Instructions to use ModelsLab/RealVisXL_V5.0_Lightning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ModelsLab/RealVisXL_V5.0_Lightning with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ModelsLab/RealVisXL_V5.0_Lightning", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
license: openrail++
Check my exclusive models on Mage: ParagonXL / NovaXL / NovaXL Lightning / NovaXL V2 / NovaXL Pony / NovaXL Pony Lightning / RealDreamXL / RealDreamXL Lightning
This model is available on Mage.Space (main sponsor)You can support me directly on Boosty - https://boosty.to/sg_161222
The model is aimed at photorealism. Can produce sfw and nsfw images of decent quality.
CivitAI Page: https://civitai.com/models/139562/realvisxl-v50
Recommended Negative Prompt:
(octane render, render, drawing, anime, bad photo, bad photography:1.3), (worst quality, low quality, blurry:1.2), (bad teeth, deformed teeth, deformed lips), (bad anatomy, bad proportions:1.1), (deformed iris, deformed pupils), (deformed eyes, bad eyes), (deformed face, ugly face, bad face), (deformed hands, bad hands, fused fingers), morbid, mutilated, mutation, disfigured
or another negative prompt
Recommended Generation Parameters:
Sampling Steps: 5
Sampling Method: DPM++ SDE Karras / DPM++ SDE
CFG Scale: 1.0-2.0
Recommended Hires Fix Parameters:
Hires steps: 3
Upscaler: 4x-NMKD-Superscale-SP_178000_G / 4x-UltraSharp upscaler / or another
Denoising strength: 0.5
Upscale by: 1.1-1.5