Downloads · 30 days
413
2% of all-time downloads
sam749/CyberRealistic-v4-2
CyberRealistic-v4-2 is a text-to-image model from sam749. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as creativeml-openrail-m.
Downloads · 30 days
413
2% of all-time downloads
All-time downloads
16.7K
Public
Parameters
860M
7.6 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors13.1 GB · 100%
From the Hugging Face model README

<p>Several features developed for CyberRealistic Classic 3.1 have been incorporated into this version along with some additional enhancements. Furthermore, the foundation of CyberRealistic has been slightly adjusted.</p><p>Most sample images use a test negative TI (which still is in development), which can be downloaded from Huggingface.</p><p><u>More explicit than earlier editions. Disregard this version if it's not what you're looking for.</u></p>
You can use this with the 🧨Diffusers library
from diffusers import StableDiffusionPipeline
import torch
model_id = "sam749/CyberRealistic-v4-2"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "masterpiece, best quality, 1girl, (colorful),(delicate eyes and face), volumatic light, ray tracing, bust shot ,extremely detailed CG unity 8k wallpaper,solo,smile"
image = pipe(prompt).images[0]
image.save("result.png")