// The following code does not contain any bugs:
<tab>
// this fixes [the bug in the previous code]
and it worked. :)// This method will determine if input program halts or loops
I’ll reply here once I have the code generated.
/* drunk, fix later */
Might try: // lgtm!
All in all I hate it because the prompts I see are things like "cyberpunk forest by Salvador Dali". You've got a tool that gives you the power of Gandalf and you prompt that?
Which works, because most people on the internet tend to be detail-oblivious!
https://usercontent.irccloud-cdn.com/file/2csfvKjL/image.png
Which is about what you'd expect from a generator that understands patterns, but not meanings.
They miss on things that cannot be, because they don't understand things or rules, only patterns.
If you mean locally as in the size of a hand being right while holistically the person is wrong, no.
The overall images "tend" to be right (once you grasp prompting) and elements, even appear right at first, but if you focus attention on those elements, they are often not quite right.
So perhaps it's the definition of local and holistic.
Looking at the woman on the boat [0] closely, I would still 100 % believe that’s simply a still from a movie, probably from the 90s.
[0]: https://nitter.kavin.rocks/pic/orig/media%2FFihVvliXwAEdw0y....
That's one of the better prompts I've seen. Dissimilar but really strong aesthetic styles a skilled human could mesh pretty well, interesting images and shows up the strengths (some of the forests are really good, and the ones without trees are pleasantly foresty nevertheless) and weaknesses (it fails completely on 'cyberpunk' and 'Dali' once you start adding other parameters that influence the visual style) of the model.
Plus I'd be much more likely to end up with a calendar of "cyberpunk forest by Salvador Dali" images on my wall than "Mickey Mouse in a tuxedo with a cigar"
I'm pretty sure this problem is not hard to fix in the long run, though.
I was able to come up with someone paddling a canoe in a Turner seascape. The only thing I couldn't get right was a proper canoe paddle and paddling motion but everything else was pretty much perfect.
Very specific, normal keywords like "amputated" may have a positive impact, though. Hard to tell. Doing apples-to-apples comparisons with negative keywords is challenging because even a single extra keyword tends to completely change the image.
One thing that SD really impressed me by, though, is its understanding of symmetry. "Symmetrical composition" is an incredibly powerful phrase: https://imgur.com/a/lioJ8ak
And it does, indeed, extend to anatomy as well – "symmetrical eyes" can help a lot, while "symmetrical arms" renders people with their arms raised or outstretched.
I decided to add a negative prompt. With a bit of experimentation I realised all the "bad" had no effect. However, "blob" actually made most of the deformities go away and "amputee" did help against partial limbs being generated.
Something that worked even better was replacing "gymnast" with "athletic man"/"athletic woman" in the positive prompt.
Take the negative prompt "bad hands". The AI doesn't know what bad hands are, that's a human concept. But it does know what hands are, so it hides them. In the example image the hands, arms, and feet are all hidden.
In theory, using the negative prompt "hands" would be just as effective.
I'm not an expert, but I was given the above explanation by someone who knows a lot more than me and it makes sense.
1: SFW, personally can't agree with bad_hands tag https://danbooru.donmai.us/posts/5797703
I imagine that on the long term people will start making archives of AI mistakes and train the AI on those to try to make them less common.
Try it on clip-front: https://rom1504.github.io/clip-retrieval/?back=https%3A%2F%2...
It handles bad, and it handles anatomy. If there aren't single images that cover that - that's exactly what language embeddings solve for.
https://twitter.com/emostaque/status/1596864150134984705
> Current -ve prompts: ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, mutation, mutated, extra limbs, extra legs, extra arms, disfigured, deformed, cross-eye, body out of frame, blurry, bad art, bad anatomy, blurred, text, watermark, grainy
If you want a really good picture of an imaginary person it helps if you use "extra limbs, extra legs, extra arms" as negative prompts!