DGirl

CHECKPOINT
Original


Updated:

36

v4.1 长图,宽图优化,出图男女皆可,很好的提示词响应

交流:651194700

不填词,tile贼好用

1girl,配上一些魔法,发挥想象力吧,负面描述这里取

(worst quality:1.4), (low quality:1), (normal quality:2),badhandv4,web/image/995cfee47d3e2908b971ea43feacdd8f9bc09416282b843ff3538f143b81abda.png

建议:采样步数20,高清修复(高分迭代步数)10,近景重绘幅度0.15左右,中距离及远景0.5

全身及远景打开adtalier,看个人喜好 采样器 dpm++ 2m karras

部分服装类会出现权重偏移,可以适当降低权重确保出图效果,

近距离诸如closeup之类的描述词不需要开太大的重绘幅度,0.15左右即可(高了变大妈)。

模型光影方面表现还可以,个人比较喜欢皮肤的纹理,背景比较真实,有一定的风格,具体还是看大家拿去测试吧

Version Detail

SD 1.5
<pre><code>V5 has been adjusted for nearly a month, just to pursue continuous optimization, down to the hairline. If you don’t want glue to appear, please use a special negative description or import an example image to generate it. When generating online, adjust the negative weight appropriately and reduce the redrawing range. Please use it for half the body or the whole body. Open ADetailer. Please open ADetailer to generate pictures above half body. Reduce the use of embedding. Badhandv4 is recommended. Negative prompt:(worst quality:1.6),(low quality:1.6),(normal quality:1.6),lowres,bad anatomy</code></pre>

Project Permissions

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated images

  • Use on generation services

  • Sell this model or merges

Comments

Related Posts

No posts yet
Describe the image you want to generate, then press Enter to send.