Sign In

jiufen / ruifang / (九份 / 瑞芳)

158

Download

1 variant available

bf16 SafeTensor

jiufenoldstreet_anyanima102.safetensors

BF16, good balance • 44.06 MB

Verified:

Type
LoRA
Stats

112

146

131

Reviews
Published

Jul 7, 2026

Base Model

Anima

Training
Steps: 666
Epochs: 6
Usage Tips
Strength: 1
Hash
AutoV2
6B8A28464B
Trigger Words
jiufen old street, narrow alley, storefront, 1girl, solo, young, skinny, dress, breasts, awning, eaves, slope, shop, road, sky, taiwan, lantern, photo background, medium shot, upper body, crowd, people,
indoors, drain cover, aqua canopy,
anime coloring, anime style,
default creator card background decoration
Followers - 1873

1.9K

Likes - 18507

18.5K

Downloads - 177215

177.2K

Donator Badge

License:

Anima

The Anima Model is licensed by CircleStone Labs LLC. Copyright CircleStone Labs LLC. IN NO EVENT SHALL CIRCLESTONE LABS LLC BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.

Built on NVIDIA Cosmos

00061-405703486.png

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)