Finetuning HassanBlend1.5 update
Added 2022-12-02 23:55:09 +0000 UTCQuick update on the finetuning, I've been testing it today after a few hundred thousand steps, and although I've had some great success in some area's I've had poor success in other areas.
I'm trying to keep this as a well balanced model that can be iterated on each version and also that others can finetune whatever way they want after too. I don't think in it's current state it's balanced enough.
I want to re-edit all the captions for the images and fine tune again with some changes to the datasets, basically a second review of all my datasets and captions. This means ultimately it will take another few days or a week to get this done using RunPod.
Again the goal is to have a well balanced model not something that is particularly good at women bending over or women standing still so I appreciate your support while I go through these thousands of captions again and start the finetuning again 
When the finetuning starts on runpod, I will start training more datasets into hypernetworks and embeddings in the interim to give you something interesting because it seems the hypernetworks are popular :D
Same thing will apply, different tiers gain different rewards and when the model will be ready, the higher the tier the earlier the access.
I appreciate all your support while I polish this!
