Photos & Videos AI Tools: How to and Technical Discussion on Creating NSFW Gay Sex Stuff with Stable Diffusion (and others)

Which model did you use? Some of them are heavily geared towards female models.
I've come a long way after a few attempts. I was using the Pony model, but kept coming up with things like this:

1742513724593.png


Eventually I switched to the "Homofidelis" checkpoint and got this:

1742513761575.png
 
Oh, nice one. So why is Virile Stallion available for download on civit.ai, but not available to generate from? I get that I can make an account on tensor.art, but just trying to figure out how this all works.

Virile Stallion - v5.0 Photoreal | Stable Diffusion Checkpoint | Civitai

Also, are there any real advantages to running models locally? Or are online services like civit.ai and tensor.art a superset of what can be done at home? I'm partly trying to gauge if I will build an AI machine as a hobby project. It might be worth it if it gives me access to models or features not available online.
 
Oh, nice one. So why is Virile Stallion available for download on civit.ai, but not available to generate from? I get that I can make an account on tensor.art, but just trying to figure out how this all works.

Virile Stallion - v5.0 Photoreal | Stable Diffusion Checkpoint | Civitai

Also, are there any real advantages to running models locally? Or are online services like civit.ai and tensor.art a superset of what can be done at home? I'm partly trying to gauge if I will build an AI machine as a hobby project. It might be worth it if it gives me access to models or features not available online.
I think the advantages of running locally is no one can access your images. Even though Tensor.Art says they aren't sharing your creations, it is possible they could be shared.

With the cloud services, you're at the mercy of their processor and storage. At present Tensor.Art is load balancing and restricting creations during specific times. Doing everything locally takes all this out of the mix, but you also have to deal with the processing speed and cost.
 
It's fine advertising these. There are a handful of online cloud based private servers/services to host your creations. This one reminds me a little bit of DeepSwap (Deepswap - Best AI Face Swap Online for Video & Photo) in that it seems more specifically tailored to generating your own private 'models'.
Has anyone here installed an AI tool for video face swap on your own machine?

Or is that not feasible due to the needed computing power? For example, how long would a good single machine/gpu need to face swap 1 min of video at a standard framerate? Thanks.
 
Does anyone know if there's a way to import models/loras from Civtai into tensor.art that I'm just completely missing? I've been slowly learning how to use tensor.art and getting some solid results, but the learning curve is still pretty steep and frustrating. I wish the site had as wide of a selection of models as Civtai has :weary_face: