alea31415's picture
Update README.md
2bce461
|
raw
history blame
1.05 kB
---
license: creativeml-openrail-m
---
Prompt with **"hutari"**
**Training details:**
- Trained with [TheLastBen's fast-DreamBooth notebook](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb)
- data set: around 20 concept images + around 50 custmized reg images, the concept images are then duplicated to balance the two
- learning rate 2e-6 for 5000 steps
- text encoder rate 15%
**Example generations:**
![3712879356-hutari](https://huggingface.co/alea31415/hutari-bocchi-the-rock/resolve/main/3712879356-hutari.png)
![170473768-beautiful](https://huggingface.co/alea31415/hutari-bocchi-the-rock/resolve/main/170473768-beautiful.png)
![4077722094-hutari](https://huggingface.co/alea31415/hutari-bocchi-the-rock/resolve/main/4077722094-hutari.png)
![925299796-beautiful](https://huggingface.co/alea31415/hutari-bocchi-the-rock/resolve/main/925299796-beautiful.png)
![3820948984-beautiful](https://huggingface.co/alea31415/hutari-bocchi-the-rock/resolve/main/3820948984-beautiful.png)