Posted for civitai.com and tensor.art only
Each of these LoRAs take me dozens of hours and GPU usage out of pocket. Every review is appreciated and encourages me to do more of these.
-MoC
See about this version for model details 👉
Description
Dataset gathered and trained on a single concept (model had a relatively short active career period).
~14.5 hour Kohya_ss training in 32.028 steps across 34 epochs @base dim (rank): 32.
1248x1248px training resolution base
Used a wide variety of resolutions in training data, however by far the most common bucketed resolution was @ 1216x1216px.
You may find on some shots you need to use a higher strength.
Please note the trigger word