Properly baked v1.1 due soon (previewed in first 1.0 gallery image)
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
4/10/2024 Update: I've now removed the previous v1.0 as it was very overcooked and I didn't notice it at the time.
v1.1 should be more flexible, easier to generate quality headshots at the sacrifice of lower quality distance shots.
Dataset gathered and trained on a single concept, focusing on her short career.
9 hour Kohya_ss training in 15825 steps across 25 epochs @base dim (rank): 32.
1248x1248px training resolution base
Common bucketed resolutions @ 1024x1472, 1216x1216, 1472/1530x960