AI [AI Art] - Show Us Your AI Skill *NO TEENS*

[BlenderGuy]

Guys, I created a character using AI. Is it possible for me to use this character in several sex scenes? Every time I tried, the AI changes my character, and I would like to use it without wanting to change the character characteristics.
View attachment 3543815

When I use an AI generator it will be based on a model, with something called an SDXL refiner.



SDXL Refiner explained below.



AI generation for me is all about correct prompting but also choosing the correct Lora and other parts which complement/contribute to what you actually want.
I have experience in music production daws so I kinda feel this is similar in the way it gives you something, and you decide if
it reflects your choice.

Of course, there are some people out there doing amazing stuff with AI.

You seem to be in the same mind as me.

1. Produce unique character.

2. Pose and manipulate them as if you're using Daz/Blender/Poser but without all the hassle of learning them.

I'm learning Daz3d and Blender as well as Renpy.

I'm also learning AI stuff but I think you'd have to really push your skill set and knowledge to be able to control it in the way those other methods offer.

Of course, this will change over time, as tech has a habit of changing how we do things.

 

[Sgt028]

When I use an AI generator it will be based on a model, with something called an SDXL refiner.

View attachment 3543837

SDXL Refiner explained below.

View attachment 3543842

AI generation for me is all about correct prompting but also choosing the correct Lora and other parts which complement/contribute to what you actually want.
I have experience in music production daws so I kinda feel this is similar in the way it gives you something, and you decide if
it reflects your choice.

Of course, there are some people out there doing amazing stuff with AI.

You seem to be in the same mind as me.

1. Produce unique character.

2. Pose and manipulate them as if you're using Daz/Blender/Poser but without all the hassle of learning them.

I'm learning Daz3d and Blender as well as Renpy.

I'm also learning AI stuff but I think you'd have to really push your skill set and knowledge to be able to control it in the way those other methods offer.

Of course, this will change over time, as tech has a habit of changing how we do things.

Hmm I understand! I will try to study more about it. thanks

 

[BlenderGuy]

Hmm I understand! I will try to study more about it. thanks

The wonderful thing is the fact it's pretty much all open source with people constantly pushing it to the very limits.


Also, the enjoyment you get from the results, even if you messed up, could be a woman with 9 tits and 5 vaginas.

That's a win win in my book!

 

[Leongen43]

 

[EvylEve]

Hmm I understand! I will try to study more about it. thanks

Having a consistent char, that's definitely difficult, I've tried several video tutorials, but still can't get the "perfection" I want, in the end the more consistent results I've got were from txt2img followed by tons of img2img, inpaint and good old Photoshop.

Btw, I would give a look at some foundamental extensions for Stable Diffusion, ADetailer and Reactor, they may help tuning the small bits and faceswapping.

 

[Krysis_here]

♠︎ The Amazon Warrior ♠︎



-------------------------------------------------------------------------------------------------------------------------------------
​

 

[BeriJuns]

Deep orgasm in the fireplace light

 

[BeriJuns]

It is already late in the evening outside

 

[Messalina's Pizzaboy]

Three variations on: "Good morning baby, can I offer you a cup?...."

 

[Mipecio]

 

[Leongen43]

 

[BeriJuns]

Why doesn't anyone join her in the library?

 

[BeriJuns]

 

[phill_leotardo]

Guys, I created a character using AI. Is it possible for me to use this character in several sex scenes? Every time I tried, the AI changes my character, and I would like to use it without wanting to change the character characteristics.
View attachment 3543815

By default Stable Diffusion (assuming it's stable diffusion you're using, not midjourney or DALL-E) generates different characters depending on the pose or seed. In each case you'd need a strategy to keep the characters consistent. Now, if you're using a website to generate your images, I think you'll have more limitations/constraints as I don't imagine they'll let you use controlnet.

If you're using a website, a hint I could give you is to write down your hyperparameters such as positive prompts, negative prompts, model used to generate the images, sampler type, sampling steps, CFG configuration value, width, height and seed.

So, the next time you try to generate new poses, you just change the prompt pose description. Then, use face in-painting in-case you are not satisfied with the similarity and use your image as input.


Now, if you're using Stable Diffusion, you can load your configs by simply clicking on PNG info tab and load your generated image where you have a reference image or image zero and then click on send to text2image, then use openpose ((search civit ai)) and use reActor to automatically do the face in-paint, but do notice it will never be perfectly the same


Watch this video:

You must be registered to see the links

As the wolverine face changes, that is not a feature, but how stable diffusion works, you can search more videos for yourself, they use the extension animediff, you need camera angle tricks to keep the face visibly the same

 

[Krysis_here]

❀ Floral Girl ❀


img2img format​

 

[Leongen43]

 

[Lemmywinks]

 

[Lemmywinks]

 

[Krysis_here]

♮ Greek Goddess ♮ ​

 

[Leongen43]