- Aug 1, 2022
- 2,030
- 6,702
Alison next and is the last request i doOh and have some of the fails for fun and giggles. And two Lena and Cindy images as well, more will come.
- May 4, 2017
- 147
- 476
This was a though one, getting that little Diva to sit on the right spot almost drove me into insanity.
But i've managed to improve the comfy workflow quite a bit in the meantime, which is included in the zip file as well as the 4K version.
See ya soon, with more explicit stuff... and also Alison and Cindy or maybe Stan since the fella is badly neglected in the game and deserves some love as well.
Have a good one folks.
But i've managed to improve the comfy workflow quite a bit in the meantime, which is included in the zip file as well as the 4K version.
See ya soon, with more explicit stuff... and also Alison and Cindy or maybe Stan since the fella is badly neglected in the game and deserves some love as well.
Have a good one folks.
Would love some stan stuff. wanna make him a geek with a giant cock!This was a though one, getting that little Diva to sit on the right spot almost drove me into insanity.
But i've managed to improve the comfy workflow quite a bit in the meantime, which is included in the zip file as well as the 4K version.
See ya soon, with more explicit stuff... and also Alison and Cindy or maybe Stan since the fella is badly neglected in the game and deserves some love as well.
Have a good one folks.
I genuinely appreciate it and those look great! However, when I think aggressive gangbang I think more along the lines of airtight with a face covered in nut, tears, and spit.Here to make you feel pleased
________________________________You don't have permission to view the spoiler content. Log in or register now.
More Art here:You must be registered to see the links
- Jun 10, 2019
- 256
- 5,284
- Mar 2, 2021
- 33
- 73
Big thank you to all who gave guides how to use this
- Mar 2, 2021
- 33
- 73
Allison and Jeremy are very busy while Ian is on his stupid beach trip
Sure, it's long overdue (she still hasn't fucked a real man in the game).
Ladies and gentlemen, Ivy!
You don't have permission to view the spoiler content.
Log in or register now.
- Jan 9, 2019
- 127
- 556
New version i have started training, Once again, I implemented some new stuff to the training dataset, there has been any new image added, but I went back to training a large dataset, 490 image, which is probably bad idea, much of training is still voodoo, so I dont know maybe picking 100 image and doing 100 Epoch would be better. anyway.
Its still training there is things I like and things I dont, cant tell if its better or not
29/75 epoch trained so far, I will give 3 example of good I guess
again its barely half way through training but pov stuff with detailed tagging it does well so far. I dont think the artstyle is quite there yet, that really due to the steps and epoch stuff, at some point its not trained enough and after some point it will get fried.
now for bad. Jess. what happened, I am devastated lol.
yea I dont know, the tag was just Jess, so yea less detailed tagging the worse it is for now.
But everything is not lost
Its still training there is things I like and things I dont, cant tell if its better or not
29/75 epoch trained so far, I will give 3 example of good I guess
again its barely half way through training but pov stuff with detailed tagging it does well so far. I dont think the artstyle is quite there yet, that really due to the steps and epoch stuff, at some point its not trained enough and after some point it will get fried.
now for bad. Jess. what happened, I am devastated lol.
yea I dont know, the tag was just Jess, so yea less detailed tagging the worse it is for now.
But everything is not lost
- Feb 7, 2020
- 106
- 1,294
Hello everyone.
Guys, I have been trying new styles and I really liked them, I hope you do too, greetings.
In the next few days I will be publishing lesbian content on my page and other artistic content.
Thanks for your comments and support.
_________________________
More Art:
Guys, I have been trying new styles and I really liked them, I hope you do too, greetings.
You don't have permission to view the spoiler content.
Log in or register now.
In the next few days I will be publishing lesbian content on my page and other artistic content.
You don't have permission to view the spoiler content.
Log in or register now.
Thanks for your comments and support.
_________________________
More Art:
You must be registered to see the links
- Jan 9, 2019
- 127
- 556
Here is the final result, I would like if some of you who uses Stable Diffusion locally on your machine to try and post result and what you guys think, I dont want to put it on Civit Ai and put a new version there if its not needed, but once uploaded it will help the people who uses civitai to generate the images.
I think its better and doesnt have the problems of the last version. But its also over trained, you might have to turn down lora weight to 0.75 or 0.7 but start from 1.0
The faces arent always great on first run still, if its not pov or upclose stuff, but inpainting or upscaling does make it better, to me characters work really well, putting Louise will get you a red head girl with a choker everytime.
as I was writing I did discover the problem, I think there is an issue here, which is the girl names are acting like activation tags, if there is no keep token basically a fixed tag, every tag activates lora, except I needed to train the characters so I kept their name as keep token, it seems to me, that maybe each girl is acting like their own style? I dont know Minnerva and Holly seems to have suffered from this, but yea I will need to see what happens, maybe you guys can try and tell me. same with all the girl, in example put in Ivy and the image comes back purple, How did I forget I used 2 keep tokens last time, because I foresaw this, but forgot this time. As always, I am not an expert on anything, pretty bad on my part.
I think its better and doesnt have the problems of the last version. But its also over trained, you might have to turn down lora weight to 0.75 or 0.7 but start from 1.0
The faces arent always great on first run still, if its not pov or upclose stuff, but inpainting or upscaling does make it better, to me characters work really well, putting Louise will get you a red head girl with a choker everytime.
You must be registered to see the links
as I was writing I did discover the problem, I think there is an issue here, which is the girl names are acting like activation tags, if there is no keep token basically a fixed tag, every tag activates lora, except I needed to train the characters so I kept their name as keep token, it seems to me, that maybe each girl is acting like their own style? I dont know Minnerva and Holly seems to have suffered from this, but yea I will need to see what happens, maybe you guys can try and tell me. same with all the girl, in example put in Ivy and the image comes back purple, How did I forget I used 2 keep tokens last time, because I foresaw this, but forgot this time. As always, I am not an expert on anything, pretty bad on my part.
- Jun 10, 2019
- 256
- 5,284
I think the result is pretty good, thanks for a great job
You don't have permission to view the spoiler content.
Log in or register now.
- May 4, 2017
- 147
- 476
What is the base model you train the Lora on? This can have a significant impact with certain Characters or Styles as keywords like 'Jessica' or 'Holly' for instance may trigger data in the base model. It's always wise to use unique tags for specific features in the lora, like J3ss1ca or H0lly and the like. This way you can tell the AI that you want to specifically trigger training data from the lora. It may also help you to work out specific characteristics, like adding 'mature female' to Minnerva tags and for others using 'young adult' or using tall man for Axel and chubby man for Stan and the like. You can utilize the tags from
You must be registered to see the links
entry to your advantage to work out differences.Below are some examples done with AutismConfetti and no additional tools like face fixers or control net, just simple prompt -> sampler -> output. And for that they turned out pretty good. It sticks to the artstyle with a acceptable bias from the underlying model which can be easily fixed/reduced with a soft style transfer via control net. Base pony sucks at faces who are not upclose so you can only do so much through a lora to remedy this issue. It's better to let ADetailer or other face restoration tools deal with that, instead of focusing on your end on it. The only issue i noticed is the mistletoe with Holly, it happened for me and in CaptainBlt's image above as well.
But all in all you're doing a great job so far and i highly appreciate your efforts. I know what a time consuming process it is to create a lora! <3
Last edited:
- Jan 9, 2019
- 127
- 556
Thanks for tips, I appreciate it. In this case I was lamenting me not putting an activation tag, I think my tagging works for the characters so not too unhappy about that, I removed the activation tag from last version and didnt use it just character tag. I was thinking that I should have used it to make it clear that for the model, as the character tags are the first tag and kept in first place during training, it can create the issue of becoming different style. I did it last time, but not this time.
I use base pony to train to keep it compatible with most models and other style loras.
- Dec 22, 2023
- 30
- 93
- Jun 10, 2019
- 256
- 5,284
