---
license: creativeml-openrail-m
---

Prompt with "sarasa"

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: 111 concept images after data augmentation + a number of cusomized reg images (cannot remember)
- learning rate 2e-6 for 5000 steps
- text encoder rate 15%

Problems:

- The generated images can get blurred easily; this may be due to the use of anime screenshot
- Some cropping does not include face and this is not properly tagged, and therefore it may generate such images
- The pendant is never properly generated

Example generations (with inpainting):

![00136-1864644566-hat](https://huggingface.co/alea31415/sarasa-shinmai-renkinjutsushi/resolve/main/00136-1864644566-hat.png)
![00143-3043336834-skirt](https://huggingface.co/alea31415/sarasa-shinmai-renkinjutsushi/resolve/main/00143-3043336834-skirt.png)
![00155-1282216333-pink](https://huggingface.co/alea31415/sarasa-shinmai-renkinjutsushi/resolve/main/00155-1282216333-pink.png)
![00156-4275417758-beautiful](https://huggingface.co/alea31415/sarasa-shinmai-renkinjutsushi/resolve/main/00156-4275417758-beautiful.png)
![00159-3155561993-(sarasa](https://huggingface.co/alea31415/sarasa-shinmai-renkinjutsushi/resolve/main/00159-3155561993-(sarasa.png)
![00186-4241773092-sarasa](https://huggingface.co/alea31415/sarasa-shinmai-renkinjutsushi/resolve/main/00186-4241773092-sarasa.png)