nDimensional: SDXL Models
Collection
SDXL Full Parameter Fine-Tunes by nDimensional
• 9 items • Updated • 3
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("nDimensional/NatViS-Natural-Vision-Hyper-SDXL", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]
Natural Vision Hyper
Hyper Version(s) of Natural Vision
Model Info
- Base Model - NaturalVision v1.0 + SDXL Lightning
- VAE - sdxl-vae-fp16-fix
- Type - Full-parameter fine-tune, FP16
- Medium - Photorealistic, Cinematography, Photography, Generalist
- Hyper Generation Parameter Recommendations:
- Hyper with CFG:
- CFG: 6-8
- Steps:
x for x in model_name_hyper_{x}steps. - Sampler: Euler
- Schedule Type: SGM Uniform
- Hyper without CFG:
- CFG: 1
- Steps:
x for x in model_name_hyper_{x}steps. - Sampler: Euler
- Schedule Type: SGM Uniform
- Hyper with CFG:
- Recommended Generation Dimensions:
- 1344x768 (16:9) — Cinematic Film Stills
- 1536x640 (21:9) — Ultrawide Cinematic Film Stills
- 1152x896 (4:3) — Fullscreen
- 1216x832 (3:2) — Mobile landscape
- 1024x1024 (1:1) — Square
- 1024x704 (11:16)
- 768x1344 (9:16) — Tall (Instagram stories / snapchat)
- 896x1152 (3:4)
- 832x1216 (2:3) — Mobile Portrait
- 704x1024 (16:11)
Latest Version: v2.7_8step_CFG
Hyper varients of NatViS versions priror to v2.7 will be uploaded over time.
Civitai Link: NSFW WARNING
- Downloads last month
- 20
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for nDimensional/NatViS-Natural-Vision-Hyper-SDXL
Base model
stabilityai/stable-diffusion-xl-base-1.0 Finetuned
nDimensional/NatVis-Natural-Vision-SDXL