SD
HotaruBreed CuteAnimeMix
- Dimuat naik pada
- 21 Mac 2024, 1:22 PTG
- Kegunaan
- 990
- Ulasan
- Tiada ulasan
- Kebenaran
- Allow image generation & sharing
- Benarkan pengguna memuat turun model anda
- Kegunaan komersial
Keterangan
https://civitai.com/models/210828
[ If downloaded file name becomes short, rename it to "HotaruBreed_CuteAnimeMix_v70.safetensors". ]
[ v7.0 : Refined quality according to other latest HotaruBreed(v7) series. So intermediate versions(v2-v6) do not exist. ]
"HotaruBreed" series are merged models pursuing "kawaii", cuteness. I feel that model merging is similar to the breeding of flowers (to improve their appearance), so named "Breed".
HotaruBreed has 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.
This is "CuteAnimeMix" - Specialized version for smaller(younger) characters and "AnimeMix (Japanese TV Animation like style)" based.
HotaruBreed series have many variations :
Type A - semi realistic 2.5D style.
Type B - general purpose 2D style
Type C - semi anime style
Type D - anime style
Type E - classic anime style
Type F - light colored and flat style
Anime Mix - Japanese TV animation like style
RealMix - more 2.5d-like style than Type A
CuteMix Type B - CuteMix based on Type B
CuteMix Type D - CuteMix based on Type D
CuteMix Type F - CuteMix based on Type F
CuteAnimeMix - CuteMix based on AnimeMix
CuteMix TypeA/C/E - only available in HuggingFace repository.
More various other LoRA's and checkpoints are released on my CivitAI models list or HuggingFace repository. Please check it out.
CAUTION : Some sample images' prompt is using NegPiP extension for minus weight.
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 0.3-0.6.
Negative embeddings: EasyNegative (v1) or EasyNegativeV2
Negative prompt: bad face
VAE: included. No extra VAE is needed.
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
External resources used to merge cookiecutter_clearV45
tekuteku-nsfw
featureless25DMix_v10
CheckpointYesmix_v35
canistermix4_v10
canistermix5_v10
everdream_v10
milktea
PVCStyleModelMovable_v20NoVae
AgelesnateV1_2
dorayakimix_v30Fp16
reallynotreal_jade
ClearVAE 1.0
flat2 LoRA