Run Locally
cloing3.safetensors
162 MB · SafeTensor
Downloads are served by Civitai. Some creators ask for a Civitai login first.
About This Model
ZIMAGE · LoRAs
by allpleoleo439 - Long Sleeve Super Crop
Creator notes
中文(原文) 我很久沒有製作衣服了 我比較偏向於風格製作 但是Zimage的強項就是人物與世界連結 所以我打算製作一些物件跟服裝的LORA 以前服裝製作都是使用正則判斷式的方式 然而目前的模型似乎都不支援了
因此我研究了三四種素材終於找到適合用來製作衣服的訓練方式了 不過還是有機率會造成崩潰或是產生圖片不正常的情況 還需要再研究
日本語 もうずいぶん服を作っていませんでした。 私はどちらかというとスタイル寄りの制作が得意です。 でもZimageの強みはキャラクターと世界観の繋がりなので、 これからオブジェクトや服飾系のLoRAをいくつか作ろうと思っています。 以前は服を作る時は正規表現(regex)の判定式を使っていたのですが、 今のモデルはほとんど対応していませんね。
なので3~4種類の素材を試した末、ようやく服作りに適した訓練方法が見つかりました。 ただ、まだ崩壊したり画像が変になる確率があるので、もう少し研究が必要です。
English It's been a really long time since I last made clothing models. I personally lean more toward style-focused creations, but Zimage's biggest strength is the connection between characters and the world, so I'm planning to make some LoRAs for objects and clothing. In the past, clothing was made using regular expression triggers, but current models seem to no longer support that method.After testing three or four different datasets, I finally found a training approach that works well for making clothes. However, there's still a chance of collapse or generating abnormal images, so more research is needed.
한국어 오랜만에 옷을 만들어보네요. 저는 스타일 쪽 제작을 더 선호하는 편인데, Zimage의 강점은 캐릭터와 세계관 연결이라서 앞으로 오브젝트랑 의상 LoRA를 몇 개 만들어 볼 생각입니다. 예전에는 의상 제작할 때 정규 표현식(regexp) 판별 방식으로 했었는데, 요즘 모델들은 거의 지원을 안 하더라고요.
그래서 자료 3~4개를 이것저것 돌려보다가 겨우 옷 제작에 적합한 학습 방법을 찾았습니다. 다만 여전히 붕괴가 일어나거나 이상한 그림이 나올 확률이 있어서 더 연구가 필요해요.
Trigger words
照片包含全身,穿著運動內衣與長袖半遮上衣,露出乳溝,露出腰部
SHA256
4684C1D4A32D2C7C4F3510DABF5C3BD8E5885F754B514726B99598834BD6C908
ModelTrends.ai Model ID
#23549
Flag content
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Sampler
Euler
Steps
9
Guidance
1
Seed
216701341875088
Size
1024x1024
Prompt
一名金髮歐洲女性的寫真日常照片包含全身,穿著運動內衣與長袖半遮上衣,露出乳溝,露出腰部
Negative prompt
blurry ugly bad, LOGO
Settings
Sampler
dpmpp_2m_sde_gpu
Steps
9
Guidance
1
Seed
1111
Size
1280x1920
Prompt
Latina female with thick wavy hair, harbor boats and pastel houses behind. Breezy seaside light, warm tones, cinematic upper body portrait.
Settings
Sampler
Euler
Steps
9
Guidance
1
Seed
1026474112273890
Size
1024x1024
Prompt
一名金髮歐洲女性的寫真日常照片包含全身,穿著運動內衣與長袖半遮上衣,露出乳溝,露出腰部
Negative prompt
blurry ugly bad, LOGO
Settings
Sampler
Euler
Steps
9
Guidance
1
Seed
371490594387610
Size
1024x1024
Prompt
一名亞洲女性,露出乳溝,露出腰部,運動內衣,長袖,全身照
Negative prompt
blurry ugly bad, LOGO,阻擋臉部,白色面具,口罩
Settings
Sampler
Euler
Steps
9
Guidance
1
Seed
854913504475905
Size
1024x1024
Prompt
一名金髮歐洲女性的寫真日常照片包含全身,穿著運動內衣與長袖半遮上衣,露出乳溝,露出腰部
Negative prompt
blurry ugly bad, LOGO
Settings
Sampler
Euler
Steps
9
Guidance
1
Seed
402489215317378
Size
1024x1024
Prompt
一名亞洲女性,露出乳溝,露出腰部,運動內衣,長袖,全身照
Negative prompt
blurry ugly bad, LOGO,阻擋臉部,白色面具,口罩
Settings
Sampler
DPM++ SDE
Steps
9
Guidance
1
Seed
1111
Size
1280x1920
Prompt
Latina female with thick wavy hair, harbor boats and pastel houses behind. Breezy seaside light, warm tones, cinematic upper body portrait.
Settings
Sampler
dpmpp_2m_sde_gpu
Steps
9
Guidance
1
Seed
1111
Size
1280x1920
Prompt
Latina female with thick wavy hair, harbor boats and pastel houses behind. Breezy seaside light, warm tones, cinematic upper body portrait.
AI Models for Image, Video & Text Generation
super crop zit is a LoRA for the Zimage family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Zimage models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Text / LLM Models
411
Anima Models
509
Chroma Models
14
Flux Models
1,071
Flux 2 / Klein Models
1,237
MiniMax H3 Models
331
Hunyuan Models
197
Ideogram Models
20
Krea2 Models
674
Qwen Models
17
Qwen2 Models
36
Ltx2 Models
150
Stable Diffusion 1.5 Models
6,465
Stable Diffusion XL 1.0 Models
15,432
Zimage Models
804
Wan Models
919

Model
Trends
.ai
© ModelTrends.ai
|
Made in Japan
|
© 2026
