Sign In

Djeeta | Granblue Fantasy

569
4.0k
17
Verified:
SafeTensor
Type
LoRA
Stats
2,811
Reviews
Published
May 7, 2023
Base Model
SD 1.5
Training
Steps: 4,000
Epochs: 10
Trigger Words
djeeta
blonde hair
brown eyes
djeetadef, hairband, armor, pink dress, bow, pink skirt, thigh boots, gauntlets
djeetaidol, blue hair bow, short dress, puffy short sleeves, layered skirt, white gloves
djeetasage, hair flower, rabbit ears, leotard, wrist cuffs, cape, white thighhighs
djeetachunli, double bun, chinese clothes, china dress, puffy sleeves, pelvic curtain, brown pantyhose, spikes
djeetasummer, hairband, white one-piece swimsuit
djeetawolf, wolf costume, bandeau
djeetaego, pale skin, white hair, red eyes, crop top, sleeveless, black skirt, choker
Hash
AutoV2
EAA2C79601
The Hourglass
justTNP's Avatar
justTNP

Requests have been put on hold.

Your characters may have insufficient training data! Click here.

v2.0

Weight: 1.0

Trigger + Appearance: djeeta, blonde hair, brown eyes

Default Outfit: djeetadef, hairband, armor, pink dress, bow, pink skirt, thigh boots, gauntlets

Kimi to Boku no Mirai: djeetaidol, blue hair bow, short dress, puffy short sleeves, layered skirt, white gloves

Sage: djeetasage, hair flower, rabbit ears, leotard, wrist cuffs, cape, white thighhighs

Street Fighter: djeetachunli, double bun, chinese clothes, china dress, puffy sleeves, pelvic curtain, brown pantyhose, spikes

Summer Outfit: djeetasummer, hairband, white one-piece swimsuit

Wolf Costume: djeetawolf, wolf costume, bandeau

Alter Ego: djeetaego, pale skin, white hair, red eyes, crop top, sleeveless, black skirt, choker

Add and adjust descriptor tags if necessary.

v1.0

Weight: 1.0

Trigger + Appearance: djeeta \(granblue fantasy\), pink hairband

Default Outfit: dress, thigh boots

Add blonde hair and brown eyes if necessary.

Currently working on adding more outfits, but for now you'll get her default outfit.

The results of your generations are dependent on the additional LoRAs, weights, and models you use, so it may not work or come out as consistent as my sample images. Other reasons may include me using xformers, token merging, and a modified DPM++ 2M Karras sampler.