Models>

崩坏星穹铁道/Honkai: Star Rail/艾丝妲/Asta

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

V2.0更新:

增强了姿势方面的定制性,增加了部位关键词

可以使用head,face,legs,high heel或者upper body,from side等prompt来规定画面容纳的内容

预览图里用到了lora分层控制插件lora block weight以控制lora的脸,从而实现换装,实际上不用这一插件应该也能实现换装。

使用AOM3大模型对该lora模型进行的训练,因此使用该checkpoint能够画出与预览图相似的效果。这一lora模型适合绘制2D动漫图片,如果想要绘制2.5d或者3d图片,可以使用本站的PERFECT WORLD这一CHECKPOINT,配合hipoly3DModelLora这一lora进行绘制,但脸部特征可能丢失较多。

经过我的测试,当lora权重为0.6~0.65时能够达到较好的效果,能够使艾思妲穿着与游戏里相同的官方服装。如果权重过大,可能会使绘图与训练集相似。此外,使用时最好使用触发词"asda",以更好地触发lora。

我对人工智能领域鲜有涉猎,目前仍处于学习阶段,因此我还不知道如何在保留艾思妲面部特征的同时定制任意你想要的服装。

我会持续学习AI绘图,优化更新我的Lora模型,也期待各位的作品,希望大家喜欢,谢谢。欢迎大家使用中文或英文与我交流,虽然我的英文不是很好,但是我也会持续学习,吾生也有涯,而知也无涯。

V2.0 update:

Enhanced customization in posture and added keywords for location

You can use prompts such as head, face, legs, high height, or upper body, from side to specify the content that the screen contains

The preview image uses the Lora layered control plugin Lora block weight to control Lora's face and achieve facelift. In fact, without this plugin, it should be possible to achieve facelift.

The lora model is trained using the AOM3 large model, so using this checkpoint can draw an effect similar to the preview image.This Lora model is suitable for drawing 2D anime images. If you want to draw 2.5d or 3D images, you can use the CHECKPOINT of PERFECT WORLD on our website, combined with the Lora of hipoly3DModelLora, for drawing. However, facial features may be lost a lot.

After my test, when the lora weight is 0.6~0.65, a better effect can be achieved, which can make Esta wear the same official costume as in the game. If the weights are too large, it may make the plot similar to the training set.In addition, it is best to use the trigger word "asda" to better trigger lora.

I'm new to the field of artificial intelligence and I'm still learning, so I don't know how to customize any outfit you want while retaining Este's facial features.

I will continue to learn AI drawing, optimize and update my Lora model, and look forward to your works, I hope you like it, thank you.

You are welcome to communicate with me in Chinese or English. Although my English is not good, I will continue to learn. My life has a limit, but knowledge has no limit.

Images Generated With This Model

asda,face,1girl,head,open mouth, <lora:astalora_zsrx_v2:0.65>,sports bra,(sideboob:1.2),sitting ,shiny skin,(arms behind head:1.2),<lora:shinyOiledSkin_v1:0.4>,(thin legs, high heel:1.2),
N/A
Hidden For Public Users
asda,face,1girl,head,open mouth, <lora:astalora_zsrx_v2:0.65>,sports bra,(sideboob:1.2),sitting ,shiny skin,(arms behind head:1.2),<lora:shinyOiledSkin_v1:0.4>,(thin legs, high heel:1.2),
asda,face,1girl,head,open mouth, <lora:astalora_zsrx_v2:0.7:FACE>,sports bra,(sideboob:1.2),(cross legs:1.1),sitting ,shiny skin,(arms behind head:1.2),<lora:shinyOiledSkin_v1:0.4>
N/A
Hidden For Public Users
asda,face,1girl,head,open mouth, <lora:astalora_zsrx_v2:0.7:FACE>,sports bra,(sideboob:1.2),(cross legs:1.1),sitting ,shiny skin,(arms behind head:1.2),<lora:shinyOiledSkin_v1:0.4>
masterpiece,best quality,photo realistic,asda,face,1girl,head,thick lips, <lora:astalora_zsrx_v2:0.65>,pink hair,sitting ,wet,shiny skin, mix4,<lora:hipoly3DModelLora_v20:0.4>, <lora:cuteGirlMix4_v10:0.2> <lora:fashionGirl_v54:0.2> <lora:chilloutmixss_xss10:0.2>
N/A
Hidden For Public Users
masterpiece,best quality,photo realistic,asda,face,1girl,head,thick lips, <lora:astalora_zsrx_v2:0.65>,pink hair,sitting ,wet,shiny skin, mix4,<lora:hipoly3DModelLora_v20:0.4>, <lora:cuteGirlMix4_v10:0.2> <lora:fashionGirl_v54:0.2> <lora:chilloutmixss_xss10:0.2>
masterpiece,best quality,asda,face,1girl,head,open mouth, <lora:astalora_zsrx_v2:0.7>,(sports bra,nipple:1.4),sitting ,(arms behind head:1.2),sweating,shiny skin,<lora:shinyOiledSkin_v1:0.4>, (wet bare pussy:1.4)
N/A
Hidden For Public Users
masterpiece,best quality,asda,face,1girl,head,open mouth, <lora:astalora_zsrx_v2:0.7>,(sports bra,nipple:1.4),sitting ,(arms behind head:1.2),sweating,shiny skin,<lora:shinyOiledSkin_v1:0.4>, (wet bare pussy:1.4)
1girl,bare shoulder, <lora:asdalora:0.6>,asda,bed,sunshine
N/A
Hidden For Public Users
1girl,bare shoulder, <lora:asdalora:0.6>,asda,bed,sunshine
1girl,bare shoulder, <lora:asdalora:0.65>,asda,
N/A
Hidden For Public Users
1girl,bare shoulder, <lora:asdalora:0.65>,asda,
,1girl,flying,
N/A
Hidden For Public Users
,1girl,flying,
,1girl,sunlight,wind,
N/A
Hidden For Public Users
,1girl,sunlight,wind,
,1girl,jumping
N/A
Hidden For Public Users
,1girl,jumping
,1girl,singing,at stage
N/A
Hidden For Public Users
,1girl,singing,at stage
,1girl,santa,snow,
N/A
Hidden For Public Users
,1girl,santa,snow,

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

Your All-in-One AI Image Solution

AIEasyImage brings AI image technology to everyone. Create stunning visuals, edit like a pro, and develop your unique style – all with the power of AI. No technical skills required!