I actually played the games it's a female link man chillBecause most of the people making all the cuck shit don't play video games, they just see something that's popular and come in to ruin it.
I actually played the games it's a female link man chillBecause most of the people making all the cuck shit don't play video games, they just see something that's popular and come in to ruin it.
its all good pal. everyone has different tastesI liked your creations/images, and I like EVE too, and likes are likes, tastes are tastes, different choices between us here, in this thread, about who is the best girl in the game.
For me, MISSY.
And then the trio CRYSTAL, ODETTE and BETH.
: )
I had to come here to defend my females
View attachment 3695243
; )
This is soo hot!! I would looove to see a scene like this unfold in the game!View attachment 3600223
You don't have permission to view the spoiler content. Log in or register now.
Best girl having a little fun...
View attachment 3695143
You don't have permission to view the spoiler content. Log in or register now.
Although there are finger error in your images but meh! still cool ....Thank man!Best girl having a little fun...
View attachment 3695143
You don't have permission to view the spoiler content. Log in or register now.
Any thoughts on creating unified LORA with all characters combined ?Katya
Perfect work.
The base SS Lora is that. There's a problem with it however. The Lora is trained for free on civitai AI, and they have a 10k step limit for training. The more images your dataset contains, the more steps you'll need.Any thoughts on creating unified LORA with all characters combined ?
I thought about it, but I don't know if I have enough experience. Maybe I will try it sometime in the future, but I have to learn some things. I'm not sure that one big model will be better than the individual small models. And I will probably come across the limits of civitai. Well, we will see.Any thoughts on creating unified LORA with all characters combined ?
Yeah, stable diffusion just kept adding a sixth finger no matter what i tweaked with the prompt / neg prompt. Ai isn't replacing artists anytime soonAlthough there are finger error in your images but meh! still cool ....Thank man!
In other words, be happy with what we have now as it’s a big task to do something that we can do currently do with good results.The base SS Lora is that. There's a problem with it however. The Lora is trained for free on civitai AI, and they have a 10k step limit for training. The more images your dataset contains, the more steps you'll need.
Including all or most of the characters causes the training to require more than 10k steps. As it is, the current Lora is undertrained.
To solve this, we can purchase GPU time to do our training somewhere else than civitai, or train locally with a beefy GPU.
When SD3 comes out, I expect to purchase GPU time to create a new and improved lora. However, it firsts needs to come out. We also might need a sexual base checkpoint like pony diffusion or we'll waste our time. And the full tech update has to release so we have access to high resolution images.
Techupdate has a greater resolution, but with Upscale I will achieve quite good results. If you want to try the new better model and are interested, I would share my datasets. That took me the most work and time.The base SS Lora is that. There's a problem with it however. The Lora is trained for free on civitai AI, and they have a 10k step limit for training. The more images your dataset contains, the more steps you'll need.
Including all or most of the characters causes the training to require more than 10k steps. As it is, the current Lora is undertrained.
To solve this, we can purchase GPU time to do our training somewhere else than civitai, or train locally with a beefy GPU.
When SD3 comes out, I expect to purchase GPU time to create a new and improved lora. However, it firsts needs to come out. We also might need a sexual base checkpoint like pony diffusion or we'll waste our time. And the full tech update has to release so we have access to high resolution images.
Yeah sure, I'd like to see one of your lora dataset. It's true that in this example, DC's art looks much blurrier compared to your upscale. The lines however have a lighter interior in your upscale version. Here, for example:Techupdate has a greater resolution, but with Upscale I will achieve quite good results. If you want to try the new better model and are interested, I would share my datasets. That took me the most work and time.
New Tech Update:
View attachment 3698195
My upscale from old art:
View attachment 3698202