Try size: 768 x 1024 or 1024 x 768 or 1024 x 1024
Weights: 0.5~1.0
Clip skip: 2
Training material from web pics and banana
Note: If overfitting occurs, reduce the weights to improve the situation. / 如果出現過擬合的情形,請降低權重來改善狀況。(Anima10)
Note: I've wanted to train Jiufen LoRa since last year, but I wasn't confident about the materials and parameters, so I kept putting it off until now. The scenes is quite complex, so I suggest referring to the prompt in the training set. I don't recommend generating realistic characters; my plan is to focus on anime characters. / 從去年就想訓練九份LoRa了,但那時對素材跟參數沒有把握,所以一直拖到現在。場景比較複雜,所以建議參考訓練集中的完整提詞。不建議生成寫實人物,我的計劃就是針對動漫人物。(ILXL)
Description
FAQ
Details
Downloads
156
Platform
CivitAI
Platform Status
Available
Created
11/19/2025
Updated
8/21/2026
Deleted
-
Trigger Words:
jiufen old street, alley, 1girl, solo, dress, upper body, outdoors, awning, road, shop, sky, taiwan, messy, lantern, photo background, looking at viewer,
glass ceiling, skylight,
people,
crowd,



















