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

大家好,我是chosen鲷,今天就是万圣夜了,这次带来的是恶灵 Lora,提前祝大家万圣节快乐。

这个训练集由绪儿提供https://space.bilibili.com/37459046?spm_id_from=333.337.0.0,本来想训练耿鬼的角色lora的,但是由于mj出图出的不是很准确,所以它成为了某种类耿鬼生物?所以就叫它恶灵吧~

这个lora兼容性蛮好的,跟许多模型都适配。触发词:gengar

推荐的tag:

(masterpiece:1.2), best quality,PIXIV, Gengar,
这里写你想要的内容
<lora:Gengar_20231030164316-000016:1>
Negative prompt: EasyNegative, badhandsv5-neg,Subtitles,word,
Steps: 32, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 724839989, Size: 512x768, Model hash: e3edb8a26f, Model: ghostmix_v20Bakedvae, Denoising strength: 0.5, Clip skip: 2, Hires upscale: 2, Hires upscaler: R-ESRGAN 4x+, Lora hashes: "Gengar_20231030164316-000016: 27a04c3c69da", Version: v1.4.1

大模型我推荐用我ghost,我的其他模型也成,例如chosen mix、irises、星辰之类的,但是推荐用比较扁平化的二次元插画模型.

感谢大家的下载使用,如果喜欢的话欢迎关注我,我的bilibili pixiv ID均为chosen鲷,欢迎大家关注我的频道https://space.bilibili.com/3867754?spm_id_from=333.1007.0.0https://www.pixiv.net/users/40911695 谢谢。

The following content is from Google Translate:

Hello everyone, I am chosen鲷. Today is Halloween night, and I bring you the evil spirit Lora. I wish you all a happy Halloween in advance.

This training set was provided by 绪儿 at https://space.bilibili.com/37459046?spm_id_from=333.337.0.0. Originally, I wanted to train a character named Lora as Gengar, but due to inaccurate image generation by mj, it became some kind of Gengar-like creature. So let's call it an evil spirit~

Lora has good compatibility and works well with many models. Trigger word: gengar

Recommended tags: (masterpiece:1.2), best quality, PIXIV, Gengar,

Write your desired content here

<lora:Gengar_20231030164316-000016:1>
Negative prompt: EasyNegative, badhandsv5-neg,Subtitles,word,
Steps: 32, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 724839989, Size: 512x768, Model hash: e3edb8a26f, Model: ghostmix_v20Bakedvae, Denoising strength: 0.5, Clip skip: 2, Hires upscale: 2, Hires upscaler: R-ESRGAN 4x+, Lora hashes: "Gengar_20231030164316-000016: 27a04c3c69da", Version: v1.4.1

For large-scale models, I recommend using my ghost model. My other models like chosen mix, irises, and stars are also suitable, but I recommend using flatter two-dimensional illustration models.

Thank you for downloading and using it. If you like it, feel free to follow me. My bilibili and pixiv IDs are both chosen鲷. You are welcome to follow my channels at https://space.bilibili.com/3867754?spm_id_from=333.1007.0.0 and https://www.pixiv.net/users/40911695. Thank you.

Images Generated With This Model

Loading...

Similar Models

温馨的动画场景/cozy animation scenes Lora
V1
温馨的动画场景/cozy animation scenes Lora
(5.00)
0
4 Ratings
狗狗/cute dog/midjourney style dog Lora
V1
狗狗/cute dog/midjourney style dog Lora
(5.00)
0
7 Ratings
猫猫/Cute cat /midjourney style cat  Lora
V1
猫猫/Cute cat /midjourney style cat Lora
(5.00)
0
26 Ratings
碧蓝档案场景/blue archive style background lora
V1
碧蓝档案场景/blue archive style background lora
(0.00)
0
0 Ratings
童话绘本/fairy tale style
V1
童话绘本/fairy tale style
(5.00)
0
2 Ratings
富婆style/童话般的服设/fairy tale girl Lora
V1
富婆style/童话般的服设/fairy tale girl Lora
(5.00)
0
6 Ratings
恭贺新禧/happy new year/おみくじ
V1
恭贺新禧/happy new year/おみくじ
(5.00)
0
4 Ratings
武士少女/Samurai girl lora
V1
武士少女/Samurai girl lora
(5.00)
0
4 Ratings
佐伊(幻兽帕鲁)/zoe(palworld)
N/A
V1
佐伊(幻兽帕鲁)/zoe(palworld)
(5.00)
0
7 Ratings
露华浓/ancient Chinese style/古风/midjourney style Lora
V1
露华浓/ancient Chinese style/古风/midjourney style Lora
(5.00)
0
3 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.