D&D General DALL·E 3 does amazing D&D art

More explorations of Orcish feminity. Dangerous waters, many images were NSFW or otherwise ludicrous, but these fit the bill

pig-faced beautiful graceful lithe muscular green Orc lady in plate mail contemplating her bloody axe, burning castle, high quality digital painting



pig-faced beautiful graceful lithe muscular green Orc lady in leather armor contemplating her bloody axe, burning castle, high quality digital painting



pig-faced beautiful graceful lithe muscular green Orc lady dressed aa Medieval queen giving a stirring speech to a crowd of pig-faced Orcs whoncheer, Castle grounds, high quality digital painting



pig-faced beautiful graceful lithe muscular green Orc lady dressed as a roman empress giving a stirring speechfrom a castle balcony, high quality digital painting




pig-faced beautiful graceful lithe muscular green Orc lady dressed as a Catholic priestess giving a stirring speech from a temple pulpit, high quality digital painting




pig-faced beautiful graceful lithe muscular green Orc lady dressed as a modest pirate firing a flintlock pistol, coastal fortress on fire, high quality digital painting



pig-faced beautiful graceful lithe muscular green Orc lady dressed in an 18th century military uniform attacking with a rapier, sunlit garden, high quality digital painting



And some I lost the prompt, sorry:

Dwarven feminity.is, however, much more harrowing. Many Bothans dies to bring this much out of the experiment, @Reynard

Going for an aasimar using his healing hands on a sick villager here:





Prompt: Holy Adonis male armored human with glowing eyes and fair skin healing a sick villager with his bare hands. A holy glow surrounds his hands. Other villagers look on in awe. Setting is medieval village with tudor cottages. Rural. Oil on canvas.

Li Shenron said:

Still some issues with the number of fingers wondering why that is so hard for AI to manage...

Click to expand...

Missed this before, but I can give some answers here. I am not an expert at all, but I've been consuming Numberphile and Computerphile stuff that discusses this, as well as some things from other prominent math youtubers that go into the science of it (and actually have the accreditation to know what they're talking about.)

More or less, pictures about humans usually involve very simple parts arranged in pretty simple ways. Faces are extremely important, featured in almost every image about people, and generally follow very simple patterns that are easy to recognize and reproduce. Likewise, limbs and torsos are quite simple to model. Clothing is a bit more complex, but it too tends to follow certain patterns just because...well, it's usually cloth draped over a body, so it has common physics. Armor, likewise, follows patterns. Both of them are more complex than faces or limbs, but not that much more.

Hands, on the other (heh) hand? Good Lord. They're incredibly complex. They have to be at the end of arms, that's a blatant association. But fingers can take all sorts of very subtly different orientations and angles, and worse, they can easily blend together into a single blob or otherwise smudge out and lose detail. Hands are very rarely the central focus of an image, almost always at least somewhat peripheral, which means AI training algorithms will place less emphasis on those parts of the image. There are many, many, MANY photos of humans which don't even show hands at all, while there are comparatively almost none that show only hands and not faces.

So...yeah. Hands have lots of fine detail that is easy to miss, they can take an enormous variety of positions which (to an AI) all look like completely different objects, and they're almost always at the periphery or at least away from the central focus of the image, which means the AI both collects less data and makes more approximations when asked to generate data.

There's a reason we have sign language via hands, not via faces. Hands can carry enough linguistic information to communicate extremely subtle syntactic and semantic detail. Faces....not so much.

Prompt: a dark skinned mother night inside a bronze cauldron that is flying off the ground while she holds an ornate wooden spoon in one hand in a dark forest, digital art

These two just dropped, because theybwere waiting without the boost:

strong beautiful Elven lady pirate attacking the camera with a cutlass, top of a burning castle wall, high quality digital painting



strong short Dwarven pirate walking with a warhammer, moonlit town street, high quality digital painting

Bing doesnt let me do pictures today.

I think I made it angry!

I like trying the same prompt in different styles and seeing what comes up

I tried to make an image of a goblin PC from a campaign I'm running, a beast conclave ranger (the revised UA ranger). The image creator hasn't got the ken of crossbows, it seems. Also, some of the giant spiders are just... disturbing.



I think the last photo is probably the best in terms of the crossbow and spider quality.

The prompts I used were:
A goblin is a small, slender, green-skinned humanoid, about three feet tall, with long pointed ears, sharp crooked teeth, yellow eyes with cat-like irises, and green skin. This goblin is laughing maniacally while riding a giant spider and wielding a crossbow. Highly detailed fantasy painting.

A goblin is a small, slender, green-skinned humanoid, about three feet tall, with long pointed ears, sharp crooked teeth, yellow eyes with cat-like irises, and green skin. A civilised goblin, wearing leather armour, is laughing maniacally while riding a man-sized spider and wielding a crossbow. Highly detailed fantasy painting.