Created by JujoHotaru
CAUTION : PLEASE DO NOT use Negative Prompts (or negative embedding). Otherwise it will reproduce worse quality outputs. If you need to exclude some elements, please use NegPiP extension. I'm currently investigating these issues.
"HotaruBreed XL" is pursuing "kawaii", cuteness. These checkpoints are trained with outputs of original HotaruBreed series (for SD1.5) to reproduce their impressions.
This is "Japanese TV Animation" style. Normal style versions and Semi-real (2.5D) style version are also available.
I feel that model merging is similar to the breeding of flowers (to improve their appearance), so named "Breed".
These models have special features :
Include many originally trained LoRA's to adjust painting style (saturation, tone), eye shape, and quality (finely detailed pupils, finely detailed outlines, reducing grain noise etc).
Highly detailed backgrounds.
Support NSFW outputs.
More various other LoRA's and Checkpoints are released on my CivitAI models list or HuggingFace repository. Please check it out.
Recommended output settings
CFG Scale: 7 - 10
Clip skip: 2
Sampler : DPM++ 2M SDE Karras / DPM++ 3M SDE Karras
Sampling steps: 30 - 50
Resolution: mainly tested on 768x768, 832x1216, 800x1200 and 1024x768
HiRes Fix: use SwinIR_4x, R-ESRGAN 4x+ or 4x-UltraSharp with denoise strength 0.3-0.7.
Negative prompt: DO NOT USE (see above)
VAE: embedded.
Recommended quality prompts (optional)
These checkpoints are derived from PonyDiffusion, so use quality prompts of Pony models.
newest, masterpiece, best quality BREAK score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up BREAK (PUT YOUR PROMPTS HERE)
