes, night, interior, messy hair, film grain, retro, (bokeh:1.3), Porta 160 color, shot on ARRI ALEXA 65, sharp focus on subject, Fujifilm XT-3
Prompt négatif
(worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art:1.4)
Réglages
Sampler
DPM++ 2M
Étapes
30
Guidance
7
Seed
1517725810
Taille
768x1024
Prompt
Create a captivating story or description inspired by this photo of a busty smiling Yupik woman with brown messy hairbun, cleavage and subtle freckles and gray-brown eyes. She gazes innocently from the side towards the camera, sitting in a cozy gaming room at a desktop computer, hair bangs forehead fringe and a a wooly knitted full bodysuit with yellow/blue pop-art print, very detailed, atmospheric haze, Film grain, cinematic film still, shallow depth of field, highly detailed, high budget, cinemascope, moody, epic, OverallDetail, gorgeous, 2000s vintage RAW photo, photorealistic, candid camera, color graded cinematic, eye catchlights, atmospheric lighting, skin pores, imperfections, natural, shallow dof
Prompt négatif
(worst quality, low quality, normal quality, lowres, low details, grayscale, bw)
Réglages
Sampler
DPM++ 2M
Étapes
40
Guidance
7
Seed
61808643
Taille
768x1024
Prompt
beautiful girl, smile, happy, close up, (detailed eyes:0.8), (looking at the camera:1.4), interior, (ginger hair:1.3), dark studio, muted colors, freckles
Prompt négatif
(worst quality, low quality, normal quality, lowres, low details, grayscale, bw), (bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs, deformities:1.3)
Réglages
Sampler
DPM++ 2M
Étapes
30
Guidance
7
Seed
1951034651
Taille
768x1024
Prompt
(Soft Lighting Photography by Mimoza Veliu and Mario Giacomelli:1.2), portrait, upper body, close up, cute woman, beautiful, 20 years old, green eyes, (black bold eyeliner, makeup:1.3), freckles, soft smile, shoulder length ginger hair at side, ear, see through loose blouse, cleavage, kneeling, living room, knee high socks, petite body, beautiful legs, realistic soft skin, looking at viewer
Prompt négatif
(worst quality, low quality, normal quality, lowres, low details, grayscale, bw), (bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs, deformities:1.3)
Réglages
Sampler
DPM++ 2M
Étapes
30
Guidance
5.5
Seed
3642796036
Taille
768x1024
Prompt
gritty raw street photography, plain clean earthy young female hacker, short skirt, pantyhose, black boots, matrix punk clothing, sitting, with neon lighting from shop signs
Prompt négatif
(worst quality, low quality, normal quality, lowres, low details, grayscale, bw)
Réglages
Sampler
DPM++ 2M
Étapes
35
Guidance
7
Seed
1051505092
Taille
768x1024
Prompt
(photography,realistic:1.4), 23yo ,female,black hair,smart looking,maldivian,classroom looking out of window,cinematic lighting,Highly detailed eyes, highly detailed face, brown eyes,freckles,glasses,smiling
Prompt négatif
(worst quality, low quality, normal quality, lowres, low details, grayscale, bw), (bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs, deformities:1.3)
Modèles d'IA pour générer image, vidéo et texte
cyberreal2 xl est un modèle de base pour la famille Stable Diffusion XL 1.0, référencé sur ModelTrends.ai, un catalogue en lecture seule de modèles d'IA open source pour l'image, la vidéo et le texte. Comparez-le aux autres modèles Stable Diffusion XL 1.0, consultez son score de chaleur pour suivre sa tendance et ouvrez-le sur PirateDiffusion ou BitVector pour l'essayer.
Parcourir par famille de modèles
Voir tous les modèles