This is a LoRA for xipa(@jipa42760710)'s recent Style. I made it on request.
I will remove it if offered.
Trigger words:
For v2.0: @xipa2026late03-05,
For v0.1-1.1: @x1p4early2026,
For v0.01(Krea2 test): xipa style.
Description
His art style from January 2026 to mid-March.
Trained on Anima Preview 3 Base.
FAQ
Comments (6)
incredible prompting skill, concise but effective❤️
Thank you so much for the previous model! Could you possibly make a anima model of this painter?kuook - pixiv weibo - 怅夜骨髓 - E-Hentai Galleries I really love his makeup look
请问下，楼主是window环境训练的吗，用的什么训练器工具呢，能否给个链接，我看你的lora参数里使用了CAME优化器，我的优化器里没有CAME 这个选项，谢谢
I create LoRAs using sd-scripts on a local Windows PC.
@toghashie441 谢谢，我看你的lora体积非常小，只有20m，而且只训练了1000 step，但效果意外的不错，能分享下你的配置文件吗
It is simply that Anima's LoRAs have a smaller file size compared to those of SDXL. Also, since this LoRA was trained with the Train batch size set to 2, the actual total number of steps is 2 * 1000, which is approximately 2000. Please refer directly to the metadata for the specific LoRA settings.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.