Type | |
Stats | 470 |
Reviews | (7) |
Published | Aug 29, 2023 |
Base Model | |
Training | Steps: 418 Epochs: 11 |
Usage Tips | Clip Skip: 2 |
Trigger Words | phiadef facial mark body markings armor pelvic curtain white gloves elbow gloves cape choker earrings |
Hash | AutoV2 3A80622038 |
Default only outfit was trained using CivitAI's upcoming LoRA trainer. Will publish a more proper model soon.
Weight: 0.8 - 1.0 (adjust if necessary)
Default Only
Trigger + Appearance: phiadef, facial mark, body markings
Default Outfit: armor, pelvic curtain, white gloves, elbow gloves, cape, choker, earrings
Training resolution is 512 so some things may look really off.
Both Outfits
Default Outfit: phiadef, armor, pelvic curtain, white gloves, elbow gloves, cape, choker, earrings
Bikini Armor: phiabikini
Quite overbaked. Her spiky shoulder armor bleeds over to her default outfit.
Add red hair and red eyes if necessary.
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. You may sometimes notice that my prompt includes <lyco:. Note that some of my LoRA files are located within my LyCORIS folder. If the model is labeled as a LoRA, it's a simple LoRA. If it's specified as a LyCORIS, it's a LoCon/LoHa.