The WAM University cheerleader squad came up with a money-making concept - PIE TIME LIVE - where they'd play various games with the winners pieing the losers in the face. In their first episode, they played blondes vs brunettes rock-paper-scissors. They all agreed that the losers would have to dress up in ridiculously tiny orange micro-bikinis and take a pie in the face from the winner in front of the studio audience. In the end, the blondes beat the brunettes, who happily submitted to their messy punishment, giving the audience a good show. Each blonde picked their favorite brunette and let 'em have it, with a picture taken right before each brunette got creamed.
Ok, kind of a tease/anticipation series, but I'm going to try to "pie" these AI women using Wan and/or Kling next. Wish me luck!
Ok seriously, Kling 2.1 can do actual pieings pretty well (no plate in the face, but still messy and fun) which is wild cuz their prior versions could NOT at all. 2.0/2.1 can do seriously good slimings and pieings, and their censorship trips seem to have loosened a LOT recently. I don't know how they made such an improvement with WAM content, but damn.
But oh MAN is it expensive. A buck and change for each one of these, and these are only the good ones lol. Oh well, it's addictive and fun, I'm into it.
Hope y'all enjoy! I made a (unlisted, just for y'all) montage on YouTube as well - https://www.youtube.com/watch?v=gpliO1y8YiQ - for those that want to see higher quality than the animated gifs which are only 512x512/8fps.
0b1000101 said: Ok seriously, Kling 2.1 can do actual pieings pretty well (no plate in the face, but still messy and fun) which is wild cuz their prior versions could NOT at all. 2.0/2.1 can do seriously good slimings and pieings, and their censorship trips seem to have loosened a LOT recently. I don't know how they made such an improvement with WAM content, but damn.
But oh MAN is it expensive. A buck and change for each one of these, and these are only the good ones lol. Oh well, it's addictive and fun, I'm into it.
Hope y'all enjoy! I made a (unlisted, just for y'all) montage on YouTube as well - https://www.youtube.com/shorts/gpliO1y8YiQ - for those that want to see higher quality than the animated gifs which are only 512x512/8fps.
Absolutely amazing work, the substance behavior and model reactions in these are just superb! I'm sure the plate/tin push and crust is something that will surely come with time as this AI stuff gets better and better.
I have a thread on here about women getting pies/slime/gunge licked off of their feet, but I wanted to share these specific images from Whisk that really hit the exact pose/action I was looking for.
Hi all, https://umd.net/groups/i/a-place-to-post-ai-content-2 I started posting earlier this year some of my Bing creations from the year before thinking I would upload frequently but it didn't really take off so I'll do it here instead.
These are from when Bing results were better and less restricted so I'm glad to be sharing them now.
I tend to go for game-show / stage-show, with hints of glamour and fun.
Query for the group: Has anyone been able to create head dunking images using any of the generators? I'm using ImageFX right now, and while it has yielded great results in most things, I still have not been able to create a head dunking. Thoughts?
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.
0b1000101 said: Ok seriously, Kling 2.1 can do actual pieings pretty well (no plate in the face, but still messy and fun) which is wild cuz their prior versions could NOT at all. 2.0/2.1 can do seriously good slimings and pieings, and their censorship trips seem to have loosened a LOT recently. I don't know how they made such an improvement with WAM content, but damn.
But oh MAN is it expensive. A buck and change for each one of these, and these are only the good ones lol. Oh well, it's addictive and fun, I'm into it.
Hope y'all enjoy! I made a (unlisted, just for y'all) montage on YouTube as well - https://www.youtube.com/watch?v=gpliO1y8YiQ - for those that want to see higher quality than the animated gifs which are only 512x512/8fps.
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.
getemdown said: 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.
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.
getemdown said: 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.
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.