Models>

Take control of the oceans 海飞丝

haifeisi,1girl,solo,long hair,water,closed eyes,chinese clothes,long sleeves,waves,hanfu,black hair,floating hair,wide sleeves,hair bun,sash,yellow dress,closed mouth,
Best quality,masterpiece,ultra high res,<lora:20240122-1705924259525-0015:0.65>,
haifeisi,1girl,solo,jewelry,earrings,black hair,long hair,waves,water,floating hair,hair ornament,wide sleeves,japanese clothes,kimono,ocean,wind,hair bun,outdoors,
Best quality,masterpiece,ultra high res,<lora:20240122-1705924259525-0015:0.65>,
haifeisi, 1girl, solo, long hair, water, green dress, hair ornament, chinese clothes, waves, ponytail, splashing, dress, closed eyes, brown hair, long sleeves, hanfu, standing, watermark, jewelry, outdoors, wide sleeves,
Best quality,masterpiece,ultra high res,<lora:20240122-1705924259525-0015:0.65>,
Quick Generate
Select a style, write what you want to see and click Generate
What you want in the image.
Clear
Random
* This model is available for use and will generate similar character to the ones seen in the images.

Model Description by Creator

v4.1

v4.1 Waves Background

The background part of V3.5 is extracted in layers, which can produce a good background effect without affecting the characters, and can even achieve the effect of V3.5 version when used in 2.5D large models and 2D large models, but the effect is average in realistic large models

Recommended weight: 0.7

It mainly affects the background and has little impact on the characters

分层提取了v3.5的背景部分,能不影响人物同时产生不错的背景效果,在2.5d大模型和2d大模型中使用甚至可以实现v3.5版的效果,但是在写实大模型中效果一般

推荐权重:0.7

主要影响背景,对人物影响不大

v3.5

lora weight:0.65, and 0.5 in hires.fix or i2i

v2

全新升级版海飞丝v2,分层融入了小部分哲学系的李诗人大佬的水神共工氏。

采用正则训练,泛化性较好,兼容各种大模型的画风,提示词注意加入衣服,负面提示词加入nsfw,避免产生不必要的麻烦。

推荐权重:2d大模型0.55-0.7,3d大模型0.64-0.9

推荐模型:都行,画风完美兼容

推荐使用 lora block weight 插件的MIDD来进一步加强lora泛化性

English Translation:

The all-new upgraded version of 海飞丝 V2 incorporates elements of the Gonggongshi from CN_LeePoet.

Utilizing regular training, it demonstrates good generalization, compatible with various artistic styles of large models. Reminder words should include clothing you want, and negative prompts should incorporate NSFW to avoid unnecessary complications.

Recommended weights: 2D checkpoint 0.55-0.7, 3D checkpoint 0.64-0.9.

Recommended models: Any, with perfect compatibility with artistic styles.

It is advised to use the MIDD with the lora block weight plugin to further enhance the generalization of lora.

Images Generated With This Model

Loading...

Train Models

Train AI Models On Your Own Pictures

You can use your own pictures to train AI models. Reimagine yourself in new ways with our AI-powered image generator.
Create pictures of yourself around the world, in your dream outfit, as a video game character, or in countless art styles. The possibilities are endless.
Train Your Own Model

Generate AI Images. Simple and Easy

AIEasyPic is the #1 AI image generator. Generate images with simple prompts, swap faces, train models to reimagine yourself, and more.