La Luminette de la Nuit
Luminette, the smaller variant of the Lumina 2 checkpoint. I have torn off her tiny parts (diffusion layers) and glued together a new doll, carefully crafted her training regiment, and finally sent her to the wild.
For those who need help with metaphors:
Please, do not have high expectations. This is not the full model, but a smaller, unique one. The lite version was trained further in full precision. It was born as a playground for "knowledge transfer".
The training pipeline and the converter scripts were built from scratch.
Prior to training, data preprocessing and image alignment have been made to improve efficiency. Some of the complexity is being taken out, and the focus is on generating unique styles and features. This means that instead of trying to figure out how to draw the same thing from lots of different angles, the model can just render figures with their own distinct looks and personalities.
Please do not reupload to Huggingface, TensorArt, in the original, or in any smart compressed format. I can do it myself. Thank you.
The Lumina models keep their text encoder and vae unchanged, with only the diffusion model uploaded.
Description
Today's release was made possible by a generous donation.
I train the layers in full precision, then adjust the strength against the base checkpoint. All of the images are captioned with tags and natural language prompts, then manually verified. The thing I do differently from the Kolors checkpoint is that I focus on the subject in each image, not just reusing the downloaded gallery.
Find the angel for the downloadable workflow. Higher quality images usually appear with prompts longer than 60 tokens, you don't need a prompt generator for that.
The dataset comes from a thousand unique fashion, and a thousand more unique half-realistic anime character tags. The model doesn't reproduce them, because the training stopped at an earlier stage. This gives the model a certain style.