Lora trained on 71 images by Inukaze.
Example Prompts:
<lora:inukaze-000005:1>, 1girl, red hair, red eyes, large breasts, leotard, rabbit ears, cleavage, standing, simple background,
<lora:inukaze-000005:1>, unknown, original, inukaze yamu, 1girl, , animal ears, bell, blue eyes, blue ribbon, blush, breasts, cleavage, closed mouth, covering nipples, detached sleeves, fox ears, fox tail, gradient background, grey background, grey hair, hair bell, hair between eyes, hair ornament, hair ribbon, jingle bell, large breasts, long sleeves, looking at viewer, medium hair, ribbon, shishimanako hareko, solo, standing, tail, tears
<lora:inukaze-000005:1>, unknown, original, inukaze yamu, 1girl, , arms behind back, bare shoulders, blush, detached sleeves, hair between eyes, looking at viewer, medium hair, parted lips, red eyes, short hair, simple background, solo, tears, white background, white hair
<lora:inukaze-000005:1>, inukaze yamu, 1girl, animal ears, black gloves, blue skirt, breasts, brown pantyhose, closed mouth, detached sleeves, fox ears, fox tail, gloves, grey eyes, grey hair, high-waist skirt, holding, holding sack, large breasts, long sleeves, looking at viewer, necktie, pantyhose, purple necktie, sack, short necktie, skirt, solo, standing, tail
Description
FAQ
Comments (2)
Please include your model training workflow if you ever get time please :)
"https://rentry.org/lora_train
https://github.com/derrian-distro/LoRA_Easy_Training_Scripts/releases/tag/installers-v1
I normally use 5_name for my folder when training image sets that have sufficient data.
upon opening run_popup.bat
I always do the following
load json config file (no)
base model I use NAI / final pruned
select your image folder
select your output folder
I dont save json (no)
regularisation (no)
continue (no)
batch size (cancel)
epoch's 4
dim (cancel)
alpha (cancel)
resolution (cancel)
rate (cancel)
encoder (cancel)
unet (cancel)
scheduler (cancel)
save epochs (yes / ok) set to 1 or press (cancel)
shuffle (no)
tokens (no)
warmup (no)
change name optional / (no)
comment (cancel)"
I now also do batch size of 2 & aprox 8 epochs with a dim size of 8
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.