--- license: creativeml-openrail-m --- Prompt with **"francat"** **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: 225 concept images + 224 custmized reg images - learning rate 2e-6 for 5500 steps - text encoder rate 15% **Problems:** - The generated images can get blurred easily is often quite dark, especially when anime screenshot is specified. - Cannot get the clothes and the sword properly. This may require tagging the clothes separately. - The model can never put the cat tail at the right position. **Example generations (with inpainting):** ![00013-1296443511](https://huggingface.co/alea31415/fran-tenken/resolve/main/00013-1296443511.png) ![00014-1854085158](https://huggingface.co/alea31415/fran-tenken/resolve/main/00014-1854085158.png) ![00018-3256134196](https://huggingface.co/alea31415/fran-tenken/resolve/main/00018-3256134196.png) ![00049-3570819184](https://huggingface.co/alea31415/fran-tenken/resolve/main/00049-3570819184.png) ![00050-632977591](https://huggingface.co/alea31415/fran-tenken/resolve/main/00050-632977591.png) ![00057-758575380](https://huggingface.co/alea31415/fran-tenken/resolve/main/00057-758575380.png) ![00068-3383662237-beautiful](https://huggingface.co/alea31415/fran-tenken/resolve/main/00068-3383662237-beautiful.png) ![00069-2702000739-anime](https://huggingface.co/alea31415/fran-tenken/resolve/main/00069-2702000739-anime.png) ![00073-1621079570-beautiful](https://huggingface.co/alea31415/fran-tenken/resolve/main/00073-1621079570-beautiful.png) ![00036-1595297284](https://huggingface.co/alea31415/fran-tenken/resolve/main/00036-1595297284.png)