这是一个中国的江南水乡写实风景模型，基础模型使用的是sd xl 1.0 base。
Training
Key words： jiangnan
Caption: caption拼接了clip interrogator 和wd14 tagger的结果，并剔除了wd14 tagger结果中无用的词和已经在clip interrogator结果中出现的词。
使用了60张分辨率为1152x896的风景图片训练。
How to Use
Prompt：你可以仿照clip interrogator和wd14 tagger的句式，描述你想生成的内容。或者可以参考我训练集的样本，替换某些词以生成你想要的内容。
佛塔，湖
jiangnan, a pier with a person standing on it at sunset or dawn over a lake with a pagoda in the background, scenery, sky, cloud, outdoors, reflection, water, tree, mountain, bridge
绿色，建筑，湖
jiangnan, a river running through a lush green forest next to a building with red lanterns on it's windows, scenery, sky, grass, outdoors, tree, day, blue sky, reflection, house
塔，公园，落日
jiangnan, a pagoda in a park with a sunset in the background and a pond in the foreground with a rock and grass path, scenery, sky, cloud, outdoors, architecture, east asian architecture, tree, nature
Others： 使用训练时用的分辨率1152x896 可以得到更好的结果。
Have fun!
Description
trained by 60 jiangnan landsacape images
FAQ
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.