Rem / README.md
not-lain's picture
Update README.md
e255ac8
---
license: mit
---
# Description
Trainer: ChrisC
Rem from Re:zero
# How to run
```python
from diffusers import StableDiffusionPipeline
import torch
pipeline = StableDiffusionPipeline.from_single_file(
"https://huggingface.co/waifu-research-department/Rem/blob/main/rem_3k.ckpt",
).to("cuda")
pipeline.safety_checker = None # disable safety content, delete this line if you want a safe for work content
postive_prompt = "rem"
negative_prompt = ""
image = pipeline(postive_prompt,negative_prompt=negative_prompt).images[0]
```
or you can run in [colab](https://colab.research.google.com/drive/1uRc6W1xNeSie1RoeSpBemcssbZOfBZ4k?usp=sharing)
# Dataset
>Training: 22 images
>Regularization: 400 images
# Info
>rem_3k_WD1-3.ckpt
>Model Used: Waifu Diffusion 1.3
>Steps: 3000
>Keyword: Rem (Use this in the prompt)
>Class Phrase: onetruerem
>rem_3k.ckpt is based on Waifu Diffusion 1.2