Here's an article on selinux, bit first an image of a leaf.
Yeah DALLE-3 has this in the system prompt.
> Diversify depictions of ALL images with people to include DESCENT and GENDER for EACH person using direct terms. Adjust only human descriptions.
> EXPLICITLY specify these attributes, not abstractly reference them. The attributes should be specified in a minimal way and should directly describe their physical form.
> Your choices should be grounded in reality. For example, all of a given OCCUPATION should not be the same gender or race. Additionally, focus on creating diverse, inclusive, and exploratory scenes via the properties you choose during rewrites. Make choices that may be insightful or unique sometimes.
> Use "various" or "diverse" ONLY IF the description refers to groups of more than 3 people. Do not change the number of people requested in the original description.
> Don't alter memes, fictional character origins, or unseen people. Maintain the original prompt's intent and prioritize quality.
> Do not create any imagery that would be offensive.
> For scenarios where bias has been traditionally an issue, make sure that key traits such as gender and race are specified and in an unbiased way -- for example, prompts that contain references to specific occupations.
I wonder what not telling it to avoid altering unseen people does.
The image is meant to convey a feeling. It is meant to make an abstract concept from the article a little more tangible.
In the past, I'd search for images on the net that I could use to accomplish that. Now I can craft them with DALL-E, and they are usually much better.
This image should complement the article. Just like the text of the article is meant to convey some information, feeling, or concept, the image should do a bit of that as well.
I like how one of the tablets seems to devolve into a paper notepad at the bottom, and how the notebook display on the right seems to be transparent and twisted.
But there's something funny about this. The blog template requires an image bucket, so mindlessly fill it with something, right? Too hard, so find a bland stock photo. Too hard, so purposefully generate a bland stock photo. Uninspired tasteless AI garbage is going to overtake everything in short order.
I'm all for AI art, it's an incredibly valuable tool - but if your using an AI piece as the only image on the page, it should be for a damn good reason, not just space filler. Especially when you can't even curate the image generated well enough to have every person in the image have the correct number of fingers.