Joe Penna

Some similar results here. Thank you for the help setting it up, Niko! Training set:  Best I got with traditional textual encoding:   With fine-tuning:...

Yes. You can load your ckpt into DeForum, or a similar batch img2img colab.

+1 on what @kitty7779 said. This repo automatically prunes the ckpt down to 2GB after creation (takes about 15-20 extra seconds) https://github.com/JoePenna/Dreambooth-Stable-Diffusion/ Use `main_prune.py` for that.

@binaryninja @ExponentialML absolutely, I changed every single thing I could. Including the training prompts.

# Miscellaneous `basquiat`  `picasso`  `mondrian` ![painting of sks in the style of...

A find: By removing the "photo of" from the training:  We're able to salvage some of the latent space. Here's "photograph of an apple"  As opposed to the...

@GpuLover would love to merge this in! could you resolve that conflict?