Models>

背景及距离控制/background & distence control/背景と距離制御

No Images Found

Try Our Text To Image Demo

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 not available for use and might generate different characters compared to the ones seen in the images.

Model Description by Creator

权重设置为负值让背景更深邃,人物镜头离得更远,使背景更具有规则化;

权重设置为正值让背景变简单,人物离镜头更近;使背景减少规则化;

镜头/距离的效果需要人物词和背景词占比不均匀时才容易触发,lora会加大这种不均衡,

假如写了非常多关于人物的词,而只有很少的背景词,而把人物维持高清拉远.现在可以办到了,用的另一个lora《边缘弱化/强化》,取负值,详见人群的图例。

使背景变得层次丰富或者简单的效果则没有限制。 无触发词,直接加载即可。推荐值-2~+2,对画面几乎没有污染-3,+3的值也可以使用,请自行尝试。

用法1:加非常多的背景词,并强调了人物词的权重。平衡人物词和背景词的占比。使得人物拥有足够多的像素,同时增加了背景丰富度和细节,使用-2的权重。

用法2:在画建筑、或者教室、超市货架等场景的时候使用负的权重,可以使背景更具规则,详见图例4,超市货架的例图。

用法3:想要突出主体、不想背景喧宾夺主的时候,可以设置正的权重,扁平化背景。正的权重也有非常细微的平滑线条的作用,适用于简单卡通形象的创作。

和lora 《背景细节增强/简化》一起使用将会得到令人惊异的效果,详见图例5和图例6

Setting the weight to a negative value makes the background deeper with more ditails and make the character farther to the viewer;

Setting the weight to the proof value makes the background simpler with less ditails and make the character closer to the viewer;

The effect of the lens/distence should be triggered when the proportion of character words and background words is unbalanced, and Lora will increase this imbalance.

If you write a lot of words about characters and only use little background words. Now you can maintain high definition and distance the characters, you can use another Lora called Edge weaken/strengthen', which takes a negative value, effect as shown in the legend of the crowd of girls.

The effect of making the background deeper or simpler is always work.

No trigger words, just set it directly. The recommended value is -2~+2.

Because this lora has almost no pollution to the picture, so a value of -3 and+3 can also be used. Please try it by yourself.

Usage1: Add a lot of background words and emphasize the weight of character words. Balanced the proportion of character words and background words. Make the characters have enough pixels while increasing background richness and detail, using -2 weight.

Usage 2: When drawing background, such as buildings, classrooms, or supermarket shelves, using negative weights can make the background more regular. Please refer to sample 4, an example of supermarket shelves.

Usage 3: When you want to highlight the subject and not want the background to dominate, you can set a positive weight to flatten the background. Positive weights also have a very slightly effect on smoothing lines, more suitable for creating simple cartoon characters.

Using it in conjunction with Lora<Background Detail Enhancement/Simplification> will achieve amazing results, as detailed in sample 5 and 6

重みを負の値に設定すると、背景がより深くなり、人物がより遠くになります。

重みを正の値に設定すると、背景がより簡単になり、人物がより近くになります。

レンズ/距離の効果は、人物提示語と背景提示語の比率が不均衡であることが必要とされ、このloraはその不均衡を大きくする。

もし人物に関する言葉が非常に多く書かれていて、背景語が少ないだけで、人物をハイビジョンに維持することができるようになったら、もう一つのlora『エッジ弱体化/強化』を使って、マイナス値を取って、女の子の群れの図例を詳しく見てください。

背景を豊かにしたり、簡単にしたりする効果には制限はありません。キーワードはありません、直接使用すればいいです。推奨値-2 ~+2は、画面には、ほとんど汚染されませんのて、-3、+3の値も使用できます、自分で試してみてください。

使い方1:非常に多くの背景語を加え、人物語の重みを強調した。人物語と背景語の比率をバランスさせた。人物に十分なピクセルを持たせながら、背景の豊かさとディテールを増やし、-2の重みを使用します。

使い方2:建築、あるいは教室、スーパーの棚などのシーンを描く時に、負の重みを使用して、背景をもっと規則的にすることができます、詳しくは図例4、スーパーの棚の例図を参照してください。

使い方3:本体を強調したいとき、背景が主客転倒したくないとき、正の重みを設定し、背景を平坦化することができます。正の重みはほんの少しけと、線を滑らかにすることができます、簡単なキャラクターの創作に適しています。

lora『背景詳細の強化/簡略化』と一緒に使用すると,凄まじい効果が得られる。詳細は図例5と図例6を参照

可以访问ritansonoac554的lora《背景细节增强/简化》链接

to accuss ritansonoac554‘s lora <Background Detail Enhancement/Simplification>

ritansonoac 554さんのlora『背景詳細の拡張/簡略化』リンクにアクセスできます

《背景细节增强/简化》

Images Generated With This Model

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>
1girl,collared shirt, skirt,(from above:0.85),dynamic pose,hands,(face),thigh,simple background,child, <lora:den2niji: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:den2niji: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.