Type | |
Stats | 352 159 1 |
Reviews | (43) |
Published | Nov 27, 2023 |
Base Model | |
Training | Steps: 1,200 Epochs: 10 |
Usage Tips | Clip Skip: 2 Strength: 0.8 |
Trigger Words | uniform, cloak, thigh boots christmas, antlers, dress swimsuit |
Hash | AutoV2 B4D1988037 |
v2b
添加了圣诞皮肤和泳装皮肤作为数据集制作 3in1 模型。
基本触发词:
原始皮肤:uniform, cloak, thigh boots
圣诞皮肤:antlers, dress, christmas
泳装:swimsuit
该版本特征丢失较为严重,故建议在使用中对照生成结果额外补充以下提示词:
圣诞皮肤:white thighhighs, ribbon on breasts, very long hair 等
泳装:red frills 等
同时,建议在使用某一装扮时将另外两个装扮的触发词加入负词缀。比如,在生成圣诞装扮时,将 uniform, cloak 加入负词缀。
已知问题:在提示词较少时经常画出默认皮肤的手杖。
Add Christmas suit and swimsuit into dataset, now this lora is 3in1.
Base Trigger:
Origin: uniform, cloak, thigh boots
Christmas: antlers, dress, christmas
Swimsuit: Just "swimsuit"
Feature loss in this version is quite severe. Therefore, I recommended to supplement the following prompt words by comparing the generated results during use:
Christmas: white thighhighs, ribbon on breasts, very long hair, etc
Swimsuit: red frills, etc
Meanwhile, I recommended to add the trigger words of other two outfits into negative when you only using one outfit. For example, when generating Christmas, add ‘uniform' and 'cloak' into negative.
Known issue: Often drawing a cane with default skin when there are few prompt words.
v1
[Note] Prompt of example grid:
1girl, solo, princeton, full body, standing, dress, legwear, <lora:Princeton_v1-000008:0.8>,
No negative.
一个简单的《碧蓝航线》普林斯顿角色LoRA,仅使用单张图片训练。
触发词:princeton, dress, legwear
推荐权重:0.5
此权重下可方便地为角色更换服装和姿态。而需要完整还原角色,您可以适当提高权重。
高权重下建议将 purple background 添加到负词缀中。
Simply a character LoRA of Princeton from mobile game Azurlane. Trained from single image.
Trigger: princeton, dress. legwear
Weight: 0.5
On that weight you can easily draw other clothing for Princeton. Increase it when you want to revival her entirely.
Negative "purple background" when you on a high weight.