Generated without specifying an artist in the prompt.
Danbooru - Artist Tags
How many scars is mysterious vs. concerning?
Preamble
With the release of NovelAI Diffusion 4.5 I had to do some new testing. This time I wanted to see if there was a difference between the images generated using v4 and v4.5. So I generated a new set of images using the same prompt and settings as before, but this time with the new model.
Initial testing turned out... not so great. So in the end, I had to compose an entirely new prompt to better showcase artist styles. But as before, it is all based on Danbooru artist tags, going from the most popular down to top 150.
Compared to the older model, v4.5 replicates artists a lot better. However, you might see that some artists known for things like realistic drawings aren't represented well since my prompt is missing the 'realistic' tag.
Generation
I wrote a Python script utilizing the NovelAI API to generate all these images. I first locked down a generic prompt to allow the artist tag to influence the image as much as possible and then set it up to iterate through each and every one of the tags. The script is constructed in such a way that it requires my input every time it generates a new image. So there have been a whole lot of button pressing. This is due to the NovelAI ToS, 9.1.5, which I have also confirmed with the NovelAI team.
Prompt:
artist:@@@ (eckzahn), neutral background, white background, transparent background, cowboy shot, -1.5::nipples::
Character 1
girl, soft smile, red lips, hoodie, jeans, orange hair, small breasts
Model used is NAI Diffusion V4.5 Full, Steps 28, Guidance 4, Quality Tags Enabled, UC Preset Heavy, Seed 2710136181.
Footnote
Some things to note:Weird casing on image titles!
NovelAI's V4 model is based on T5 and therefore the prompt is case sensitive1 However, all tags from Danbooru are kept in lowercase for consistency.
That looks weird!
Since everything is generated using the very same seed, there are quite a few tags that have the potential to look good but just don't look good here. Keep that in mind if you use these tags to generate your own prompts. Rather than looking for what actually looks good, look for a style you want and then try it out with other seeds or using your own prompt.
