LiquidMind Arts 111

Results 87 comments of LiquidMind Arts 111

> Hello, I will turn it off shortly. Tip: you can upload the class images to your gdrive before running the colab, then use the path to that folder in...

> * If you want a photo of a single male person, you should upload square photos of a single male person (photo dimensions : H=W eg: 512x512 or 1024x1024...

> * If you want a photo of a single male person, you should upload square photos of a single male person (photo dimensions : H=W eg: 512x512 or 1024x1024...

> The training is made on half precision, so the CKPT would behave the same if it were a full precision model. > > As long as the code is...

> > where can I find a notebook that works? > > If you want to use the old method : https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/Dreambooth/fast_DreamBooth-Old-Method.ipynb > > new method (better one) : https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb...

> If you set "contains_faces" to male, female or both, it will use a method of prior preservation, applied only on the text encoder which yields better results in my...

> one of them is 4ZEEEddie_man_08.jpg they work flawless on the OLD model and NEW, but on the NEW it does NOT looks like me, it has characteristic of me,...

> those instructions were for the old method, the new method's instruction were written in the new method cell. > > ![sdss](https://user-images.githubusercontent.com/110583491/200121474-882124bd-53d2-45fe-9797-d3064e97bd03.JPG) ok dont worry about that, seems im mixing...