Harayutaka はらへら style [Animagine XL]

style by hara_(harayutaka)Yodayo / (sd 1.5) | Seaart.aiVersions for sd 1.5, Animagine and Pony, contains several for each, pick whichever you think you need. I recommend Animagine. Thousandths in ver. are just model differences, the dataset is identicalFor all versions: Minimum recommended steps: 25-28Trigger word: shr All images have a prompt you can look at and choose what you are interested in! v0.91 PDXL Trained on Pony diffusion v6. Recommended weight: 1-1.5 (1.35)Recommend word: (hara (harayutaka):0.45-0.7) ~ (0.5)When using this word, it is recommended to reduce the weight of lora.It is not recommended to use the word without lowering the weight. Recommended word for harayutaka original style: anime screencap Sweet spot epoc: 12 v0.911 SDXL Trained on Animagine XL v3.1 Recommended weight: 0.8-1 (0.9)Recommend word: hara (harayutaka)When using this word, it is recommended to reduce the weight of lora Sweet spot epoc: 09-11 (11) Differences: more original style, perhaps because the model knows the original style and has it inside it. v0.932 sd 1.5 Trained on aamAnyloraAnimeMix Recommended weight: 0.75-1.1 (0.9) Sweet spot epoc: 13-16 Differences: more flexibility in everything because of the large set of checkpoints and lora sd 1.5.