Some more theatrical images, these were some of the better responses to prompts, the unexpected results were the best like when messing around with monochrome a sepia had splashes of color.

Just some new wet and pied pictures no theme.

A few last pies, retro themes and some foot stomps thrown in for extra and one World of Warcraft that didn't really work.

AI is evolving fast.
In mid 2024 I was using Bing which had severe restrictions.
I now us Google AI image generator, which I find much better.

I have looked back at some of my creations from a year ago, which looks.poor in terms of being realistic by current standards.

Kling2.1 is pretty impressive for a lot of things, I have been using it for a while, and seen the evolution and it is... impressive. At the moment they are trialling sound with video generation, based on what is in the video. Some of the times it gets it right... some of the times... not so much.

However, if you have ever considered trying it, I would give it a ... get creative, use the inbuilt deepseek prompt creator, or for those of you with ChatGPT, there are several GPTs for KlingAI prompt enhancement.

This post inspired me to recreate some of my older creations using Whisk that I did not feel were worthy of upload previously. I've included both the flawed, older images and new and hopefully improved creations, sometimes with multiple versions of the new images. Definitely interesting to see how much AI generation has advanced already.

I don't want to hurt anyone's feelings, but you're easily my favorite AI creator on this site, and have been since early on. You've always had so much variety in your outfits, poses, locations, and situations, and have inspired a lot of my own attempts. I especially like how you've put so much attention to realism and believability into them. Your subjects always look so natural.

Now, back to the topic...

I've been sorting through my neverending stock of images I've created over the last couple years, and I have entire folders I'm discarding because even though I was really proud of them at the time, my OCD perfectionist mind just can't justify uploading them when my new stuff is leaps-and-bounds better. I should really do what you did and recreate the old prompts.

Some probably will never be recreated to my desires, because the original results were strongly influenced by the generators training and quirks. Like, for example, DALL-E 3 had specific hairstyles and facial features that it would create without even being prompted that I haven't been able to get any other generator to recreate even with very detailed prompts. Different generators have unique clothing styles that others just don't seem to be able to recreate

Thank you for the kind words Kabe22, your creations are fantastic and we seem to have similar tastes. It's interesting that you bring up the quirks of the different generators, when creating these it was quite interesting to see the limitations that Google was giving me in recreating aspects of previous creations. Outfits, expressions, poses; sometimes quite similar to the original image, other times way different. There were definitely several attempts that the Google version never got right either and were discarded. Some of the older generators created some absolutely fantastic images that I really like, other than they are too cartoon-like for me, but newer generators just can't replicate the "vibe" of the original. I still struggle with messy images, and I respect the heck out of all of you that have mastered that style. I am grateful for this threads continued existence and all of the creators, it's a neat time capsule through the progress of AI images. And since I'm posting anyway, I'll add a couple that didn't make it into yesterday's post.

"So much for a romantic boat trip on the lake!"

A few more recent generations

I need to say it again. ChatGPT can produce some really striking imagery.

I've tried every possible description and combination to persuade Kling to create a dunk tank clip.
This is the best result so far.

I've been frustrated in attempts to get dunk tanks in images. The LLM generally ignores the prompt and puts the person facing the wrong way, or the seat floating over the middle of the tank, or the tank is too small.

You need to think laterally about what you're trying to achieve and what context does the model understand.
It is highly unlikely that it understands what a gungetank is. It also doesn't understand how a person would sit in it. You need to to be as specific as possible within the confines of the prompt.
If you are using GPT4o or Sora, you can sketch and image in pencil and upload it with specific instructions. It is smart enough to understand your sketch and notes.

You might try Whisk - I got OK results for "Office ladies and the Dunk Tank" from it.
https://labs.google/fx/tools/whisk

But you are correct - AI dunk tanks still have a ways to go.

I'm getting consistent dunk-tank image results in Whisk, specifying an elevated over the shoulder perspective.
It's the video prompts that are infuriating me, the entire seat assembly constantly falls with the contestants attached to it, regardless of how I've described it.
It seems like the only thing Kling can generate successfully is a credit card deduction.

Edit - It did just manage to do this, but it cost thousands of credits to get there.

It is challenging. Best results so far.

Oh, I have been. The prompt has gone into detail such as 'a plastic seat attached to the inside rim of the vat' and 'she is sitting above the gunge with legs over the edge of the seat.'
Didn't know you could use a sketch as a basis, will try that.

Gameshows and Glamour.

Some Kling creations from my sexy and messy cruel gameshow

AI dunk tank images are improving, as are short videos.

So I decided to climb atop the hot seat and take the plunge myself...

Another post of bikini babes getting pied due to lost bets. I have so many kling videos now I dunno what to do with them, and will try to post more if people are interested. Here's the video on youtube below which is higher quality. Enjoy y'all!

https://www.youtube.com/watch?v=BtQCahM5NcQ

POV - The game-show outcome you never expected...

Images from Whisk, animated with Veo 3.

Here is some of my first try with ai

I think this magazine might have caught my attention. But which cover to choose?

(These are ImageFX portrait images, so the previews are only showing the top half, and the mud's mostly at the bottom)

I made these by starting from a genuine 1980s fashion photo (not included because that would be a picture of a real person), then using imagetoprompt.com to get a detailed description of the model's makeup and hair. That became the basis for the ImageFX prompts.

So, WAN 2.2 is pretty good at WAM! Went for a "bikini-clad clowns at the circus pieing themselves in the face while wearing Pie Me party hats" theme this time around. Animated gifs (give them some time to load) of the pieings, plus I posted the higher-quality/resolution clip to youtube - https://www.youtube.com/watch?v=m5JJvtyU2Y4 - I hope y'all dig these!

For those that want to try this themselves on WAN 2.2 (free and open source), here's my (probably overly verbose) prompt:

A woman holding a plate full of whipped cream in her hand. She presses the plate full of whipped cream against her face, splatting the plate full of liquid gooey lumpy whipped cream all over her forehead and face, sending whipped cream flying behind her, covering her face, hair and hat in whipped cream. This covers her entire face and drips onto her breasts in a thick gooey layer of wet dripping whipped cream as it drips from her face to her chest. In the end, the woman lowers the empty plate to show her cream covered face, with her whole face (hair brow, forehead, cheeks, chin, eyes) and breasts all covered in white gooey fluffy lumpy whipped cream as she opens her mouth in shock then sticks her cream-covered tongue. The scene ends with the woman's entire face covered in a thick layer of whipped cream and her breasts covered in the whipped cream and the plate empty. Make the whipped cream drip and look really bumpy and gooey, leaving trails of white cream, and look wet and gooey.

For her birthday she wanted a pie instead of presents, or 2 or 3 ...