Downloads · 30 days
3
0% of all-time downloads
kamillaova/epiCRealism
epiCRealism is a text-to-image model from kamillaova. 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
3
0% of all-time downloads
All-time downloads
1.2K
Public
Parameters
860M
9.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors2.7 GB · 100%
From the Hugging Face model README
![]() | ![]() |
![]() | ![]() |
![]() | ![]() |
![]() | ![]() |
Since SDXL is right around the corner, let's say it is the final version for now since I put a lot effort into it
and probably cannot do much more.
I tried to refine the understanding of the Prompts, Hands and of course the Realism.
Let's see what you guys can do with it.
Advices:
Prompt: simple explanation of the image (try first without extra keywords)
Negative: "cartoon, painting, illustration, (worst quality, low quality, normal quality:2)"
Steps: >50 (if image has errors or artefacts use higher steps)
CFG Scale: 5.0 (higher config scale can lose realism, depends on prompt, sampler and steps)
Size: 512x768 or 768x512
This model can be used just like any other Stable Diffusion model. For more information, please have a look at the Diffusers.
import torch
from diffusers import DiffusionPipeline
pipe = DiffusionPipeline.from_pretrained(
'kamillaova/epiCRealism',
torch_dtype=torch.float16
).to('cuda')
img = pipe(
prompt='positive prompt',
negative_prompt='negative prompt',
guidance_scale=5.0,
num_inference_steps=50,
width=512, height=768,
).images[0]
img.save('image.png')