PLEASE put some images in gallery ;)
thx to GraXXXho - 10k Buzz
if you want more , eg only grab no suck or side view, positions... -> give me buzz for training
so thx for the buzz, i can train more :*
ALL training is based on handpicked images (without watermarks). Promt was created with tuned joycaption and corrected manually
trained with 1024pix, if you notice noise raise up resolution up to 1800pix
every lorra does what it says
-> *** ~25steps *** EULER AND (Schedule) DDIM or SGM Uniform or Beta
HINT: GGUF dont work that good (rise up weight), and they are very slow, take one of my suggested fp8 models
AND for more complex poses i suggest to use a distilled model with CGF ~2
if you Raise up "CFG Scale" 2 with neg-prompt: "photo, photograph, realistic" you can force anime/cartoon style (only on special models distilled or use my distilled lora)
play with ALL ages, but i dont train forbidden stuff
rimjob(v2) - pls read my prompts on info symbol on images (i), it is only that working what my images shows, DPM++2M and SGMUniform works well
cowgirl(anal) - seems okay, sometimes body twisted, call mans hair and beard to make him more visible, no cum
doggy-anal - one of five are okay - its a complex pose, try to add some more details to the scene, may increase disitilled CFG to 5,
missio_v2 - more luck with good poses, trained on natural language
dildo_v1 - first shot, read my prompts (is not that easy to train 4-6 positions at once)
cowgirl(vulva) - sometimes weight 0.7 better than 1. start with my prompts and change it slowly
reverse cowgirl(anus) - sometimes bodies are fused or limbs are missing, but otherwise quite okay, start with my prompts! -> for free folks ;) ... (i have trained vagina penetration but it doesnt mater FLUX dont know)
noblow - 1 of 5 are quite ok, cum works not that good, (training is very confusing)
noblow_v2 - you need more explained prompts to get a good image but may be its more felxible (trained on more epoches and joy-captioned) maybe dont call "man", 1 of 3 are okay
missio - start with my prompt (important: view from below or view from above), iam not that happy, only 1 of 5 are good
use -> new checkpoint
side view - play with it (dont trained big/small)
pov_V2 - simple prompt, is more trained, so u can use it stand alone, in some cases weight 1.2
pov_V1 - simple prompt, in some cases i use the loras two times for better images
eg: <lora33:0.8> <lora15:0.4> or vs
play a little with the weight
(i dont trained, pubic hair and text and whatever he/she sucks ^^)
keywords for blowjob_v1/v2: blowjob, pov, deepthroat, small penis, big penis, huge penis, sucking deep, mout stuffed, grab penis, long big black penis, lot of cum on face
you can play with all ages and animals, cum on face only sometimes work, for black penis may add "black mans" and "white skinned woman"
hybrid seems heavy, because no weights in FLUX... tell me if you have an option
Euler: with simple, SGM Uniform, Beta -> i suggest DDIM
steps: ~25 if you have power raise up to 40
1024x704 / 704x1024 or 1200*800 / 800*1200 - most times portrait
weights like pony for prompt words ":1.6" dont work well
Be careful with publications and creations with well-known personalities or minors. I assume no responsibility!
Description
low weight
use it with v1 033
FAQ
Comments (20)
Please post more diverse gallery samples. Do it with different art styles/more complex characters like a female mage or something/etc.
it works ...
@sevenof9247 it works great!
@guy33 THX a lot
"more diverse gallery samples" followed by "female mage" LMAO
How about lizard-people or aliens or muppets? That's more diverse than big titty female mages!
@wktra True. Not really into the lizard thing but that would be more diverse
@wktra Might I suggest doing it with a single ant carrying a entire carrot?
it is all possible, but iam not there for your fantisies :D
Agreed. It takes so little time to do this I wonder if the LoRA is actually any good.
Absolutely extraordinary. This will give me a sleepless night.
sry ^^
I just started using flux today so this may be a dumb question, but does this work with the nf4 model versions? When I try and use it it crashes Forge and I'm not sure if it's the lora itself or if something else is going wrong. I'm using the flux1-dev-bnb-nf4-v2 model.
i use it too "flux1DevV1V2Flux1_flux1DevBNBNF4V2" ... what crash may you open a chat ^^
I have the same issue. It's almost like something with a recent Forge update broke lora compatibility. I can't even generate images with loras that I used before. Like I put the image into png info, to get the same settings and it will throw CUDA error out of memmory kernel error and then freeze the console. changing swap methods/locations doesn't matter. I'm currently redownloading the venv requirements. Hopefully it helps. Edit: It did help kind of, then the error comes back, sometimes with the same prompts. urrg!
@lost_moon set GPU memory to 7000MB
@sevenof9247 I'm not sure what the difference is, but the new side version runs no problem for me! I still can't the pov ones working but this one is giving great results. Thanks!
@skullzy77 thx, which one ov pov? and error or dont get a good image?
@sevenof9247 When using any of the pov ones it gets to "Patching LoRAs for KModel" it will go to 85% and stops then tells me "press any key to continue" and when I do it shuts down Forge. The side view one doesn't give me that issue and works as expected.
it's felixble enough to add other subjects? Wow.
Did you include anything besides sucking dicks in the training data?
yes ... and no ;)
it was similar in sdxl, seems flux also work