import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("votepurchase/RealVisXL_V4.0", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]This model is available on Mage.Space (main sponsor)
You can support me directly on Boosty - https://boosty.to/sg_161222
It's important! Read it!
The model is still in the training phase. This is not the final version and may contain artifacts and perform poorly in some cases.
The model is aimed at photorealism. Can produce sfw and nsfw images of decent quality.
CivitAI Page: https://civitai.com/models/139562/realvisxl-v40-turbo
Recommended Negative Prompt:
(face asymmetry, eyes asymmetry, deformed eyes, open mouth)
or another negative prompt
Recommended Generation Parameters:
Sampling Steps: 25+
Sampling Method: DPM++ 2M Karras
Recommended Hires Fix Parameters:
Hires steps: 10+
Upscaler: 4x-UltraSharp upscaler / or another
Denoising strength: 0.1 - 0.5
Upscale by: 1.1-2.0
- Downloads last month
- 101