AI(Stable Diffusion 1.5模型)眼里,艺术家们的风格是这样的。
注意:这些图样可以参考,不过他们更多是对艺术家作品某些维度的模仿。比如:颜色、艺术形式、领域等)。在用AI生成图像时,其他提示词同样重要。
不过,这些图样依然值得参考。
把图像拖到这个页面,相关信息会自动提取出来。.
Stable Diffusion1.5版本是基于512X512尺寸的图像训练的,2.1基于768x768, XL是基于1024x1024。 我们在设置长宽尺寸的时候如果是 128的倍数,效果可能会更好一些。不过其他数值也是可以的。
Some of the common ratios in SD dimensions:
| Square | 1:1 | 512 × 512 |
| Photo | 2:3 | 512 × 768 |
| Photo | 3:4 | 512 × 683 |
| Social Media | 4:5 | 512 × 640 |
| Standard Monitor | 16:9 | 910 × 512 |
| Monitor | 16:10 | 819 × 512 |
| UltraWide Monitor | 21:9 | 1195 × 512 |
Use only-data.html for a version without images.
That page also includes a list of all artists that were checked for availability.
Information on how the images were generated and how to check if an artist style is available can be found on the documentation page.
The JSON data files had to be changed to .js and wrapped with a variable to allow offline use (CORS).
A BIG THANK YOU TO
Code from Himuro-Majika's Stable Diffusion image metadata viewer browser extension
Reading metadata with ExifReader, extra search results supported by String-Similarity
Lazyload Script from Verlok, webfont is Google's Roboto, SVG icons from Ionicons
Automatic1111 for the Stable Diffusion Web UI
Stable Diffusion by LMU and stability.ai
Links that helped me understand the technical side of Stable Diffusion (no affiliation):
All information has been collected with the utmost care, however, mistakes happen. Location information is sometimes difficult when artists move very early in life, or the indication of the era, if the lifetime falls between two centuries.
In case something breaks, allows you to save a backup of your favorite styles.
Clicking 'Import' will replace your liked styles with what is in this textfield.
Leave field empty to delete all likes.