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

生成自己想象中的兰那罗吧!

Generate your own imaginary Aranara!

tag: "1 lannaluo"或者"Aranara"均可触发,两触发词同时使用会导致画面出现多个兰那罗。用颜色tag来确定兰那罗的主题色,使用leaf, smile等tag或许能帮助生成兰那罗。

基于anything4.5模型进行训练,在CounterfeitV25等二次元模型均可使用,在真实系模型中可能出现蔬菜成精的效果。推荐强度~0.9。建议使用512×512尺寸,其他尺寸未经测试,我不太确定使用效果。

在使用anything4.5与CounterfeitV2模型时与其他风格化lora、角色lora均适应良好,可混合使用,产生不同艺术风格的兰那罗或者不同角色兰那罗化后的样貌。建议同时使用时,其他风格化lora权重最高不要高于0.7,过高可能无法产生兰那罗。在无法产生兰那罗时,这个lora倾向于为角色周边增添森林场景与一些植物。

在pastelMixStylizedAnime、meinapastel模型中混合其他角色lora使用时会导致兰那罗形象出现概率降低,在负面tag中加入1girl、human 或可改善,但仍会出现此问题。

tag样例——例图中神里绫华兰那罗所用tag:

1 lannaluo, kamisato ayaka (flawless radiance), ponytail, kote, blunt bangs, hair ribbon, light blue hair, smile, leaf, <lora:lannaluo-000012:0.9> <lora:kamisatoAyakaSpringbloom_v10:0.6>
Negative prompt: EasyNegative
Steps: 20, Sampler: Euler a, CFG scale: 10, Seed: 531460020, Size: 512x512, Model hash: a074b8864e, Model: CounterfeitV25_25, Clip skip: 2, ENSD: 31337

Trigger Words:use "1 lannaluo"or"Aranara" as the Trigger Word. Using both of them may cause multiple Aranaras to appear in the picture. Use color tags to determine the main color of the Aranara, and use tags such as leaf, smile may help to generate Aranara.

Training based on the anything4.5 model, can be used in 2D style models such as CounterfeitV25, and the effect of Vegetable monsters may occur in the Realistic style model. Recommend strenth: ~0.9.The 512×512 picture size is recommended.

When using the Anything 4.5 and Counterfeit V2 models, they are well adapted to other stylized lora and character lora, and can be mixed to produce different art styles of Aranara or different Aranara characters. It is recommended that when used at the same time, the weight of other stylized LoRa should not be higher than 0.7, and too high may not produce Aranara. When Aranara is not spawned, this lora tends to add a forest scene and some plants to the character's surroundings.

Mixing other characters lora in the pastelMixStylizedAnime, meinapastel model causes the Aranara image to appear less likely, and adding 1girl, human to the negative tag may be improved, but this problem still occurs.

tag example - the tag used by Kamisato Ayaka Aranara in the example picture:

1 lannaluo, kamisato ayaka (flawless radiance), ponytail, kote, blunt bangs, hair ribbon, light blue hair, smile, leaf, <lora:lannaluo-000012:0.9> <lora:kamisatoAyakaSpringbloom_v10:0.6>
Negative prompt: EasyNegative
Steps: 20, Sampler: Euler a, CFG scale: 10, Seed: 531460020, Size: 512x512, Model hash: a074b8864e, Model: CounterfeitV25_25, Clip skip: 2, ENSD: 31337

本模型使用《原神》游戏截图、《原神》官方网页活动截图与部分网图进行训练,lora所生成图片不具备任何版权,不能用于任何商业活动。This model is trained using screenshots of Genshin impacts games, screenshots of official website activities of Genshin and some network pictures. The images generated by this LoRA are not copyrighted and cannot be used for any commercial activity.

Images Generated With This Model

Loading...

Similar Models

Gentle Cubism 轻立体主义几何构线
V1
Gentle Cubism 轻立体主义几何构线
(0.00)
0
0 Ratings
[Honkai: Star Rail崩坏:星穹铁道]liuying流萤
N/A
V1
[Honkai: Star Rail崩坏:星穹铁道]liuying流萤
(5.00)
0
1 Ratings
Bowser
V1
Bowser
(5.00)
0
1 Ratings
Doraemon/哆啦a梦/ドラえもん
V1
Doraemon/哆啦a梦/ドラえもん
(5.00)
0
3 Ratings
Little Hero_v1.0
V1
Little Hero_v1.0
(0.00)
0
0 Ratings
Doraemon/哆啦a梦/ドラえもん
V1
Doraemon/哆啦a梦/ドラえもん
(5.00)
0
1 Ratings
hanfu_feiyu_style 汉服 飞鱼服风格
V1
hanfu_feiyu_style 汉服 飞鱼服风格
(0.00)
0
0 Ratings
Doraemon/哆啦a梦/ドラえもん
V1
Doraemon/哆啦a梦/ドラえもん
(5.00)
0
2 Ratings
Gentle Cubism 轻立体主义几何构线
V1
Gentle Cubism 轻立体主义几何构线
(5.00)
0
2 Ratings
荒野景观调/landscape/Architecture
V1
荒野景观调/landscape/Architecture
(0.00)
0
0 Ratings

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.