epicrealismxl / README.md
nroggendorff's picture
Update README.md
2451025 verified
metadata
library_name: diffusers
license: mit

epiCRealism XL Model Card

epiCRealism Diffusion XL is a latent text-to-image diffusion model capable of generating images of people, mainly, and other things. For more information about how Stable Diffusion functions, please have a look at 🤗's Stable Diffusion blog.

You can use this with the 🧨Diffusers library from Hugging Face.

So pretty, right?

Diffusers

from diffusers import StableDiffusionXLPipeline
import torch

pipeline = StableDiffusionXLPipeline.from_pretrained("nroggendorff/epicrealismxl").to("cuda")

image = pipeline(prompt="a girl standing in the rain").images[0]
image.save("not.png")

Model Details

  • train_batch_size: 1
  • gradient_accumulation_steps: 4
  • learning_rate: 1e-2
  • lr_warmup_steps: 500
  • mixed_precision: "fp16"
  • eval_metric: "mean_squared_error"

Limitations

  • The model does not achieve perfect photorealism
  • The model cannot render legible text

Developed by

  • Noa Linden Roggendorff

This model card was written by Noa Roggendorff and is based on the Stable Diffusion v1-5 Model Card.