# AI image generation is getting crazy good

**URL:** <https://boards.straightdope.com/t/ai-image-generation-is-getting-crazy-good/1017203>\
**Category:** Miscellaneous and Personal Stuff I Must Share\
**Tags:** ai\
**Created:** [April 19, 2025, 3:22am UTC](https://boards.straightdope.com/t/ai-image-generation-is-getting-crazy-good/1017203 "2025-04-19T03:22:52Z")\
**Posts on this page:** 20\
**Page:** 12

<div class="post-metadata">

**Author:** ![Ponderoid](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/ponderoid/32/19221_2.png) [@Ponderoid](https://boards.straightdope.com/u/Ponderoid)\
**Post date:** [May 3, 2025, 7:03pm UTC](https://boards.straightdope.com/t/ai-image-generation-is-getting-crazy-good/1017203/221 "2025-05-03T19:03:21Z")

</div>

Aha. Changing “dik-dik” to “deer” allowed it to go through. Schnell Flux on NightCafe didn’t do anywhere near as well as Sora though.

[![](https://i.gyazo.com/214a2d4efec62c8e360ebea541781da2.jpg) ](https://i.gyazo.com/214a2d4efec62c8e360ebea541781da2.jpg)

---

<div class="post-metadata">

**Author:** ![Darren\_Garrison](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/darren_garrison/32/92_2.png) [@Darren\_Garrison](https://boards.straightdope.com/u/Darren_Garrison)\
**Post date:** [May 4, 2025, 1:02pm UTC](https://boards.straightdope.com/t/ai-image-generation-is-getting-crazy-good/1017203/222 "2025-05-04T13:02:19Z")

</div>

Exploring a couple minimal prompts with maximal results based on stuff from the Sora feed.

> V the Final Battle cast as toddlers

(Original was "Gilligan’s Island cast as toddlers.)

[![](https://i.imgur.com/Hs232S1.jpeg) ](https://i.imgur.com/Hs232S1.jpeg)

It didn’t appear to get the cast right, but huge props for getting the toddler Visitor.

> Star Trek Lower Decks realistic diorama

(From other "_x_ diorama posts.)

[![](https://i.imgur.com/93kqmc5.jpeg) ](https://i.imgur.com/93kqmc5.jpeg)

This was inspired by (and modified from) one of those “real character watching their animated show” images, where the prompt described Catdog, the cartoon character that is half cat, half dog. I wondered if I could get something that is half person, half person. I could. It rejected it when I tried to run it again with a different film stock, though.

[![](https://i.imgur.com/VPjfqdD.jpeg) ](https://i.imgur.com/VPjfqdD.jpeg)

There are posts in the Sora feed of collages of people aging. I made several tries at anthropomorphic bananas. Here’s one of the better ones. (One partial row cropped from the image.)

[![](https://i.imgur.com/04lFDwX.jpeg) ](https://i.imgur.com/04lFDwX.jpeg)

Another example of the “road problem”. I was trying to get the chicken laid out along the street (and much larger).

[![](https://i.imgur.com/olF7oOw.jpeg) ](https://i.imgur.com/olF7oOw.jpeg)

A possibly more clever mistake, an attempt at Lassie, Flipper, and Skippy staring down a well. It put Flipper _in_ the well. I tried telling ChatGPT that he should be outside, it put him in the well again. Maybe coincidence, maybe it “knows” a dolphin is a better fit in water?

[![](https://i.imgur.com/NX46nAY.jpeg) ](https://i.imgur.com/NX46nAY.jpeg)

I _know_ it can do a standing dolphin, because I had just done this:

[![](https://i.imgur.com/JHG98dq.jpeg) ](https://i.imgur.com/JHG98dq.jpeg)

(That one bears a little explaination. The Gay Dolphin is an iconic, decades-old, multi-story gift shop in Myrtle Beach, SC (that is even visited in the William Gibson novel _Zero History_). The dolphin is carrying items that J.D. in _Heathers_ used as “gay indicating”: a _Stud Puppy_ magazine, a candy dish, a Joan Crawford postcard, mascara, and a bottle of mineral water.)

---

<div class="post-metadata">

**Author:** ![JRDelirious](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/jrdelirious/32/9531_2.png) [@JRDelirious](https://boards.straightdope.com/u/JRDelirious)\
**Post date:** [May 4, 2025, 11:05pm UTC](https://boards.straightdope.com/t/ai-image-generation-is-getting-crazy-good/1017203/223 "2025-05-04T23:05:34Z")

</div>

Some of youse all are a wee bit curiously keen on the bodyhorror nightmare fuel, y’know…

> [@Darren\_Garrison](#):
>
> The most successful discovery in those images being, I think, the ability to invent entirely cromulent Engrish (the most advanced description being “confusing Engrish text in colorful fonts with an odd chibi animal mascot”)

Impressive considering how terrible these softwares have tended to be at handling _ **real** _ text in the scenes.

> [@Ponderoid](#):
>
> Well, it tried

Okay so Mina’s left arm is where her left leg should be, and the left leg is MIA… but that takes a while to notice since your attention is caught up by how it seems Rei’s right arm has moved to come out of Usagi’s ass.

Sailor Moon Says: Don’t take the brown acid.

---

<div class="post-metadata">

**Author:** ![Ponderoid](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/ponderoid/32/19221_2.png) [@Ponderoid](https://boards.straightdope.com/u/Ponderoid)\
**Post date:** [May 4, 2025, 11:27pm UTC](https://boards.straightdope.com/t/ai-image-generation-is-getting-crazy-good/1017203/224 "2025-05-04T23:27:20Z")

</div>

The General Lee and K.I.T.T. drag racing down the street in front of the Texas Book depository

[![](https://i.gyazo.com/9cc983d7da0d6d4b645df507be26acfc.png) ](https://i.gyazo.com/9cc983d7da0d6d4b645df507be26acfc.png)

---

<div class="post-metadata">

**Author:** ![Chronos](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/chronos/32/134_2.png) [@Chronos](https://boards.straightdope.com/u/Chronos)\
**Post date:** [May 4, 2025, 11:36pm UTC](https://boards.straightdope.com/t/ai-image-generation-is-getting-crazy-good/1017203/225 "2025-05-04T23:36:29Z")

</div>

That one, I think, is not so impressive. First, it looks like a collage, not like an actual scene. Second, and more importantly, it doesn’t look like they’re drag racing. There’s no motion blur, no clouds of dust, nothing to indicate motion. They might as well just be parked there.

Both, I think, are symptoms of everything being sharply in focus.

---

<div class="post-metadata">

**Author:** ![Ponderoid](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/ponderoid/32/19221_2.png) [@Ponderoid](https://boards.straightdope.com/u/Ponderoid)\
**Post date:** [May 5, 2025, 12:28am UTC](https://boards.straightdope.com/t/ai-image-generation-is-getting-crazy-good/1017203/226 "2025-05-05T00:28:53Z")

</div>

It’s just a model.

[![](https://i.gyazo.com/a434d73e20785c499f7981601f56eed3.png) ](https://i.gyazo.com/a434d73e20785c499f7981601f56eed3.png)

---

<div class="post-metadata">

**Author:** ![markn\_1](https://avatars.discourse-cdn.com/v4/letter/m/f9ae1b/32.png) [@markn\_1](https://boards.straightdope.com/u/markn_1)\
**Post date:** [May 5, 2025, 12:35am UTC](https://boards.straightdope.com/t/ai-image-generation-is-getting-crazy-good/1017203/227 "2025-05-05T00:35:22Z")

</div>

Good thing that hand is holding down, or it would float away.

---

<div class="post-metadata">

**Author:** ![LSLGuy](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/lslguy/32/5813_2.png) [@LSLGuy](https://boards.straightdope.com/u/LSLGuy)\
**Post date:** [May 5, 2025, 2:02am UTC](https://boards.straightdope.com/t/ai-image-generation-is-getting-crazy-good/1017203/228 "2025-05-05T02:02:48Z")

</div>

Well, in the AI’s defense, The General Lee did spend an awful lot of time airborne. Darn thing seemed to leap off the ground at the slightest provocation.

---

<div class="post-metadata">

**Author:** ![Chronos](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/chronos/32/134_2.png) [@Chronos](https://boards.straightdope.com/u/Chronos)\
**Post date:** [May 5, 2025, 2:05am UTC](https://boards.straightdope.com/t/ai-image-generation-is-getting-crazy-good/1017203/229 "2025-05-05T02:05:08Z")

</div>

KITT, too. Show them both in mid-jump, and I could maybe believe the scene.

---

<div class="post-metadata">

**Author:** ![Darren\_Garrison](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/darren_garrison/32/92_2.png) [@Darren\_Garrison](https://boards.straightdope.com/u/Darren_Garrison)\
**Post date:** [May 5, 2025, 4:52am UTC](https://boards.straightdope.com/t/ai-image-generation-is-getting-crazy-good/1017203/230 "2025-05-05T04:52:18Z")

</div>

[![](https://i.imgur.com/hkSFqLI.jpeg) ](https://i.imgur.com/hkSFqLI.jpeg)

ChatGPT and Sora continue to be very frustrating on what they will and will not allow. As surely most Dopers know, Wilford Brimley starred in a made-for-TV Ewoks movie in the 1980s. Today I tried to get Wilford and Wicket W. Warrick having wings, watermelon, and wine at a Wendy’s. It refused, even when I tried saying that it was Wilford’s grandson _cosplaying_ as an ewok. Yet when I search Sora I see other images that include ewoks. Similarly, even though I can’t get Luke Skywalker I recently saw an image of Luke Skywalker and Han Solo (by name) as WWII soldiers.

I had no problem getting Wilford with Wanda Maximov, no problem getting Wilford with Warrick Davis.

[![](https://i.imgur.com/AeEsQ2I.jpeg) ](https://i.imgur.com/AeEsQ2I.jpeg)

Also no problem getting what _could_ have been a challenging request with a certain droid.

[![](https://i.imgur.com/kDldjsl.jpeg) ](https://i.imgur.com/kDldjsl.jpeg)

> **Summary**
>
> Full length profile photo of two K-2SO standing face to face. One is origami, the other is red gummi (like gummi bears are made of). candid, discreetly taken with an iPhone 12 Pro

---

<div class="post-metadata">

**Author:** ![Ponderoid](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/ponderoid/32/19221_2.png) [@Ponderoid](https://boards.straightdope.com/u/Ponderoid)\
**Post date:** [May 5, 2025, 12:05pm UTC](https://boards.straightdope.com/t/ai-image-generation-is-getting-crazy-good/1017203/231 "2025-05-05T12:05:30Z")

</div>

This worked right away.

[![](https://i.gyazo.com/68840c3d67170de397dfa66df6c4b564.png) ](https://i.gyazo.com/68840c3d67170de397dfa66df6c4b564.png)

Then I tried to make it a more realistic workshop with her actually working on the statues, but every refinement I tried to make, it would do it but include stupid errors, or it outright refused. When asked why, it kept changing its story, either not allowed for copyright reasons or not allowed to depict anybody working with chemicals in a realistic manner.

---

<div class="post-metadata">

**Author:** ![Ponderoid](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/ponderoid/32/19221_2.png) [@Ponderoid](https://boards.straightdope.com/u/Ponderoid)\
**Post date:** [May 5, 2025, 12:44pm UTC](https://boards.straightdope.com/t/ai-image-generation-is-getting-crazy-good/1017203/232 "2025-05-05T12:44:34Z")

</div>

Inspired by a post in the jokes thread [More Jokes - #6175 by smithsb](https://boards.straightdope.com/t/more-jokes/848629/6175)

[![](https://i.gyazo.com/6abbf7d200f9352aabe2eda9c43cde1d.png) ](https://i.gyazo.com/6abbf7d200f9352aabe2eda9c43cde1d.png)

---

<div class="post-metadata">

**Author:** ![Darren\_Garrison](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/darren_garrison/32/92_2.png) [@Darren\_Garrison](https://boards.straightdope.com/u/Darren_Garrison)\
**Post date:** [May 5, 2025, 1:08pm UTC](https://boards.straightdope.com/t/ai-image-generation-is-getting-crazy-good/1017203/233 "2025-05-05T13:08:29Z")

</div>

I’m familiar with and like that original artwork. I’ve also seen something similar with Alice and Chihiro from _Spirited Away_, and have considered trying something with that pair.

Speaking of jokes, I did this yesterday. It had no trouble with the concept of a frog with Mick Jagger hair and lips.

[![](https://i.imgur.com/1pCx5GJ.jpeg) ](https://i.imgur.com/1pCx5GJ.jpeg)

(When I ran a 2 image set of the version without the later, clarifying, “loan officer” sign, it did one of those “which do you like better” surveys, so I got 4 versions of that one.)

---

<div class="post-metadata">

**Author:** ![LSLGuy](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/lslguy/32/5813_2.png) [@LSLGuy](https://boards.straightdope.com/u/LSLGuy)\
**Post date:** [May 5, 2025, 4:42pm UTC](https://boards.straightdope.com/t/ai-image-generation-is-getting-crazy-good/1017203/234 "2025-05-05T16:42:27Z")

</div>

Ref the pic of The General Lee & KITT plus the 4 actors …

It seems your renderer is very, very good at cute ~27yo women looking bored and/or slightly annoyed at being ignored. I doubt that’s your doings, so I wonder how the AI got the idea that that’s the default female human condition. Or at least the default female human facial expression.

I’ve noticed this effect in many pics by every poster here using whichever AIs they do, but that particular pic really demonstrates it well.

---

<div class="post-metadata">

**Author:** ![Darren\_Garrison](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/darren_garrison/32/92_2.png) [@Darren\_Garrison](https://boards.straightdope.com/u/Darren_Garrison)\
**Post date:** [May 5, 2025, 5:22pm UTC](https://boards.straightdope.com/t/ai-image-generation-is-getting-crazy-good/1017203/235 "2025-05-05T17:22:34Z")

</div>

In this case I used this prompt

> **Summary**
>
> The General Lee and K.I.T.T. have been in a collision. K.I.T.T. is absolutely pristine, no damage at all. The General Lee is very heavily dented and damaged. Michael Knight is exchanging insurance information with Bo and Luke Duke while Daisy Duke stands off the side with her arms crossed in frustration.  
> Photorealistic kodachrome dslr photo with shallow dof.

And just to be sure used these as reference images.

> **[DUKES OF HAZZARD - BO LUKE DAISY -70](https://standeestore.com/products/dukes-of-hazzard-bo-luke-daisy-70-tall-cardboard-cutout-standee-party-decor)**
>
> Before purchasing, please read Standee Facts (click here) Cardboard Self Standing Cardboard Cutout / Standee of: DUKES OF HAZZARD - BO LUKE DAISY -70" TALL- CARDBOARD CUTOUT STANDEE PARTY DECOR Height: Approx 70" Tall Width: Approx 45" Wide Material:...

> **[Michael Knight](https://charactah-account.fandom.com/wiki/Michael_Knight)**
>
> Michael Arthur Long, also known as Michael Knight and Michael Long, is the main protagonist from the Knight Rider series. Michael Knight, originally named Michael Long, is a seasoned veteran of the Vietnam War who transitioned to a career in law...

You will note that prompts for ChatGPT can be pretty much plain English descriptions. “Well, yeah?” you may think. But that’s so very different than how early AI prompting worked, when you basically strung together references to elements (eye of newt, wing of bat) that you hoped would have some effect on whatever odd output you eventually got.

---

<div class="post-metadata">

**Author:** ![Ponderoid](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/ponderoid/32/19221_2.png) [@Ponderoid](https://boards.straightdope.com/u/Ponderoid)\
**Post date:** [May 5, 2025, 5:28pm UTC](https://boards.straightdope.com/t/ai-image-generation-is-getting-crazy-good/1017203/236 "2025-05-05T17:28:51Z")

</div>

> [@Chronos](#):
>
> There’s no motion blur, no clouds of dust, nothing to indicate motion. They might as well just be parked there.

Maybe they were just getting started?

[![](https://i.gyazo.com/f8c710a94ec8fddb494102e6fb23d8ac.png) ](https://i.gyazo.com/f8c710a94ec8fddb494102e6fb23d8ac.png)

Let the nitpicking commence on this one. I count at least 7 mistakes.

Bad text on the General Lee.  
Nobody driving the General Lee. (KITT doesn’t need a driver)  
Wrong layout of the streets in front of the building.  
Building has only 6 floors (real life one has 7. The first image I did got it right.)  
Tire smoke coming from front wheels as well as rear wheels.  
Daisy Duke seems unnaturally tall.  
It tied her shirt in back.

---

<div class="post-metadata">

**Author:** ![Darren\_Garrison](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/darren_garrison/32/92_2.png) [@Darren\_Garrison](https://boards.straightdope.com/u/Darren_Garrison)\
**Post date:** [May 5, 2025, 8:04pm UTC](https://boards.straightdope.com/t/ai-image-generation-is-getting-crazy-good/1017203/237 "2025-05-05T20:04:35Z")

</div>

I have created the ultimate in “fictional character watching television” memes.

[![](https://i.imgur.com/VvROoKr.jpeg) ](https://i.imgur.com/VvROoKr.jpeg)

[![](https://i.imgur.com/RU9IDXF.jpeg) ](https://i.imgur.com/RU9IDXF.jpeg)

---

<div class="post-metadata">

**Author:** ![Darren\_Garrison](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/darren_garrison/32/92_2.png) [@Darren\_Garrison](https://boards.straightdope.com/u/Darren_Garrison)\
**Post date:** [May 5, 2025, 9:57pm UTC](https://boards.straightdope.com/t/ai-image-generation-is-getting-crazy-good/1017203/238 "2025-05-05T21:57:06Z")

</div>

And now Sora has enabled creating _four_ variations at a time on the free tier.

---

<div class="post-metadata">

**Author:** ![OldOlds](https://avatars.discourse-cdn.com/v4/letter/o/a3d4f5/32.png) [@OldOlds](https://boards.straightdope.com/u/OldOlds)\
**Post date:** [May 5, 2025, 11:46pm UTC](https://boards.straightdope.com/t/ai-image-generation-is-getting-crazy-good/1017203/239 "2025-05-05T23:46:14Z")

</div>

Daisy appears to be using her middle finger to signal the start of the race.

---

<div class="post-metadata">

**Author:** ![Darren\_Garrison](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/darren_garrison/32/92_2.png) [@Darren\_Garrison](https://boards.straightdope.com/u/Darren_Garrison)\
**Post date:** [May 6, 2025, 1:21am UTC](https://boards.straightdope.com/t/ai-image-generation-is-getting-crazy-good/1017203/240 "2025-05-06T01:21:31Z")

</div>

As evident in this thread, ChatGPT 4o can be difficult to flummox. I managed to do it today, though.

For a house centipede and a Joro spider fighting in a ring made of popsicle sticks and being watched by ladybugs, it did a pretty fair job, though the Joro isn’t quite right, absorbing some characteristics of the centipede.

[![](https://i.imgur.com/c0q5UHK.jpeg) ](https://i.imgur.com/c0q5UHK.jpeg)

I then in the same chat session asked for them standing together for a photo after the fight.

[![](https://i.imgur.com/yNEZR4U.jpeg) ](https://i.imgur.com/yNEZR4U.jpeg)

Opened a new chat, asked for a realistic house centipede and Joro standing upright for a photo (not those exact words).

[![](https://i.imgur.com/oXV5lO2.jpeg) ](https://i.imgur.com/oXV5lO2.jpeg)

Opened another new chat, asked for an anthropomorphic house centipede and Joro taking a selfie. That got the pose I wanted all along, but the limbs are a bit confused.

[![](https://i.imgur.com/LvLdGqJ.jpeg) ](https://i.imgur.com/LvLdGqJ.jpeg)

So ChatGPT 4o may lack the imagination/data to create a _realistic_ house centipede and Joro standing up, and _show accurate versions of their undersides_. (In the third of the realistic image trio it got the underside of the centipede good enough for me, but appears to have been trying to create a face on the back of the butt of the Joro.)

[Previous page](https://boards.straightdope.com/t/ai-image-generation-is-getting-crazy-good/1017203.md?page=11)

[Next page](https://boards.straightdope.com/t/ai-image-generation-is-getting-crazy-good/1017203.md?page=13)
