Sign In

Utaha Kasumigaoka PonyXL

75

391

498

20

Updated: Dec 22, 2024

characterutaha kasumigaoka

Verified:

SafeTensor

Type

LoRA

Stats

269

485

137

Reviews

Published

Nov 9, 2024

Base Model

Pony

Training

Steps: 1,200

Trigger Words

utahakasumigaoka

Hash

AutoV2
EC1F5790F3
2025 Year of the Snake Contest Participant
sumai's Avatar

sumai

20241109v1.5

Utaha Kasumigaoka from Saenai Heroine no Sodatekata

Trigger Words: utahakasumigaoka

Trained with Pony Diffusion V6 XL checkpoint.

I have set a moderation on the gallery, so the NSFW content may not appear.

Due to "flagged for review", many images will be delayed by many hours before they can be viewed.

The original style has been enhanced, but the characters' body movements and hand details still need improvement. Gradually, I've been figuring out how to train a highly accurate character LoRA, even when the dataset's references are suboptimal (e.g., flashy visuals, complex poses).

Problems

  • Bad hands, changing a checkpoint to generate images may be better.

  • Anatomy not good enough.

  • Delete many outfits from dataset for a continuous style.

Usage tips

  • The model's output may heavily rely on the checkpoint.

  • The character's face, eyes, and pupils can be repaired through ADetailer.

  • You could find the example prompts from my post.

  • My prompts are basically composed in the order of [character traits] + [style] + [expression] + [clothing] + [camera and action] + [background], and you can delete or modify them as needed.

  • Recommended weight: 1~0.6, adjust as needed until the character's appearance meets your requirements.

  • Upscale value recommendation is around 1.2~2.0, denoising strength is 0.2

20241103v1

This training has given me new experience; Megumi Kato should also be able to be improved through this method.

Usage tips

  • The model's output may heavily rely on the checkpoint.

  • "3d" tag must be added to the negative prompt to avoid uncontrollable outputs.

  • The character's face, eyes, and pupils can be repaired through ADetailer.

  • You could find the example prompts from my post.

  • My prompts are basically composed in the order of [character traits] + [style] + [expression] + [clothing] + [camera and action] + [background], and you can delete or modify them as needed.

  • Recommended weight: 1~0.6, adjust as needed until the character's appearance meets your requirements.

  • Upscale value recommendation is around 1.2~2.0, denoising strength is 0.2