Type | |
Stats | 148 2,041 |
Reviews | (34) |
Published | Jan 29, 2024 |
Base Model | |
Training | Steps: 1,500 Epochs: 50 |
Usage Tips | Clip Skip: 2 Strength: 1 |
Trigger Words | Kitraandra, green eyes, anthro, colored skin, (orange skin:1.3), tiger girl, tail, pointy ears, facial mark, medium hair, blonde hair Large breasts, red lips Muscular, biceps two-tone bodysuit, (orange armor:1.4), thigh boots, breastplate, pauldrons, gauntlets |
Hash | AutoV2 1307E2EE51 |
The bounty hunter Kitraandra from the flash game on Newgrounds Clixposing Kitraandra. Works best around 1.0 weight. Training done on NAI.
Trigger: "Kitraandra, green eyes, anthro, colored skin, (orange skin:1.3), tiger girl, tail, pointy ears, facial mark, medium hair, blonde hair" always needed, "Large breasts, red lips" and "Muscular, biceps" suggested for accuracy and/or taste.
Suggestions/notes:
Disclaimer: As it is a furry character it may not work very well on all models.
Main Outfit: "two-tone bodysuit, (orange armor:1.4), thigh boots, breastplate, pauldrons, gauntlets"
Note data was really bad for the outfits so do not expect good or consistent results.
Colors are very random sadly due to bad data
The middle of the body's color will sometimes fail depending on model/pose.
Increasing boost on tags like "(orange skin:1.3)" can help make it more consistent across all clothing/lack of clothing.
Note to add more color to clothing to reduce color bleed.
Removing "anthro" will make her more human but the skin color will start to fail a lot more.
She is flexible clothing wise and NSFW capable but there is some mild bleed of random clothing which I do not know the exact source so might be an SD issue.
An orange fit tiger gal? Hit me right up. This character is a classic from my early days of exploring the internet and flash games so I wanted to make her for the rest of you all to experience. I hope you all enjoy.
Feedback and reviews are always appreciated.
Nerdy training numbers:
Trained on D8Dreambooth trainer
Optimizer: Dadaptation
Training resolution: 768
Unet LR: 1
Tnec LR: 1
Unet weight decay: 0.01
Tenc weight decay: 0.014
50 Epochs - 1500 Steps
Trained on 30 images.