I very rarely use Lora, and I don't use real people. I like to fine-tune the prompt to the extreme.
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.
In the context of ComfyUI, there's no workflow. To this day, I still use Forge – I prefer it, it's more comfortable for my way of working, and it feels more intuitive. I've used Comfy as well, and I acknowledge its advantages, but for my meticulous tweaking, Forge suits me better.I would also be interested in tour workflow. Which base model and, if any, which lora do you use for these?
___
Also, I will be posting some more 'wet dreams' soon
Most of the time, I use realistic Pony models. For the café scene, for example, I used the latest version 8.5 of CyberRealistic Pony. As I mentioned, most of the time, I don't use Lora.
One more thing: for me, quality comes first, so I almost always use the DPM++ SDE / Karras sampling method with 40+ steps. In my experience, that gives me the best results.
Thanks for the info, very much appreciated. Now I have a new Checkpoint to play with.
I think they nailed it with the skin for epicrealism's latest SDXL model. bye bye flux!
It also instinctively does upskirts without needing any LORAs or even me adding the prompt at all lol
It also instinctively does upskirts without needing any LORAs or even me adding the prompt at all lol
And their genital penetration is amazing
Edit: Yeah it's official that model is the GOAT. goodbye productivity too...
Edit: Yeah it's official that model is the GOAT. goodbye productivity too...
Last edited:
