Type | |
Stats | 237 1,267 4.9k |
Reviews | (35) |
Published | Aug 22, 2024 |
Base Model | |
Training | Steps: 930 Epochs: 10 |
Usage Tips | Clip Skip: 1 |
Trigger Words | sailor_moon |
Hash | AutoV2 D919CFE76C |
Flux LoRA model trained with 31 screen caps from the original Sailor Moon series in 640x480.
I annotated the dataset by hand, providing natural language descriptions in logical sections:
tags
lora tag
sailor_moon
style tag
classic 1990s anime
composition tag
full body shot
,portrait
,close-up portrait
,cowboy shot
,upper body shot
,hero shot
,close-up side portrait
Outfit description
recurring keywords: sailor uniform, white bodice, white top, sailor collar, red chest bow, red boots, white gloves, pleated skirt, red necklace, …
Hair description
recurring keywords: distinctive style, twin-tails, buns, bangs, long blonde hair, ponytails, …
Facial expression description
Scene and/or background description
I don't have a local flux install so I cannot really test the best epoch. I also made the mistake to let ComfyUI generate 2 of the 3 test prompts. So I only had one image to compare versions.
This is why I publish multiple epochs for you to test if you wish.