-
Sign up or login, and you'll have full access to opportunities of forum.
Discussion about A.I.
- Thread starter Doragon
- Start date
fallenmystic
Tribune
I think they look more realistic but still feel like enhanced Daz3D renders than photos, which is perfectly fine if that's the style you are looking for. But if you are aiming for semi-photorealism or feel annoyed at the flaws it introduces, I recommend switching to more flexible tools like Foocus, A1111, or ComfyUI (preferably with the Krita plugin, which is how I make my images).
If you don't have a graphics card with 10GB+ VRAM, there are several options for running such tools on a GPU cloud. Online services like Krea are quite limited in the features they provide, so they are often insufficient for serious work.
With the tools I mentioned above, you can create a series and fix the flaws. The former is a bit tricky, but it's definitely doable with the right tool (e.g. IPAdapter / Face ID) and workflow.
As for depicting real people in AI images, changing the backdrop of a photo or making photo manip work realistic is quite trivial to achieve. You can use the same method I just mentioned for something more exciting too. To make a series, you'll need a way to preserve the identity of characters across the images. And if it's possible, it means you can preserve the face of you and your friends across the original photographs and AI-generated images also.
fallenmystic
Tribune
I heard that a new version of the Krita AI plugin had just been released, which added a regional prompting feature, so I tried it out in conjunction with the Pony model I mentioned above.
To make a long story short, I think I've found the ultimate AI tool I've been looking for:
To share my new workflow:
I'll link a video to help you get an idea of how this feature works:
To make a long story short, I think I've found the ultimate AI tool I've been looking for:
To share my new workflow:
- Live regional painting with Pony Lightning to visualise my idea.
- Inpaint to fix deformations and add details to create a base sketch.
- Make controlnet images out of 2.
- Switch to the generation mode (i.e. non-live mode) and do "seed hunting".
- Adjust things like CFG, sample counts, and so on with the seed found in the previous step.
- Inpaint any remaining problems, if necessary.
- Upscale the result using SUPIR.
- Post-process in a photo editor (e.g. Darktable) for finishing touches (e.g. colour correction, adding grains, etc.).
I'll link a video to help you get an idea of how this feature works:
fallenmystic
Tribune
As my honeymoon period with the Pony Diffusion was over, I began to see both its strengths and weaknesses.
I'm still very happy with its ability to depict various lewd concepts with relative precision. It really helps when the model understands tags like "grabbing_another's_breast," for example. I even stopped using my own slave restraints Lora, because the Pony model does it better by default.
On the flip side, I often found its anime origin sips through, even though I'm using a photorealistic variant. This was a typical image I got while I was seed-hunting for my latest render:
As you can see, things like the face or the suit clearly show strong anime/illustration influences. I envy those who create anime-style works since the Pony Diffusion would be a gift from god to them as it is (I have to wonder how gods would think about censorship, though). But as I'm aiming for photorealism, I must find a better way of doing it.
I decided to run it through a non-Pony model, improving realism while destroying the details. The lost details could be recovered by inpainting with the Pony model again since it's much better at keeping with the overall image style when used that way.
There's something which might be worth mentioning that I tried for the first time in my latest render. The original base image looked like this, which I felt rather dull:
I wanted to make it look like they were on a stage with spotlights on the girl's body. It'd make the scene more dramatic while emphasising the girl's humiliation. The problem is that precisely controlling the lighting condition might be very difficult in Stable Diffusion. Well, at least it was so until recently.
Now, we have IC-Light, which allows us to change the lighting condition of an image without destroying its content. With IC-Light, I could add a nice spotlight on the girl's body like this:
On a side note, similar AI technology seems to be making a large impact on filmmaking as well since it allows filmmakers to freely experiment with different lighting setups in the editing room after the shot is taken.
Anyway, I'm very happy with my current Pony / Krita + SUPIR/Light-IC/etc workflow. I used to spend a few days per image before, but now I can generate better ones just in several hours. I still don't know what will become of SD3, but it looks like I can still squeeze a bit more fun out of SDXL while I'm waiting for the next big thing.
I'm still very happy with its ability to depict various lewd concepts with relative precision. It really helps when the model understands tags like "grabbing_another's_breast," for example. I even stopped using my own slave restraints Lora, because the Pony model does it better by default.
On the flip side, I often found its anime origin sips through, even though I'm using a photorealistic variant. This was a typical image I got while I was seed-hunting for my latest render:
As you can see, things like the face or the suit clearly show strong anime/illustration influences. I envy those who create anime-style works since the Pony Diffusion would be a gift from god to them as it is (I have to wonder how gods would think about censorship, though). But as I'm aiming for photorealism, I must find a better way of doing it.
I decided to run it through a non-Pony model, improving realism while destroying the details. The lost details could be recovered by inpainting with the Pony model again since it's much better at keeping with the overall image style when used that way.
There's something which might be worth mentioning that I tried for the first time in my latest render. The original base image looked like this, which I felt rather dull:
I wanted to make it look like they were on a stage with spotlights on the girl's body. It'd make the scene more dramatic while emphasising the girl's humiliation. The problem is that precisely controlling the lighting condition might be very difficult in Stable Diffusion. Well, at least it was so until recently.
Now, we have IC-Light, which allows us to change the lighting condition of an image without destroying its content. With IC-Light, I could add a nice spotlight on the girl's body like this:
On a side note, similar AI technology seems to be making a large impact on filmmaking as well since it allows filmmakers to freely experiment with different lighting setups in the editing room after the shot is taken.
Anyway, I'm very happy with my current Pony / Krita + SUPIR/Light-IC/etc workflow. I used to spend a few days per image before, but now I can generate better ones just in several hours. I still don't know what will become of SD3, but it looks like I can still squeeze a bit more fun out of SDXL while I'm waiting for the next big thing.
fallenmystic
Tribune
Amid the chaos and disappointment after SD3's disastrous release, a glimpse of hope finally emerged:
Civita's announcement: https://civitai.com/articles/5884
InvokeAI's announcement: https://www.invoke.com/the-open-model-initiative
LAION and Comfy are also on board but haven't yet made an announcement.
I've already mentioned many times in this thread why upholding the open-source ideal is essential for AI development, so I won't repeat it here.
So, to summarise the news, a joint effort to develop an open-source AI model for generating images, videos, and audio was just launched.
While several other attempts with a similar goal have been made before (including "Unstable Diffusion," which turns out to be more or less a scam), The Open Model Initiative may be more successful than its predecessors because it was led by those who have the actual knowledge and resources to create capable community models. With Civitai, Comfy, InvokeAI, and LAION all participating in the project, they already have skills, training data, and even the community to support such an endeavour.
It'll probably take quite some time before we can see anything concrete coming out of the project.
But I'm cautiously optimistic about the prospect, considering the members participating in the initiative.
The Open Model Initiative
Civita's announcement: https://civitai.com/articles/5884
InvokeAI's announcement: https://www.invoke.com/the-open-model-initiative
LAION and Comfy are also on board but haven't yet made an announcement.
I've already mentioned many times in this thread why upholding the open-source ideal is essential for AI development, so I won't repeat it here.
So, to summarise the news, a joint effort to develop an open-source AI model for generating images, videos, and audio was just launched.
While several other attempts with a similar goal have been made before (including "Unstable Diffusion," which turns out to be more or less a scam), The Open Model Initiative may be more successful than its predecessors because it was led by those who have the actual knowledge and resources to create capable community models. With Civitai, Comfy, InvokeAI, and LAION all participating in the project, they already have skills, training data, and even the community to support such an endeavour.
It'll probably take quite some time before we can see anything concrete coming out of the project.
But I'm cautiously optimistic about the prospect, considering the members participating in the initiative.
Grendenhal
Condemned
Can anyone recommend a good text-prompt AI generator to make crux images just for my own enjoyment? I don't have the technical capability to use the more complicated tools usually discussed here. I've been using generators such as seduced.ai., soulgen.net, and createporn.com, each of which has its own advantages and disadvantages. FWIW, I can't get any of them to generate an X-cross, although seduced.ai does T-crosses reasonably well.
fallenmystic
Tribune
Unfortunately, there's no model exists that can generate a decent crux scene using prompting alone. You'll need things like Lora, inpainting, etc., to make it work.
If you rely on prompting mostly, Flux could be the best option currently available, followed by Pony variant SDXL models. Note that base Flux models are censored, however, and Pony models require a specific prompt style to be most effective.
By the way, the model determines the quality and level of censorship. Services like those mentioned only differ in what models and frontends they provide. So, check if any of them provides a Flux or Pony model.
P.S.: It's been a while since I last posted here, and a LOT has happened since then, as is expected of a field moving at such a speed. Probably the most shocking news could be that Stable Diffusion is dead now. It's not "dead dead", but effectively so since everyone has moved, or in the process of moving to Flux.
And we'll probably get good NSFW models based on AuraFlow in the foreseeable future, in direct competition with Flux. It's an exciting time to live in for a kink content creator like me.
Last edited:
Grendenhal
Condemned
Thanks! Appreciate the top. I’m just beginning to explore Flux, but it’s clearly a noticeable upgrade over the sites I mentioned. Deformed hands, feet, extra digits, extra limbs are much less of an issue. I haven’t yet figured out models, so, yes, the insistence on loincloths and weird goop covering nipples is odd.
Really the only thing (so far) I like better about seduced.ai is its extensive, detailed ethnic database. You can specify a model from nearly any country and the result is recognizable and distinct.
fallenmystic
Tribune
Just to make sure we're talking about the same thing: What do you mean by "Flux"? What I meant was these two base models, not any specific website that may provide a web-based image generation frontend that uses them:
https://huggingface.co/black-forest-labs
I'm not sure how you're using Flux, but if the method allows you to choose a different model, you may want to try one of the finetunes of Flux.1-dev instead.
While the base model itself is censored, we already have several NSFW finetunes like this one, which I'm using myself. The ecosystem (e.g. Loras, control nets) hasn't fully matured compared with SDXL, but we can already generate uncensored images with it.
Grendenhal
Condemned
I meant the latter, specifically Aitubo. I don't have the skills to use the base models.
fallenmystic
Tribune
Oh, I see. I think Civitai itself could also be a good option for you if a simple paid service with a wide selection of models is what you're looking for.
For now, they only offer Flux base models like Aitubo does, but they'll likely add support for finetunes later since they're already hosting them anyway. Since they're the largest community where people share SD/Pony models, they'll probably play the same role for Flux finetunes when they become more widely available.
Hornet1ba
Governor
One of the newly released Flux NSFW model that gives great results, https://civitai.com/models/161068/stoiqo-newreality-or-flux-sd-xl-lightning?modelVersionId=869391
is also good and respond better for me anyway to my custom made Lora :
(Those 2 are non edited first generated images with the nails missing from the Lora training)
fallenmystic
Tribune
That happens to be the one I’m using myself.
It looks like they haven’t yet found a perfect way to finetune Flux, but considering how it was initially claimed that it was not possible at all to train, I’m sure it’s just a matter of time.
Hornet1ba
Governor
I was not really a fan of AI face swapping until i tried to face swap some AI generated face to some of some of my old Daz animation and results are
quite nice i think!
Sadly this kind of software can be used for creepy usage :-(
Here is a short comparison video hosted at Mega:
https://mega.nz/file/VkknBIIJ#bgEmj3DdEM1lt3TKQlinKTyh8OWnZa8j2H_2n6Go9zk
quite nice i think!
Sadly this kind of software can be used for creepy usage :-(
Here is a short comparison video hosted at Mega:
https://mega.nz/file/VkknBIIJ#bgEmj3DdEM1lt3TKQlinKTyh8OWnZa8j2H_2n6Go9zk
Hornet1ba
Governor
FaceFusion3.0.0 can be automatically installed through Pinokio fairly easily:https://pinokio.computer/item?uri=https://github.com/facefusion/facefusion-pinokio
It can be even be run on CPU, it's a standalone application.
Nice video. Interesting how the women can move when crucified bot never escape the spikes holding them to their cross!