RealityVision_SDXL - v2.0
Prompts recommandés
8k uhd,dslr,high quality,film grain,uhd,dslr,best quality,professional photography,cinema,ultra realistic,outdoor,film camera,dslr,lens flare,super-resolution,(16k),uhd,realistic,ultra realistic,ultra quality,film look
raw photo, 8k uhd, dslr, soft lighting, high quality, film grain, Hyperrealismus hyperrealistic, detailed face, realistic eyes, European face
Prompts négatifs recommandés
Low-quality, asian, blurred, jpeg artifacts, cropped image, out of shot, cartoon, cg, comic, drawing, bad art, bad artist, bad fan art, cgi, grainy, kitsch, lazy art, less creative, lowres, noise, bad composition, mutated body parts, blurry image, disfigured, bad anatomy, deformed body features, double head, double figure, double body, extra fingers, mutated
low-quality, Asian, blurred, jpeg artifacts, cropped image, out of shot, cartoon, cg, comic, drawing, bad art, bad artist, bad fan art, CGI, grainy, kitsch, lazy art, less creative, lowres, noise, bad composition, mutated body parts, blurry image, disfigured, bad anatomy, deformed body features, double head, double figure, double body, extra fingers, mutated hands, poorly drawn hands, mutation, deformed, dehydrated, bad proportions, extra limbs, cloned face, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, disconnected head, malformed hands, huge calf, fused hand, disappearing arms, disappearing thigh, disappearing calf, disappearing legs, abnormal eye proportion, Abnormal legs
Paramètres recommandés
samplers
steps
cfg
resolution
vae
Paramètres haute résolution recommandés
denoising strength
Conseils
Do not use the SDXL refiner with RealityVision_SDXL as it reduces output quality.
The model prefers simple prompts and does most of the scene building automatically.
Follow the author on Instagram and provide feedback to help future revisions.
Sponsors du créateur
RealityVision_SDXL
Welcome to RealityVision_SDXL, a stable diffusion model (SDXL) that has been lightly trained and further refined with community LORAs to achieve its current state.
- Training Images: +300 - Training Steps: +44280RealityVision_SDXL has been meticulously crafted and biased to generate photorealistic output that is perfectly stylized for social media posting! 📸
RealityVision_SDXL excels in maintaining coherency and avoids the peculiar body issues and biases that are starting to affect some of the other photorealistic models. Moreover, RealityVision_SDXL is capable of producing images with rich deep blacks, making it ideal for creating stunning evening or nighttime scenes. It can also produce incredibly bright output!
RealityVision_SDXL is capable of both SFW and NSFW output. Like all of our other models, tools, and embeddings, RealityVision_SDXL is user-friendly, preferring simple prompts and allowing the model to do the heavy lifting for scene building.
Note
This version includes a baked VAE, so there’s no need to download or use the “suggested” external VAE.
Warning
DO NOT USE SDXL REFINER WITH REALITYVISION_SDXL
The SDXL refiner is incompatible and you will experience reduced quality output if you attempt to use the base model refiner with RealityVision_SDXL.
Follow us here by clicking the heart ❤️ and liking the model 👍, and you will be notified of any future versions we release. We also need your help with feedback, please post your images and your honest feedback below. We will use your feedback and your output to help guide future revisions! 🙏
Positive prompt:
8k uhd,dslr,high quality,film grain,uhd,dslr,best quality,professional photography,cinema,ultra realistic,outdoor,film camera,dslr,lens flare,super-resolution,(16k),uhd,realistic,ultra realistic,ultra quality,film look,Negative prompt:
Low-quality, asian, blurred, jpeg artifacts, cropped image, out of shot, cartoon, cg, comic, drawing, bad art, bad artist, bad fan art, cgi, grainy, kitsch, lazy art, less creative, lowres, noise, bad composition, mutated body parts, blurry image, disfigured, bad anatomy, deformed body features, double head, double figure, double body, extra fingers, mutatedContributeur
Détails du modèle
Type de modèle
Modèle de base
Version du modèle
Hash du modèle
Créateur
Discussion
Veuillez vous log in pour laisser un commentaire.