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

在预览图最后有惊喜哦!

There is a surprise at the end of the preview image!

已经在下面更新了关于流光溢彩组合的简体中文说明哦!

The Chinese Simplified instructions for Ambilight combinations have been updated below!

在运行前请先查看这里哦!!!

Please check here before running!!

TRAIN Model:sd v1.5

VAE:vae-ft-mse-840000-ema-pruned

LORA Weight:0.7

Sampler:DPM2 Karras

Sampling Steps:20

CFG:7

Tips:这次的v3.0大概就是最终版啦!

Tips: This v3.0 is probably the final version!

3.0相较之前我添加了夕阳的效果(也就是霞谷啦qwq),注意哦夕阳(霞谷)的控制词(Prompt)为Sunset Valley,而云野的控制词(Prompt)为Cloud Field,两者不能同时使用哦。

In 3.0, compared with the previous I added the effect of sunset, note that the control word (Prompt) of Sunset is Sunset Valley, and the control word (Prompt) of Yunye is Cloud Field, and the two cannot be used at the same time.

除此之外3.0还试着控制了斗篷的样式,(不过只有两种),分别为蝙蝠斗篷(Bat Cloak)和普通的白色斗篷(White Cloak),同样的两者不能同时使用哦。

In addition, 3.0 also tried to control the style of the cape, (but there are only two), namely the Bat Cloak and the normal white cloak, which cannot be used at the same time.

上方推荐权重仅为参考,使用时请酌情设置权重,在生成图片过程中,发现图片像素过小可能出现脸部崩坏。

The above recommended weight is only for reference, please set the weight as appropriate when using, in the process of generating the image, it is found that the image pixel is too small and the face may collapse.

qwq,最后的预览图哦不是Lora模型的效果,而是我写的一套提示词哦,我管它叫做流光溢彩组合(ᕑᗢᓫ∗)˒(要是喜欢的话记得告诉我哦!我会把写提示词的想法也和你们讲讲看啦,虽然没什么人会看啦qwq)

qwq, the final preview image oh is not the effect of the Lora model, but a set of cue words I wrote, I call it the Ambilight Combination (ᕑᗢᓫ∗) ˒ (if you like it, remember to tell me!). I'll tell you about the idea of writing prompts, although no one will read qwq)

(唔,不知为何还是没有图片信息呢,所以我在文件中添加了示例图片的压缩包,可以尝试一下自己读取图片信息哦,希望这能不再出错了。

Well, for some reason there is still no image information, so I added a compressed package of the sample image to the file,you can try to read the picture information yourself,hoping that this will not go wrong again.)

20230721更新:

20230721 updates:

流光溢彩组合 ✧*。 (ˊᗜˋ*) ✧*。

大概的思路啦:通过调整提示词的权重之间,让画面渐渐变的可控。

通常我会使用的正面提示词是(masterpiece,best quality,),以及会在负面提示词中添加的(lowres,bad anatomy,bad hands,text,error,missing fingers,extra digit,fewer digits,cropped,worst quality,low quality,normal quality,jpeg artifacts,signature,watermark,username,blurry,bad feet),使用这些会帮助你的画面更加精美,使人物肢体更加合理。但是!这些提示词只是在基本情况下使用,如果想要不同的效果还是需要调整的哦(比如在流光溢彩组合里,添加的彩虹效果很容易就会变成儿童绘画里的卡通彩虹,这样的效果当然不是我们想要的啦,所以这时候需要在负面提示词中添加 children's illustration,cartoon rainbow painting之类的提示词)

  • 首先画面中十分明显的的分布一些要素(阳光的散射效果,彩虹色的光影,多彩的瞳孔之类的),这些是实现虹彩效果的附加而控制效果的则是(,(strong emotions:1.1),(rainbow color:1.1),((tyndall effect)),(colorful pupils),(diffuse sunlight),iridescence pupils,iridescence hair,iridescence sunshine,)

  • 其次是画面镜头描述(正面描写,侧面描写,逆光之类的),这些效果可以进一步帮你确定最终画面的样式哦(,(upper body close-up:1.2),(side close-up:1.2,Backlight),)

  • 最后啦就是再对画面风格进行调整(梦幻,动态感一类的,同时这一步也可以使用Lora来帮助确定风格)(,(((fantasy))),(dream),(yoneyamamai style),)

Tips:最后的最后啦,任何一种风格的提示词都是一点一点调整出来的,就像这样:

1.

2.

3.

4.

可以发现啦,在每一阶段图片的效果都是有所不同的,甚至是第一张图和最后的效果完全无关的情况,这都是很正常的事情,在不断调整提示词和提示词的权重的过程中慢慢让画面变成自己想要的样子,我写提示词的想法也就是这样的啦。

还有还有,每一套提示词都是可以经过你的修改的,比如:

5.

当然啦,还可以和Lora相互结合哦,例如和我的v3.0模型相结合的效果:

6.

最后的最后的最后的啦,任何一套提示词都不是绝对保证效果的,它可能会被很多情况影响,比如使用的大模型不同,使用的生成比例不同之类的,都会影响最终的效果,所以也一定要知道不能被所谓的标准影响,需要由你自己慢慢尝试,找出适合你的那一种风格⊂(˃̶͈̀ε ˂̶͈́ ⊂ ).

希望每个人都能画出自己想要的画面啦,最后附上流光溢彩的提示词哦(,(((masterpiece))),(((best quality))),(((fantasy))),(blur background),(transparent blue eyes),hoodies,((upper body close-up:1.2)),(((midjourney))),((strong emotions)),shadow,(rainbow color:1.1),(after a storm comes a calm),iridescence pupils,(lovely:1.1),(white shirt:1.1),iridescence hair,(open your mouth:1.4),iridescence sunshine,knapsack,(flowing hair:1.1),(yoneyamamai style),(side close-up:1.2),(((raindrops in the air))),brilliant colors,fleshy skin,blue eyes,(well ventilated:1.1),((solo)),more detail,warm sunshine,iridescence sky,the sun shines down,(((facial polishing:1.1))),(laughing heartily),happy,dynamic feeling,blue sky,(colorful pupils),(diffuse sunlight),(( tyndall effect)),warm background,face to the side,((frontlighting)),)

值得一说的是流光溢彩除开使用了以上的提示词,还有使用了一些Lora(有梦幻世界的Lora以及我的另一个Lora模型,如果发现效果不太理想的话可以试着添加一些自己理想的Lora来帮助自己进一步固定风格!)

(今天是周五啦,祝每位看到这里的光之子周末快乐啦!(୨୧• ᴗ •͈)◞︎ ♡)

Images Generated With This Model

(((masterpiece))),(((best quality))),White Cloak,cloud,day,blue sky,grass,blue eyes,white hair,blue eyes,1boy,solo,(positive description:1.4),
N/A
Hidden For Public Users
(((masterpiece))),(((best quality))),White Cloak,cloud,day,blue sky,grass,blue eyes,white hair,blue eyes,1boy,solo,(positive description:1.4),
1girl, CCCPposter, sovietposter,none,soviet poster, soviet
N/A
Hidden For Public Users
1girl, CCCPposter, sovietposter,none,soviet poster, soviet
best quality, ultra high res,  <lora:asu_hirana_locon_01-000014:1:NONE>, asu_hirana, sleeveless dress,
N/A
Hidden For Public Users
best quality, ultra high res, <lora:asu_hirana_locon_01-000014:1:NONE>, asu_hirana, sleeveless dress,
1girl,collared shirt, skirt,(from above:0.85),dynamic pose,hands,(face),thigh,simple background,child, <lora:den2SD:0:NONE>
N/A
Hidden For Public Users
1girl,collared shirt, skirt,(from above:0.85),dynamic pose,hands,(face),thigh,simple background,child, <lora:den2SD:0:NONE>
1girl (watercolor:1.3),vivid color, <lora:den2SD:0:NONE>
N/A
Hidden For Public Users
1girl (watercolor:1.3),vivid color, <lora:den2SD:0:NONE>
1boy , outdoors,upper body,red hoodie,piec, <lora:den2SD:0:NONE>
N/A
Hidden For Public Users
1boy , outdoors,upper body,red hoodie,piec, <lora:den2SD:0:NONE>
1boy , outdoors,upper body,red hoodie,piec, <lora:den2niji:0:NONE>
N/A
Hidden For Public Users
1boy , outdoors,upper body,red hoodie,piec, <lora:den2niji:0:NONE>
1girl (watercolor:1.3),vivid color, <lora:den2niji:0:NONE>
N/A
Hidden For Public Users
1girl (watercolor:1.3),vivid color, <lora:den2niji:0:NONE>

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.