Ok first off, this is a first release and so it is highly experimental. I have held off releasing to now until i get something resembling a decent model.
With automatic1111 i have taken the existing mega model which is now at 4800 checkpoints merged and branched the effort to now include adding many of the 1000s of LORA models that are now available by using the supermerger extension and through some trial and error i have my first version of this new development pathway. It is decent, it isnt perfect, but after starting i found it kind of broke the model in the first few hundred merges, but over time it has slowly been almost developing its own art style which seems to be getting better all the time.
So feedback, dont expect perfection, the next version will be once i see where yet more merging takes us. I am using cosmine A merging in supermerger as after doing some reading and the documentation is very limited, they seem to have developed a much closer to lossless merging method. Different from the basic merge a/b = c as i was doing before. there will be some color blotches in some images, this is much better than it was from 500-800 LORA. The fine details are picking up as are more variety of outputs as i go along. Questions are welcome. so please try this out, fully experimental, see what u can do with it and feedback is welcomed
More random artstyles added, less anime more realism compared to the last version.
Backgrounds seem to be the main improvement here, less generic and more variety to backdrops especially in landscapes, and a few minor art styles (line art, portraits, pastels and other niche styles occasionally pop up)
If you like surprises and randomness but still pretty close to prompting this one might be worth a shot. if you want anime rich 1.9 thr 1.7 might be closer to the mark.
Still working on mass merging so by no means finished, into the 2.x series now.
Feedback welcome, this remains HIGHLY EXPERIMENTAL but compared to early versions it is much more stable nowdays
