这个模型在dreamshaper上进行的微调,使用了上百万张挑选出的高审美的图片,只需要很少的关键词就可以生成非常漂亮的构图和光影.在场景/建筑/风景等几乎所有领域都有不错的表现.lora适配性也非常好.
this model is fine-tuned from DREAMSHAPER, uses millions of selected, highly aesthetic images, requiring only a few keywords to generate very beautiful compositions and shadows. Good well in almost all areas like scenes / architecture / landscape. The lora fit is also very good.
以上链接是一些sd模型的测试图对比,为了对比模型的基础能力,只使用了提示词,未使用lora等额外节点. 除了本模型外还包括dreamshaper/sd 1-5/ sd xl 1.0,此页面会不断扩充.
The above link is the test map comparison of some sd models. In order to compare the basic ability of the model, only the prompt words are used, and additional nodes such as lora are not used. this page includes models as dreamshape r/sd 1-5 / sd xl 1.0....... , this page will be updating constantly.
Description
FAQ
Comments (4)
pruned 2gb version plz
I really love the flexibility of this model. It handles LORAs well, and is extremely flexible. You can really squeeze some intentional and coherent compositions out of it. If you're looking for a break from the usual, this is it.🙏
I posted some of my images. The samples are great but they don't do it justice. I mean that in the most flattering way!
Somehow, It's impossible to get bad results from this model.
How on earth did you manage to do that?
Thx for this gem.
agreed!