CreamyLong
CreamyLong
> No dood, its already in there , you just need weights but theres no GUI for it here is a GUI for inpaint https://github.com/CreamyLong/stable-diffusion/blob/master/scripts/inpaint_gradio.py
There are the path of images in the txt file.
> It seems you have simply copied the code from https://github.com/CompVis/stable-diffusion and submitted a pull request. While it is acceptable to draw inspiration from other open-source projects, it is shameful...
I also use RTX 3090 but the training occupies 22G memory when the batch_size_training=1. How do you set --batch_size_training 30?
For creating your own dataset, simply dump all of your images into a directory with ".jpg", ".jpeg", or ".png" extensions. If you wish to train a class-conditional model, name the...
dog_01.jpg, dog_02.jpg......cat_01.jpg, cat_02.jpg... in one folder
No,you only need to change the name of file
The change of resolution will result in the change of latent space. However, this change does not affect the structure of Autoencoder and Unet in the diffusion. You can see...
Did you “pip install -e .” ?