Photorealistic AI Generated Images
- Thread starter SUNBO
- Start date
-
Akiba-Online is sponsored by FileJoker.
FileJoker is a required filehost for all new posts and content replies in the Direct Downloads subforums.
Failure to include FileJoker links for Direct Download posts will result in deletion of your posts or worse.
For more information see this thread.
NICE! Image to Video is so much fun and brings things to life in incredible ways! That looks great, did you do this locally or on a site, perhaps?
I haven't had much time lately (due to work and personal stuff) to try things with Stable Diffusion, but I've been chipping at it. Learning basic prompting, using Image-to-Image, etc.. This is pretty fun to use! But of course until I get better it will produce some odd things now and then.
The original image was rendered and then animated on a site. I'm still looking for a method of doing it locally.
Greetings All,
Huge JAV fan - and I've been reading Akiba Online JAV discussion for at least a year, I've just never posted here prior.
I'm a long time creator of AI NSFW imagery. I've witnessed some truly great creations in this thread (and I mean fabulous), so I come here with a list of small questions that can help somebody like me make the jump from transforming my AI works into small AI movies. My questions are these:
1) Is there a (FREE) NSFW AI image to video creator website that gives free tokens out there (a daily like thing) that you can then use on a single 10 second video? The two formats I would be looking for are image to video and (first image) to (last image) of the video - alongside a text descriptor of what transpires either from the beginning of the scene, or from the first and last frames of it.
I've found that you can trick Pixverse into getting a woman to lift her top off, with varying results of success, so long as you start the image out with all the elements exactly where they need to be (hands near her waist - with her wearing a stand-alone bra/tank-top/bikini top). I haven't been able to generate enough credits yet to use Civitai, but from the looks of it, it holds promise. And tensor.art actually can do some interesting things, but typically just involves creating a 3D wrap around of an existing 2-D image. Which is great! But ... not really an in-depth video generation tool.
2) Are there any PAID NSFW AI image to video generators that -really get the job done.- I mean, like, if I tell it to thrust a BBC into a small girl's pussy and for her to wince in pain, it will create something that pretty much mirrors that. None of this hokey image-morphing stuff (i.e: someone's arm turns into a train for a few frames before turning back into an arm) - and with a reputable non-scam based site?
I remember I used Promptchan for images back in the day - and compared to the image quality I could get on non paid sites - it was actually pretty poor all around. Now they're doing video - I'm guessing it's just as poor of quality, but would anybody know for sure?
I remember the original AI image generators that were paid were pretty ... hit and miss, with the emphasis being on the miss. But then I did end up finding a free one that was absolutely excellent. So I'm hoping if I just stick with it, I'll find a image to video one somewhere that actually can pull off at least some simple ten second scenes.
If I were to put down cash on the thing, and that's a big if, I'd need to know that it can deliver basic and simple prompts without a big chance of screwing it up. I have no problem simplifying the image to a a bare-bones only-what's-needed degree and playing by the rules that would net the highest returns on successful completion.
I'm getting the feeling that it's still incredibly early days - but still late enough for someone or something truly groundbreaking to come through and allow at least basic free use that can get the job done. I was hoping that with Deepseek being so much less resource intensive somebody would have made a likewise video generation tool that, even if first generation, could still get the task done without too many hiccups. But, outside of having to set up very specific parameters to trick non-NSFW img-to-vid generators to make something akin to the finished product you want, I haven't seen anything where I'm like, "This is it!" as of yet.
But ...
What about you guys? What are your experiences with NSFW AI ===IMAGE TO VIDEO=== generation (not text). Any good ones out there?
Huge JAV fan - and I've been reading Akiba Online JAV discussion for at least a year, I've just never posted here prior.
I'm a long time creator of AI NSFW imagery. I've witnessed some truly great creations in this thread (and I mean fabulous), so I come here with a list of small questions that can help somebody like me make the jump from transforming my AI works into small AI movies. My questions are these:
1) Is there a (FREE) NSFW AI image to video creator website that gives free tokens out there (a daily like thing) that you can then use on a single 10 second video? The two formats I would be looking for are image to video and (first image) to (last image) of the video - alongside a text descriptor of what transpires either from the beginning of the scene, or from the first and last frames of it.
I've found that you can trick Pixverse into getting a woman to lift her top off, with varying results of success, so long as you start the image out with all the elements exactly where they need to be (hands near her waist - with her wearing a stand-alone bra/tank-top/bikini top). I haven't been able to generate enough credits yet to use Civitai, but from the looks of it, it holds promise. And tensor.art actually can do some interesting things, but typically just involves creating a 3D wrap around of an existing 2-D image. Which is great! But ... not really an in-depth video generation tool.
2) Are there any PAID NSFW AI image to video generators that -really get the job done.- I mean, like, if I tell it to thrust a BBC into a small girl's pussy and for her to wince in pain, it will create something that pretty much mirrors that. None of this hokey image-morphing stuff (i.e: someone's arm turns into a train for a few frames before turning back into an arm) - and with a reputable non-scam based site?
I remember I used Promptchan for images back in the day - and compared to the image quality I could get on non paid sites - it was actually pretty poor all around. Now they're doing video - I'm guessing it's just as poor of quality, but would anybody know for sure?
I remember the original AI image generators that were paid were pretty ... hit and miss, with the emphasis being on the miss. But then I did end up finding a free one that was absolutely excellent. So I'm hoping if I just stick with it, I'll find a image to video one somewhere that actually can pull off at least some simple ten second scenes.
If I were to put down cash on the thing, and that's a big if, I'd need to know that it can deliver basic and simple prompts without a big chance of screwing it up. I have no problem simplifying the image to a a bare-bones only-what's-needed degree and playing by the rules that would net the highest returns on successful completion.
I'm getting the feeling that it's still incredibly early days - but still late enough for someone or something truly groundbreaking to come through and allow at least basic free use that can get the job done. I was hoping that with Deepseek being so much less resource intensive somebody would have made a likewise video generation tool that, even if first generation, could still get the task done without too many hiccups. But, outside of having to set up very specific parameters to trick non-NSFW img-to-vid generators to make something akin to the finished product you want, I haven't seen anything where I'm like, "This is it!" as of yet.
But ...
What about you guys? What are your experiences with NSFW AI ===IMAGE TO VIDEO=== generation (not text). Any good ones out there?
Ah, the holy grail of NSFW AI.
Putting together I2V or V2V generators\models is a huge, expensive task and I suspect that for now, in order to attract and maintain investment in such projects, the developers of these will have nailed the lid firmly shut on NSFW.
I know it is possible, with the correct hardware set-up and knowledge, to create this kind of stuff locally, but right now I have neither the hardware or the knowledge to do this myself.
My quest continues...
NSFW AI Image to Video, (paid or free to use) is something I've also been looking into for a while now. While there are definite signs that it is coming, I don't think we'll see them just yet. (I would however be very happy to be proven wrong).
Putting together I2V or V2V generators\models is a huge, expensive task and I suspect that for now, in order to attract and maintain investment in such projects, the developers of these will have nailed the lid firmly shut on NSFW.
I know it is possible, with the correct hardware set-up and knowledge, to create this kind of stuff locally, but right now I have neither the hardware or the knowledge to do this myself.
My quest continues...
Spent the day tinkering with fabrics again. There is naturally enough, one particular type of fabric that appeals to me, can you guess which?
Last edited:
It's a thing of bandwidth and electricity costs more than anything else. It will get there - but essentially - with image generation, people just had to worry about recreating another slice of the Internet that was about as big or powerful as the Internet from the year 2000. Doable - right? With modern tech - adding all of that capability to the existing beast of the Internet - was achieved in about a year. Or really, about six months.
But this one? This is like saying, "Hey, anybody out there willing to create another platform the size of the entire existing porn industry?" That's ... that's undoable. That's the reason they're not touching the NSFW element. Because that element for businesses, much like it is for people, is the holy grail. They're all going for that and that alone.
Do you think the world would have paid half ... nay ... a literal hundredth of the attention it did to AI if you couldn't make girls naked with it? Do you really? You know what would have happened with it? It would've been made - it would have been improved - it would have started taking jobs - and it would've been relegated to the business section of the newspaper. But - with porn? The minute -ANYBODY- hears the word "AI" - their ears perk up like they just heard a dog-whistle. "Nudies?!" - "Where?!"
There's a reason Trump made a huge AI investment - because he wants to be seen as the guy who "gets" the thing that people obviously love. All the other reasons? Sure. But, he put the emphasis on it that he did for that reason as well. If not solely - it played a large role.
Here's where the ultimate issue lies. The traditional image generators can pull off their task - and make a profit - by having you watch a couple of ads or so. That equates to a win for the platform hosting the goods. The cost of bandwidth and electricity are more than covered. But ... with video? That's like 1,800 images generated for just a single minute worth of footage. Not only that - but the processes in place to make sure it doesn't lose it's mind and go all wonk make it a larger, more complicated, and more costly enterprise as well.
You can see it in the video AI programs that did allow nudies to be created with a "flaw" in the program. With Kling - you would just have to add that cross to the corner - and you could make a video with a fully nude girl doing whatever you told them to. That -WASN'T- by accident. They knew that about fifteen seconds after that trick was discovered - everyone would flock to their program. And, the result?
An infinitely long line to make -ANY- video on Kling. As a free user? Forget it. They could barely keep up with the demand for the paid users. And that's with them constantly and consistently adding more servers and bandwidth into the mix. Now that the program has been updated, and the feature has been "corrected," they have probably the most valuable asset of all. The data. Which they can sell to other companies interested in getting into the field.
At the end of the day, though, it's going to be really, really, REALLY hard for a whole series of newborn freebie sites to start offering this service. Watching a couple of ads isn't going to cover the costs. There's a serious barrier to entry there. And one which will make it so that the people who are going to try to do it (the major porn houses and networks in North America will no doubt be funding it) will release a program that can promise, from day one, some actual stability in the finished product (to justify the cost). But then ...
Will most likely charge a ton to use the service. And even then - if it does work! - there will be a literal tidal wave of tens of millions of people all rushing the service - all wanting to use the servers - and submitting absolutely crushing energy-based and bandwidth-based workloads that would make the initial investment to make sure the actual service works astronomical.
Which is exactly what happened to Kling - and why 95% of the people who submitted a video to be made from them (and still - to this day) - are left out in the cold holding their bag for days on end with no finished video entering onto their screens.
It's already doable. AI could and can make absolutely incredible NSFW AI videos. But, unlike with making a cat lick it's paws, or a panda eat a pancake, having an 18yo AI girl flop her gigantic tits out from a T-shirt would be enough to, literally, no joke, break the Internet.
Thanks so much for your reply _2old_, much appreciated.
That type of content will probably be home grown at first, in my opinion. Which means the quality will not be there. For all the reasons you already discussed, it would be cost prohibitive for any outfit to make a profit anytime soon if they released such a beast. Everyone would want to use it for free and find ways to do it, like registering under different emails and proxy IPs. They would notice the amount of free traffic/generation queues vs paid and quickly throttle the free but see little in terms of paid growth. Just my opinion. Imagine the ratio of people who pay for vs. not pay for that type of real content already. Magnify that a few times, I'm thinking. But, like you, I'd really want to see that start becoming available.
I mainly use a site called pornpen.ai (pornpen.art currently since something messed up with their domain registration) and it creates NSFW images. They have a GIF feature but it so very lacking. I do pay for that site, but not much. I also pay for Pixverse, at least for now. You run out of credits before the next billing, that's for sure, because who wouldn't want to keep trying until things look good! But, NSFW is off limits. I can, though, create some nice content with outfits, things like that. And I've been able to get some bouncing boobs (covered up) with great success.
That site does have filters that work pretty well. Things get flagged and you can't upload an image because of it. Took me a while to figure out with some inpainting it will take things. It doesn't like too much skin showing here and there, but eventually I get things to upload. And every now and then the generated video gets flagged and won't even show for me. At least I get the credit refunded immediately.
@_2old_ has been giving me some pointers on using Stable Diffusion to create images. I've basically just started and I'm still getting used to it, but I bet before long I won't even have to pay for the pornpen site since I can create any type of image I can imagine without filters. I'm also starting to look at Image2Video using ComfyUI, but my gear is too weak for it, I'm finding. I just upgraded to 32GB of RAM, but the used GPU I got from eBay is an older one (I'm not familiar with GPU stats), its a GTX 1060 with only 3GB of VRAM, which can't do much for Image2Video, turns out. What I was able to produce was like 3 seconds and not anywhere near what can be done on Pixverse, obviously. So, as to not get totally discouraged I'm turning back to creating images. My hope was that any images Pixverse didn't take, I could turn to video myself. Maybe later in life I'll be able to.
I mainly use a site called pornpen.ai (pornpen.art currently since something messed up with their domain registration) and it creates NSFW images. They have a GIF feature but it so very lacking. I do pay for that site, but not much. I also pay for Pixverse, at least for now. You run out of credits before the next billing, that's for sure, because who wouldn't want to keep trying until things look good! But, NSFW is off limits. I can, though, create some nice content with outfits, things like that. And I've been able to get some bouncing boobs (covered up) with great success.
That site does have filters that work pretty well. Things get flagged and you can't upload an image because of it. Took me a while to figure out with some inpainting it will take things. It doesn't like too much skin showing here and there, but eventually I get things to upload. And every now and then the generated video gets flagged and won't even show for me. At least I get the credit refunded immediately.
@_2old_ has been giving me some pointers on using Stable Diffusion to create images. I've basically just started and I'm still getting used to it, but I bet before long I won't even have to pay for the pornpen site since I can create any type of image I can imagine without filters. I'm also starting to look at Image2Video using ComfyUI, but my gear is too weak for it, I'm finding. I just upgraded to 32GB of RAM, but the used GPU I got from eBay is an older one (I'm not familiar with GPU stats), its a GTX 1060 with only 3GB of VRAM, which can't do much for Image2Video, turns out. What I was able to produce was like 3 seconds and not anywhere near what can be done on Pixverse, obviously. So, as to not get totally discouraged I'm turning back to creating images. My hope was that any images Pixverse didn't take, I could turn to video myself. Maybe later in life I'll be able to.
Last edited:
What do you think about this one from civitai that I came across:
Video posted by kkkkk1234
They often have that "cross" symbol on the videos, not sure if it comes from the AI tool.
The site animegenius is absolutely fantastic in creating both NSFW and "real girl" AI images. Thing is ...
The only thing you can do with a real life image is turn it into an anime image. And an anime image into a real life image. There's an "animate" button at the end of it - to transform the image that was generated into a gif - but no way to turn the base image itself into the gif. It has to be put through the AI process first.
I remember when the site first came out, or around that time, they added a feature where you could put -any- image into it - and it would create a 3D "rotating" effect around the image. Not fully 3-D or anything like that, but it would add just enough depth in every direction to make the image pop out from it's surroundings, and make it look like you were actually "there." It would just slowly rotate, and the person in the center of the image would jiggle a bit, and ... that was it. It was like the first baby step towards AI video, like absolutely tiny, but it was still great.
They then just ... removed it. Like, from one day to the next, it was gone. They still had certain links to it on site - and referencing it - but the entire framework for generating that rotating gif just ... evaporated into thin air. And it's been gone ever since.
At that point I figured, alright, I see what's going on here. People starting getting a little too cute with the nudify images they started creating of people - and the site most likely faced some blowback, even if not legal, and they just figured ... fuck it. Better to play it safe and just yank that out. Shame too, because it was absolutely fantastic.
---
Your woman bouncing around mp4 was very nice. I've gotten close to that (but actually got pixverse to nudify the image, even though it somehow sensed it wasn't supposed to do it, and then added a bunch of extra unnatural splotches).
These are all just sparks, though. We need to get closer to actually starting a fire with these things. Which brings me to the next post - but I'm still going to be addressing what you said in it, so I'll be responding to both of you essentially at the same time.
What do you think about this one from civitai that I came across:
Video posted by kkkkk1234
civitai.com
They often have that "cross" symbol on the videos, not sure if it comes from the AI tool.
You see - now -THIS- is what I'm talking about. THIS IS THE FIRE.
Problem is - the person that created this - did so by essentially compiling an entire programming language, inserting specific data nodes in specific spots, and ... well, essentially, required having the full knowledge of a programming language AND the assembly of the program itself. Like, I'm not a complete n00ber when it comes to programming, I wrote code back in the day (not good code - but, you know - I did it) - so it's not like I'm looking at something that I don't grasp the concept of. I get it. I fully get it.
Thing is - I don't have either the time or the resources to learn the entire ins and outs of how to specifically train a LORA on my own. Even more (getting back to Cashhern2 here) - I don't have the 256 GB of RAM needed in all my different computer components to be able to BARELY run the process. I'm really more interested in the artistic side of it. Like, I've taught myself a great deal (in using a series of programs) to get some really phenomenal AI images. Even better? They don't look like AI! I've found a lot of ways to decreasing the glossiness and rubbery-ness of the skin. My skills are still beginner - and I've still got a long way I can go - but increasingly I can create imagery that's just like, "YES!"
And that's with 40 to 60 hours of work on a single image.
Thing is - I don't have the thousand hours needed to fully get into the production side of it for videos - and even if I did - I don't have the $10,000 (if this is exaggerated, forgive me) available for the parts.
But ... Hunyuan and ComfyAI seem to be getting daringly close. It seems they've found shortcuts around the tremendous amounts of processing power needed for things that aren't necessary. Having a LORA that has a stable straight-forward framework through which differentiation can occur, but the entire reality of the image doesn't have to be reconceived for every second. It sounds like it's approaching it in the way it should be approached, by creating a stable background layer, and then imposing a foreground layer (the LORA) on top of it. Allowing both the flexibility to change somewhat, but not wasting resources transforming the blue window into a pond and then into a blue bird.
I dunno - I'm still out of my depth. But it sounds like everyone's been working vigorously on it. And with TenCent being the ones that are funding Hunyuan to begin with - they might just have the willingness and capacity to fund the servers and bandwidth needed to essentially have 20 million people (minimum) all creating videos at the same time. Especially if they've reduced the waste and the workflow needed within the basis of the AI system itself.
Here's to hoping - if anyone hears of any updates to video generation - please post it in here. I - like pretty much all of us here - am going to be there on hour one, never mind day one.
Thank you to Cashhern and Qubit for the replies. Much appreciated.
And for _2old_ showing us his inner freak. lol.
The amazing folks on here creating these images (you) are all very technical in your work and discussions.
That's great and I respect you for it and your artistry.
Your images are very sexually compelling and some are downright beautiful.
That's great too. Don't lose sight of that goal.
Thanks so much for all of your hard and interesting work.
That's great and I respect you for it and your artistry.
Your images are very sexually compelling and some are downright beautiful.
That's great too. Don't lose sight of that goal.
Thanks so much for all of your hard and interesting work.
Thank You Last Ninja!.
Your creation is so real and so compiling.
I particularly liked the bra being transparent at the nipple ends.
Nice touch.
Thanks!
Your creation is so real and so compiling.
I particularly liked the bra being transparent at the nipple ends.
Nice touch.
Thanks!