Type | |
Stats | 4,982 |
Reviews | |
Published | May 26, 2023 |
Base Model | |
Training | Steps: 1,620 Epochs: 6 |
Trigger Words | Matsumoto Rangiku |
Hash | AutoV2 BE7B58792C |
Resource used: https://civitai.com/models/22530
Weight: 1.0
Trigger: Matsumoto Rangiku
Recommended Tags: blonde hair, orange hair, blue eyes, grey eyes, long hair, cleavage, wavy hair, black kimono, silver chain, pink shawl, black wide sleeves, white sash
Recommended Negatives: alternative hairstyle, Messy hair, sleeveless
Why two versions?:
Answer: I noticed that the more Epoch the LoRA had, the more realistic the output tended to look (and this was before using photorealistic tags), so I reduced the Epoch count to 6 to create a better anime version experience and kept the 13 epoch version for realism; same dataset for both.
While these LoRA don't do a perfect job, they do it good enough. (Sadly the internet doesn't have enough accurate resources, and SD still does dumb things like white sleeves and white kimono)
Note: I use a custom checkpoint: (https://civitai.com/models/18116 + https://civitai.com/models/22402/fantasticmix = 25%) + https://civitai.com/models/43977/moonmix or https://civitai.com/models/53360?modelVersionId=57724 10%
In case the CivitAI doesn't pick it up, other resources used:
Bleach Anime Style = https://civitai.com/models/51997
FilmGrain = https://civitai.com/models/33208
Add Details = https://civitai.com/models/58390
Sharpness = https://civitai.com/models/69267?modelVersionId=76092
Noise = https://civitai.com/models/13941
Negatives:
badv5 = https://civitai.com/models/16807
ng_deepnegative_v1_75t = https://civitai.com/models/4629
verybadimagenegative_v1.3 = https://civitai.com/models/11772
By bad artist = https://civitai.com/models/5224
EasyNegative = https://civitai.com/models/7808
Unspeakable Horrors = https://civitai.com/models/4499?modelVersionId=5139
Bad Prompt V2 = https://civitai.com/models/55700/badprompt-negative-embedding
Bad-Hands-5 isn't on civitai