云想衣裳花想容,春风拂槛露华浓。
———— 唐·李白
大家好,我是chosen鲷,这次带来的是露华浓Lora模型。
名称取自李白的诗句,这个模型和我的另一个古风模型花想容有类似之处,但画风又不太一样,所以我采用了古诗的后半句为其命名,主要是使用niji的一些中国风的图片作为训练集,想要训练一个古风模型,同时又有点niji的画风。这个模型稍微有点过拟合,权重不要太高,最高也就0.9,然后他的兼容性比花想容好很多,还可以画男人,例图里面那样的,大家可以根据自己需要尝试,顺带一提,这个lora模型不是只能画古风,画现代场景也可以的,横版竖版均可,分辨率512*768/512*768。关键词midjourney portrait,记得高清重绘,重绘方式建议ESRGAN_4X,重绘幅度0.5
建议使用我的chosen irses或者chosen mix模型,跟其他的大模型相性也还不错,都可以尝试一下,vae搭配蜡笔pastel即可(如果你用ghost一类的,则不需要外挂vae)。例图是能够读取tag的,大家可以尝试一下。
感谢大家的下载使用,如果喜欢的话欢迎关注我,我的bilibili pixiv ID均为chosen鲷,欢迎大家关注我的频道https://space.bilibili.com/3867754?spm_id_from=333.1007.0.0,https://www.pixiv.net/users/40911695 谢谢。
Hi, I'm chosen 鲷, and this time I'm bringing a ancient Chinese style Lora model.
The name comes from Li Bai's poem. This model is similar to my other ancient style model, but the painting style is not the same, so I use the last half sentence of the ancient poem to name it, mainly using some pictures of niji's Chinese style as a training set, hoping to train an ancient style model while having some niji's painting style. This model is slightly over-fitting, the weight is not too high, the highest is 0.9, and then his compatibility is much better than the flower wants to accommodate, you can also draw men, like in the example figure, you can try according to your own needs, by the way, this lora model can not only draw ancient style, draw modern scenes can also be, horizontal version and vertical version can be. Resolution 512*768/512*768. Key words: midjourney portrait, remember to redraw in high definition. The redrawing method is suggested as ESRGAN_4X, and the redrawing range is 0.5
It is recommended to use my chosen irses or chosen mix model, which is also quite good with other large models, you can try vae with pastel (if you use ghost, you do not need to external vae). Example diagram is able to read tag, you can try it.
Thank you for downloading and using, please follow me if you like, my bilibili pixiv ID is chosen Snapper, Welcome to focus on my channel, https://space.bilibili.com/3867754?spm_id_from=333.1007.0.0, https://www.pixiv.net/users/40911695, thank you.