created by agile363274

Lora trained without triggerword.

The very basic comfy workflow + prompt is available are in the images (even if civit doesn't show it)

Lora trained on 80 range murata images at 768x, using kohya-ss/sd-scripts. The lora has been trained for 2.5k steps with TALON optimizer 6e-04 LR cosine batch size 4.

It is trained on Chroma-DC-2K, which I feel is a better model than HD.