jlv61560 2024-06-25 14:08:172 ♡
Sweet meteor of death, come for us now -- that RunwayML Gen2 freakshow is enough to put you off the whole project!
omg, it's like that supervillain in batman beyond D:
Pity this concept didn't get developed further. I think it would have been nice to see Alison resist a bit more.
Indeed, but if you look at the horror show from RunwayML Gen2:
https://satinminions.com/RunwayML-Violet-Clean.html
This has very impressive consistency in comparison.
https://satinminions.com/RunwayML-Violet-Clean.html
This has very impressive consistency in comparison.
Creepy.
Right now I think we're getting the worst end of AI, where it's convincing enough on the surface to blow up social media, but not really practical enough for a big improvement in production.
There is a (bright?) future where a single person will be able to make a complete film using these tools. I don't know what it'll be like when there's a thousand or ten thousand new shows released every year but it sounds like we will live in interesting times.
My worry is that the best tools will remain proprietary and lawfare will be used to remove the open source alternatives.
Some people think that the current tech will cap out and never really be useful - I think this is cope. The capabilities are clearly already there, it's just a matter of controlling them.
It is unnerving for sure - especially when I go to deviantArt or rule34 or even google images and the entire page is destroyed with ai garbo. I've said this before but that's why I feel the need to mess with it, because I need to understand the threat and how to use it.
Oh I guess my other big worry is that we'll enter a completely post-fact world and it'll be impossible to find a verifiably real image of anything. Every book will be rewritten and every image repainted, all recently recorded history will be in doubt, etc.
There is a (bright?) future where a single person will be able to make a complete film using these tools. I don't know what it'll be like when there's a thousand or ten thousand new shows released every year but it sounds like we will live in interesting times.
My worry is that the best tools will remain proprietary and lawfare will be used to remove the open source alternatives.
Some people think that the current tech will cap out and never really be useful - I think this is cope. The capabilities are clearly already there, it's just a matter of controlling them.
It is unnerving for sure - especially when I go to deviantArt or rule34 or even google images and the entire page is destroyed with ai garbo. I've said this before but that's why I feel the need to mess with it, because I need to understand the threat and how to use it.
Oh I guess my other big worry is that we'll enter a completely post-fact world and it'll be impossible to find a verifiably real image of anything. Every book will be rewritten and every image repainted, all recently recorded history will be in doubt, etc.
It's a shame this is a "zero-skill user" tool as you called it. Definitely one of the best looking ones so far, AI often has a hard time keeping the iris / pupil consistent but it looks decent here! The hair bounces slightly and the blinking looks natural! I know the reason it looks good is because its barely moving the image, there is still a long way to go for tools to properly realize 2D images in a 3D space.
But I can see some uses for some of these tools now, you could add blinking eyes, animated hot breath, background weather conditions, any small thing that can flourish static images.
I am definitely not thrilled about the future of AI generation, I have a feeling it could get pretty dystopian. I am however much more excited for how these tools can ENHANCE art rather than how they can replace it.
But I can see some uses for some of these tools now, you could add blinking eyes, animated hot breath, background weather conditions, any small thing that can flourish static images.
I am definitely not thrilled about the future of AI generation, I have a feeling it could get pretty dystopian. I am however much more excited for how these tools can ENHANCE art rather than how they can replace it.
Amusing! I liked it.
That is MUCH better, though her face goes from something fairly close to your usual style to something more "conventionally" pretty. Still, imminently fuckable.
@Yepa: There are 2-l variations in the spelling of that name. Most of the Alisons/Allisons that I've known in real-life had their names spelled with two l's; so, as a result, that's been my default way to spell that name for my whole life (maybe it's a regional spelling convention endemic to where I grew up but little seen elsewhere). I didn't know that Satin Minions' creator spelled it with one l until it was pointed out in this comment thread. I have since corrected my spelling, thereof, in comments on other SM content that were posted after this comment
AI video just off doing its own thing.
You can nitpick the hands and feet but if you saw this a few years ago you'd probably think it was some random bad TV show.
The future is gonna be weird.
You can nitpick the hands and feet but if you saw this a few years ago you'd probably think it was some random bad TV show.
The future is gonna be weird.
This is a result from Luma Labs AI image-to-video. It is implemented as web page where you can provide a single image and text prompt.
Here I used this image:
https://satinminions.com/Alison-Jessica-Rabbit-Side.html
The stability and movement are impressive and it has a good understanding of materials such as the sequins and satin gloves. It tends to favor a photo realistic style, 3D rendered style, or a generic flat anime look depending on how you prompt it. Sometimes it will cut to a completely different scene, like this:
https://satinminions.com/LumaLabs-Combat-Mode-Cut.html
We're fast approaching the point where generative video AI can replace stock footage, things like "man using computer" or "drone shot of new york city at night" can be completely convincing. And of course memes where consistency doesn't matter are great. But I don't think the current model architectures will be able to replicate a style or character without specific training.
The current target audience seems to be the zero-skill user, where you only have to provide the bare minimum - because that's what gets the most engagement. As a "professional" though, I would much rather see tools that required more advanced inputs - for instance, input a complete line animation and a single colored frame and it would propagate that coloring through the animation.
Here I used this image:
https://satinminions.com/Alison-Jessica-Rabbit-Side.html
The stability and movement are impressive and it has a good understanding of materials such as the sequins and satin gloves. It tends to favor a photo realistic style, 3D rendered style, or a generic flat anime look depending on how you prompt it. Sometimes it will cut to a completely different scene, like this:
https://satinminions.com/LumaLabs-Combat-Mode-Cut.html
We're fast approaching the point where generative video AI can replace stock footage, things like "man using computer" or "drone shot of new york city at night" can be completely convincing. And of course memes where consistency doesn't matter are great. But I don't think the current model architectures will be able to replicate a style or character without specific training.
The current target audience seems to be the zero-skill user, where you only have to provide the bare minimum - because that's what gets the most engagement. As a "professional" though, I would much rather see tools that required more advanced inputs - for instance, input a complete line animation and a single colored frame and it would propagate that coloring through the animation.
Nudes of Alison in a cup of coffee has legs; I'm thinking a spinoff comic, cameos, jingles, brand deals, advertisements, heck put her nude in any liquid foodstuffs and she'll be a star! 5-10 years we'll see it go mainstream, HBO television, a whole new cinematic universe baby, that's my dream.
Poor Torrin. First Alison steals his arm. Then when she gives it back, she puts it on backwards.
Another result from Krea AI, using some of the same keyframes I fed to ToonCrafter here:
https://satinminions.com/Lighter-Chains-4-ToonCrafter.html
It has impressive stability in the face and hair, but it can't do the kind of scene interpretation that ToonCrafter can.
https://satinminions.com/Lighter-Chains-4-ToonCrafter.html
It has impressive stability in the face and hair, but it can't do the kind of scene interpretation that ToonCrafter can.
The face holds excellently -- as YQN said, a marked improvement over some of the others you've tried. The dress, on the other hand, must be infused with Demonic sex magic since it varies wildly from frame to frame!
This is a marked improvement from the earlier animation rendering
This is a result from Krea AI image-to-video. It is implemented as web application where you can upload keyframes and prompts on a timeline. I used these two images as keyframes:
https://satinminions.com/Alison-Jessica-Rabbit.html
https://satinminions.com/Alison-Jessica-Rabbit-Side.html
It's eye catching and very smooth (at least in the face), but it does not follow the original keyframes or style very strongly. I think this could be tweaked to get better results, but my "3 minutes" of free trial video generation got used up in 20 seconds, and that doesn't exactly encourage me to purchase more time.
Having a timeline with keyframes is a step in the right direction, but the hard push towards content control and monetization seems premature for something that's not really cut out for professional use.
https://satinminions.com/Alison-Jessica-Rabbit.html
https://satinminions.com/Alison-Jessica-Rabbit-Side.html
It's eye catching and very smooth (at least in the face), but it does not follow the original keyframes or style very strongly. I think this could be tweaked to get better results, but my "3 minutes" of free trial video generation got used up in 20 seconds, and that doesn't exactly encourage me to purchase more time.
Having a timeline with keyframes is a step in the right direction, but the hard push towards content control and monetization seems premature for something that's not really cut out for professional use.
Now do the same but with a cup of ramen.
Mmmmm, would I looooove to drink Alison's coffee-water!!
I guess we can't complain about not having any nudes of alison in a coffee cup anymore haha
Oooooo! I wonder how Alison got this small! Maybe mistress shrunk her to teach her a lesson? Maybe that's how she ended up in the Tinkerbell outfit after her "candy" clothes dissolved?
This is a result from RunwayML Gen2 AI image-to-video. It is implemented as a web service, so it costs money, it can be slow, there is content filtering, and you're at their mercy for data privacy and access.
It generally struggles to maintain a consistent form, with characters often melting into someone else if there is significant animation. It also can't replicate a style, which is why I used the stable diffusion edit of this character as the image prompt, since it is a more generic photorealistic style.
They have announced Gen3, but it is not available to the public yet. From the results they've shown, I'd say it has potential to replace stock video for corporate ads and video essay filler, but it's not quite there yet for animation production.
It generally struggles to maintain a consistent form, with characters often melting into someone else if there is significant animation. It also can't replicate a style, which is why I used the stable diffusion edit of this character as the image prompt, since it is a more generic photorealistic style.
They have announced Gen3, but it is not available to the public yet. From the results they've shown, I'd say it has potential to replace stock video for corporate ads and video essay filler, but it's not quite there yet for animation production.
Pika Labs AI image-to-video does a pretty decent job at realistic smoke, water, rain, fire, that sort of thing.
The intent seems to be to create cinemagraphs.
The intent seems to be to create cinemagraphs.
A pity, that. Still, your Art-Fu is strong and we eagerly await whatever you will share with us next!
This AI image-to-video from Pika Labs. You provide a single image and a text prompt and roll the dice. It's implemented as an online service via a discord bot so you sometimes have to wait a long time and there is NSFW filtering.
This was one of the only results I managed to get with a coherent movement that didn't morph into something strange. Most of the time you get the windy hair/fabric effect applied to random parts of the image or no animation at all.
Maybe if it could run locally, you could run it hundreds of times and cherry pick good results, but as it is now, it doesn't seem to have any use at all.
This was one of the only results I managed to get with a coherent movement that didn't morph into something strange. Most of the time you get the windy hair/fabric effect applied to random parts of the image or no animation at all.
Maybe if it could run locally, you could run it hundreds of times and cherry pick good results, but as it is now, it doesn't seem to have any use at all.
That's so very cool!
You may be interested in this video:
https://satinminions.com/Satin-Minions-The-Offering.html
https://satinminions.com/Satin-Minions-The-Offering.html
I mean, yeah, I could talk about all the things that are weird about this, but... who the fuck cares? Good, ethical use of these programs could do a LOT for the animation industry without harming the jobs of animators. Stuff still needs to be drawn and adjusted. Perhaps just with less tedium.
I think it's a good thing you're experimenting with this. Though, since I'm not part of the art community, I mostly say that because it seems to be a thing you're passionate about. I hope you find ways to use these tools to make things more fun for you.
I think it's a good thing you're experimenting with this. Though, since I'm not part of the art community, I mostly say that because it seems to be a thing you're passionate about. I hope you find ways to use these tools to make things more fun for you.
Gentinal transformation when?
Also I realized I named this "Lighter-Chains-4-ToonCrafter" when it is based on LC5...
This is another result from ToonCrafter, an AI frame interpolator, this time fed with panels from the opening scene of Lighter Chains Volume 5. There's some weird bits of course, but there's a lot of potential here for automating the "boring" parts of an animation where you just need some blocking and idle animations.
As a storyboarding aid, this can also show what amount of limited animation you can get away with - some of the shots work surprisingly well.
I've had some interesting results upscaling the frames from this in stable diffusion, but I want to see if doing some quick fixes to the animations or training a lora on the source panels can help things.
As a storyboarding aid, this can also show what amount of limited animation you can get away with - some of the shots work surprisingly well.
I've had some interesting results upscaling the frames from this in stable diffusion, but I want to see if doing some quick fixes to the animations or training a lora on the source panels can help things.
Ah yes.
The Awakening.
The Awakening.
Well prepare to sit wrong because I have tried several image-to-video AIs I'll be posting the results and my thoughts this week.
The goal isn't to make the best finished work right off the bat, but to test the technology and see what it can do - good and bad. Part of learning a new tool.
Or sometimes it's just a novelty.
The goal isn't to make the best finished work right off the bat, but to test the technology and see what it can do - good and bad. Part of learning a new tool.
Or sometimes it's just a novelty.
I'm sorry, I just try and stay away from AI stuff. Some of the movements...man, they just don't sit right with me.
Interesting. It's almost like a dream sequence...
I made this using a new open source AI tool called ToonCrafter that can interpolate an animation between two given key frames.
I used various crops and reverses of these two images as keyframes:
https://satinminions.com/Alison-Jessica-Rabbit.html
https://satinminions.com/Alison-Jessica-Rabbit-Side.html
The results are a little strange at times, but given that these are not really animation keyframes, I think there is some potential here.
I used various crops and reverses of these two images as keyframes:
https://satinminions.com/Alison-Jessica-Rabbit.html
https://satinminions.com/Alison-Jessica-Rabbit-Side.html
The results are a little strange at times, but given that these are not really animation keyframes, I think there is some potential here.
I think to plebs like us the face in these sketches probably causes too much of an uncanny valley reaction. I reckon that helps explain the vote count, along with jlv61560's excellent point about bias.
LAMP is quite old. Maybe try some linux, nginx, postgres, python/js?
This may be a version of "confirmation bias" in that most people tend to like the first version of something they see, and see other versions as being "less good" since they are mentally acclimated to the first version. Really all three are pretty good, but like many, I voted for the first version I saw as being just that little bit "better."
Of the options given, I selected "given as ransom" as I thought that it was the most-humiliating of these indignities for our hapless protagonist to be forced to suffer. Close second plotline for me is the "estranged twin sister"
I have an option-7, however, where our protagonist turns out to be a bodyswapped peasant boy (late adolescent or early young adult) who works a very lowly laborer job, like: ditch-digger; chimneysweep; shoeshiner; maybe even a beggar. One day, he sees this princess carriage go by and catches a glimpse of her peering between the curtains in her window at the working class surroundings passing her by with a disgusted look on her face. Filled with bitter resentment, he mutters to himself, "Why can't I be royalty? They have such easy lives and get everything handed to them without having to work for it and every whim met at the snap of a finger.
Not long after this scene, this princess' carriage is overtaken by an angry mob of peasants and members of the working class who stage a revolt, taking her prisoner. Later that night, hours after hearing of this news, our protagonist goes to sleep with a s***-eating grin on his face, only to wake up the next morning as this captured princess
I have an option-7, however, where our protagonist turns out to be a bodyswapped peasant boy (late adolescent or early young adult) who works a very lowly laborer job, like: ditch-digger; chimneysweep; shoeshiner; maybe even a beggar. One day, he sees this princess carriage go by and catches a glimpse of her peering between the curtains in her window at the working class surroundings passing her by with a disgusted look on her face. Filled with bitter resentment, he mutters to himself, "Why can't I be royalty? They have such easy lives and get everything handed to them without having to work for it and every whim met at the snap of a finger.
Not long after this scene, this princess' carriage is overtaken by an angry mob of peasants and members of the working class who stage a revolt, taking her prisoner. Later that night, hours after hearing of this news, our protagonist goes to sleep with a s***-eating grin on his face, only to wake up the next morning as this captured princess
Q&A @theAdmin:
If my Engagement level membership status allows for it, I'd like to request a "deleted scene" from this S.M. issue wherein we see Torrin fucking an especially girly looking Alison doggie-style (like he is here), but he's got handfuls of her pigtailed hair clutched in his fists, which he yanks back on with every punishing thrust, causing her enormous tits to jiggle comically on her chest
If my Engagement level membership status allows for it, I'd like to request a "deleted scene" from this S.M. issue wherein we see Torrin fucking an especially girly looking Alison doggie-style (like he is here), but he's got handfuls of her pigtailed hair clutched in his fists, which he yanks back on with every punishing thrust, causing her enormous tits to jiggle comically on her chest
Q&A @theAdmin:Is it lore-accurate to assume that this image of Alison is showing her swallowing cum for the first time and discovering that she loves the taste (a sensation reinforced by her collar's affect on her still-feminizing brain via psychic reprogramming)?
Ooooo, I love the way that Morale Officer looks in combat-mode!!
She needs to swallow more. Food is food, right? ;-)
You should definitely have him use the shackles!
I'm currently writing a story about how someone from our plane of existence ends up in Mistress' plane of existence. He ends up in a similar situation to Allison
Well I didn't think they added that much, but if you want them, I'll add them.
No High Res version with Text?
The lesson here, never jump on "your partner" just cause she was already going at it. She might tell you things not meant for even post nut clarity.