A collection of what Stable Diffusion imagines these artists' styles look like.
While having an overview is helpful, keep in mind that these styles only imitate certain aspects of the artist's work (color, medium, location, etc.). They are limited by the rather superficial knowledge of SD, but can probably give you a good base for your own creations.
Stable Diffusion was trained with base dimensions of 512 pixels (SD 1.5) and 768 pixels (SD 2/2.1).
While it's not necessary to stick to multiples of 128, it's a good place to start.
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 |
All information has been collected with the utmost care, however, mistakes always 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.
All images were generated with either the Deliberate v2 or the DreamShaper 3.2 Checkpoint.
Sampler was DMP++ 2M Karras or DMP++ SDE Karras, depending on the better result.
Final resolution never smaller than 768px × 768px.
The prompt for the textbox was:
--prompt style of ArtistName --negative_prompt nude, nsfw, frame, border, text
While Deliberate has some NSFW Checkpoint mixed in and needs 'nsfw' in the negative prompt, DreamShaper likes manga a lot and frequently requires 'manga, anime' in the np.
--prompt style of ArtistName, woman --negative_prompt same as above
--prompt style of ArtistName, Henry C_____ --negative_prompt superman
--prompt style of ArtistName, city --negative_prompt text, frame, border
Why these prompts?
The first line produces a broad, uninfluenced impression of what is most common for that artist (landscape, person, etc.).
With 'woman', you will get a wider range of portraits that are more in line with the artist's personal aesthetic.
For the third line: The actor Henry C. is currently well-known and has been well-trained into SD. You can also judge the dominance of a style if he is still rendered normally (weak artist style) or when his superhero costume appears.
The last line, 'city' (sometimes replaced by 'village'), will give you a good idea of how houses, people, and technical items (cars, bikes, etc.) appear.
Use only-data.html for a version without images.
That page also includes a list of all artists that were checked for availability.
The JSON data files had to be changed to .js and wrapped with a variable to allow offline use (CORS).
Links that helped me understand the technical side of Stable Diffusion (no affiliation):
A BIG THANK YOU TO
Lazyload Script from Verlok, Webfont is Google's Roboto, SVG Icons from Ionicons, MattiasW's ExifReader
Code from Himuro-Majika's Stable Diffusion image metadata viewer Browser Extension
Automatic1111 for the Stable Diffusion web UI
Stable Diffusion by LMU and stability.ai