RayVietii-SRm3

RayVietii series Semi Realism type.

Still, not exactly for inference, but basemodel.

I did UNet for 2500+500*X steps, (without learning text encoder), where X is the iterations, to make it understood what style without specifying some sort of "trigger word", and then i merge my LoRa which based on the same art style,,my art style, but my LoRa has already learned the context and tags.

What i did is making 2 variants, base1 is having high unet_lr (6e-5)+LoRa, and base2 is lower unet_lr (2e-5)+LoRa, and then base0 is another 2e-5 without LoRa.

And next thing i did was merging these bases: base1[0.4] + base2[0.6] = base1+2.

And then base1+2 [0.8] + base0[0.2], and so on.

I did that recipe with slightly different and keep merging the variants to itself. With that, despite only have X images training, it now have pretty much broad variations.

Just like any other basemodel, it's cohesive and stable, no more SD1.5 vanilla leaking, just pure my style, and Mean Average Emergent is my method, which i assumed quite original, and no one did this.

It is expected to be murky and muddy because of this method, but it's way much efficient since i use my own art as its dataset.

Happy generating friends! :D