Using the "add images" function of Whisk that I discussed in an earlier separate post, I took a wetlook AI picture and added some pie.

After Whisk describes the image, I add something like "A cream pie has hit her face and splattered on her shoulders and chest." or "A cream pie has hit her face and she is wiping the remains of that cream pie out of her cleavage." to the lower mustard-colored window. It doesn't always work; sometimes the original picture is too sexy or looks too much like a celebrity or Whisk is simply out getting a smoke. Sometimes I change "cleavage" to "chest" or "décolletage."

I find Whisk "pies" the pictures better than in its main "describe your ideas" window. The results are also much closer to the original image than from the main window.

I often see a picture of a beautiful woman, dry or wet, real or AI, and think "I wish someone would hit her with a pie." Now I can.

dream woman

I now have access to Sora 2 so I've started some video tests before running out of prompts for the day.

It is really impressive, especially the sound part which is stunningly natural in every language. I need to figure out how to extract a video without "posting" it but you can see screen cap examples of self-pieing being done in basically half an hour.

It's night and day compared to Sora 2. Sadly you can't do I2V with photorealistic images (even AI-generated).

Edit: unlisted YouTube videos :
https://youtube.com/shorts/kwTW0cbzyZ0?si=HCYF-biVD91bzQJi
https://youtube.com/shorts/tc9KHvd_OHA?si=caRRuyuSllvT-CV1


Sorry for the French but it was part of the testing lol

Very impressive, especially the first video. As I often comment, within what the programming will permit, the possibilities are almost endless.

I tested SORA2 a bit more using my 100 daily videos, there is definitely some potential once you understand what the tool does well and what it does not.

The biggest limitation is the lack of I2V with photorealistic images, really kills your prompt budget since you have to specify everything in the main scene.

Here are a few more proof-of-concept videos: they are kinda bad and full of artifacts and cuts but can give an idea of the tool.

If anyone wants I still have 2 invites left btw.

https://youtube.com/shorts/2fSeBsW8a_w?si=8hjkiENvXOwd8epQ

https://youtube.com/shorts/JTqr7lXXf2A?si=msNkgcYZU-dMNbD2

https://youtube.com/shorts/AvjkSWgnX9g?si=05c9YXMx_HVhxma3

https://youtube.com/shorts/4zn7CSjb5t4?si=53QBttcHivou-kII

After testing it further you can do literally anything with this tool: mud pits, pies, cakes, and I'm barely scratching the surface.

Here's one I find pretty good for mud lovers: https://streamable.com/lxdhxz

One for custard + pies: https://streamable.com/8kvepo

Liked this one.

Hello, do you still have 1 invite left or are you out?

These turned out pretty well, a lot better than my normal attempts at gunge, so I went a bit overboard and created hundreds of them. lol But I've narrowed it down to this batch and the one I posted to my profile a few days ago.

Messing with a new Lora I made mixed with an old one that is giving decent results for pies. Using Qwen Image Edit for the before picture. My next post will be slime, need to switch it up.

A couple of my recent messy video creations:

https://youtube.com/shorts/-nnJX3yeJ7Y?feature=share
https://youtube.com/shorts/9DCLxE_RfKg?feature=share
https://youtube.com/shorts/crvY4oa5-LY?feature=share
https://youtube.com/shorts/xQxrvdtzm3U?feature=share
https://youtu.be/hSwfyZJ3X7E

Hopefully someone enjoys something here!

Well-dressed women who like soup

I tried PhotoDirector 365, but unfortunately, these videos used up the free credits.

I can safely say the future is here (Sora 2).

Some dirty works

I'm not sure if these should go in this thread, or 'Funny / Unexpected results'. I made them with Whisk, intending them as an example of a scenario that would be quite tricky to do as a custom without involving AI.

Unfortunately it seems Whisk / Veo isn't up to keeping the style of her dress consistent before/after her encounter with the mud...

More POV game-show fun. Thankfully, I actually won this time around.

Using Qwen Image Edit Plus to reverse a pied bikini babe and make her clean, then animating the clean to pied with WAN 2.2. Hope y'all dig it! Youtube video below:

https://www.youtube.com/watch?v=CNYTLm6pc1I

Swamp...

Mud walker

ImageFX seems to do quite well when asked for pages from a 1990s computer catalogue. (Any wording on the pages is all its own work).

Excellent, excellent stuff!! I love their tongues sticking out too. I bet these were fun to make.

For my part I am really enjoying using Gemini 2.5 (Nano Banana) the ability to feed the first result back in to generate a story with now minimal Photoshop is so much fun and so much less work than it used to be!

Many thanks for these excellent images - love the work.

The topical Halloween witch images below are a sample from a series I posted last year, but have been revamped this week using Irfanview to both auto-adjust the colours and to sharpen the images where appropriate.

I'm in the process of uploading into albums many of the AI image sets I've posted here to have them all in one place, with those from the past couple of years being similarly enhanced with Irfanview. If the wetlook in the images below floats your boat, go into the personal photos section of my account for a lot more of the same (without the witchiness)!

A few more messy videos:

https://youtube.com/shorts/WuPEXSnnbPw

https://youtu.be/-c_ZNragNe0

https://youtube.com/shorts/PT4dO25Xzik

https://youtube.com/shorts/tOMNahU6n5Y

https://youtube.com/shorts/I8BKJSIDLp4

Hope somebody enjoys something here!
https://youtube.com/shorts/YgPowVMI-1o

https://youtube.com/shorts/SZjq-2QP2NA?feature=share

I've just added two of my recent AI creation to my videos here: snippets from Hailuo/Veo3 of pied cheerleaders and very sludgey damsels in distress. Comments welcome although I still get a realistic pie throw working, sadly.

https://umd.net/profile/i/goodpudding/section/videos/video/ai-cheerleader-initiation

https://umd.net/profile/i/goodpudding/section/videos/video/ai-damsel-in-messy-distress

Really enjoyed the cheerleader initiations video.

It's the Slime a Slut Show! Sexy scantily clad smokin hot sluts getting slimed for your perverted pleasure!

Created using Qwen Image Edit plus Wan 2.2, starting with slimed flux images from a LORA I made, removing the slime, then animating it with WAN between the clean/messy images.

Finally, I've had some more consistent luck with pie throwing - or, at least, on screen receiving - through another ai tool. I was able to extend the scene to 30 seconds and sure that it could have gone on a bit longer, and I added sound afterwards.

Here's a pretty party girl getting creamy. Hope you like it.

https://umd.net/videos/ai-speakeasy-pie

Artists at work... or play?