Created by JujoHotaru
"HotaruLabs" series are experimental(intermediate) models, used to develop my "Breed" series checkpoints.
7 types are uploaded. To download each types, switch tabs ↑ above.
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.
Tuned to work better with my LoRA's (eye shape, mouth shape, facial expressions).
Support NSFW outputs.
More various other LoRA's are released on my CivitAI models list or HuggingFace repository. Please check it out.
Recommended output settings
CFG Scale: 7 - 10
Clip skip: 1 - 2
Sampler : DPM++ 2M SDE Karras / DPM++ 3M SDE Karras
Sampling steps: 30 - 50
Resolution: mainly tested on 512x512, 800x600, 640x960 and 1024x768
HiRes Fix: use SwinIR_4x, R-ESRGAN 4x+ or 4x-UltraSharp. with denoise strength 0.2-0.6.
Negative embeddings: EasyNegative(v1), EasyNegativeV2, or SimpleNegative
Negative prompt: bad face
VAE : HotaruVAE is included(baked) in this model. No need to use external VAE by default, but
you can change to another VAE by setting on WebUI.
Tweaking details: Use HyperDetailer.
Recommended quality prompts (optional)
insanely detailed, absurdres, ultra-highres, ultra-detailed, best quality BREAK slender, kawaii, perfect symmetrical face, ultra cute girl, ultra cute face, ultra detailed eyes, ultra detailed hair, ultra cute, ultra beautiful BREAK (PUT YOUR PROMPTS HERE)
