Presenting DR34MSC4PE's WAN LoRA:
DR34MJOB - Single and Double Blowjobs (POV+)! It, as a nice surprise, is excellent at handjobs too!
Please remember to like and share - if you like our work, give us a shout below!
===========================================================================
9/20 - Come and get it... WAN 2.2 I2V updates are here!
Note: You need BOTH models to produce good output. If you don't like what you see - adjust the CFG!! We hope you enjoy. =)
===========================================================================
Sample Prompts:
d0ubl3_bj, A close-up view of two women performing a double blowjob on a man's erect penis. The woman on the left has light brown skin blonde slutty pigtail hair. Her nails are manicured with a glittery design as she grasps the base of the penis. The other woman has light tan-lined skin and skin black hair with bows and her eyes are closed. Both women are focused on the man's penis which is circumcised and erect. They both lick and run their lips along the shaft of the man's penis. The background includes a prison cell and bed, their orange jumpers cast aside their nude bodies on the floor. The lighting is bright and even highlighting the details of the subjects' skin and hair. The camera angle is a low close-up shot focusing on the women's faces and the POV 1penis they are pleasuring
bl0wj0b, A close-up view of a blonde woman with fair skin and a slim physique wearing a pink tank top. She is positioned on her knees leaning over a man who is lying on his back. The man has short brown hair and is dressed in a black suit jacket over a light blue shirt. The woman's mouth is open as she licks the head of the man's erect penis which is circumcised. Her eyes are focused intently on the man as she slowly strokes the penis with her right hand. Her left hand rests on the man's right thigh. The background includes a yellow couch and a wooden floor. The lighting is warm and soft creating a cozy atmosphere. The camera angle is slightly above and to the side of the woman providing a clear view of her facial expression and the action.
===========================================================================
DR34MSC4PE is
c0ur4ge (trainer/qa/inference code) /
ERA5ER (captions/tooling code/data/qa)
Be sure to check out our FLUX model - C4PACITOR!
Like our work? Buy us a coffee: https://ko-fi.com/dr34msc4pe
Please generate responsibly!
Keywords/Triggers:
Single BJ: bl0wj0b
Double BJ: d0ub13_bj
Description
FAQ
Comments (45)
For the Wan2.2 lora you could have added some datase where the woman gently bite the head of the cock showing her teeth, there are plenty close up videos like that.. it would have been a real dream blowjob
uhhh I’ll keep this in mind if we ever release N1GHTM4R3
Getting teeth to bite anything is hard, a "flesh bite" lora would likely mix with a lot of things well
@makiaeveli And I'm afraid its pretty close to the line of "generate responsibly" tbh for my tastes but you do you!
bruh
tell me you've totally unironically used the phrase "hi deer plz send bobs and vegana" within the last 24 hrs without telling me you've totally unironically used the phrase "hi deer plz send bobs and vegana" within the last 24 hrs
It's happening! 2.2 ! Now I just have to hope you will add a T2V version soon ;)
DR34ML4Y T2V is next :)
@c0ur4ge I hope it is coming soon =)
@WhatTheGuy I’d suggest trying T2V DR34ML4Y. It should more than suit the need here as it’s trained on this dataset and more!
@c0ur4ge tried it but it often gives wanky movements. maybe bacause all the other concepts are bleeding in? Hm.. I will give it another try ;)
@WhatTheGuy Try the one that will likely come out of early access today and let me know. I think it was just undertrained potentially on certain things. Might still be? But I'm in new territory with 2.2's two model structure and trying not to overcook it and make it overfit/influence too much.
@c0ur4ge I tried the v2. But I also see it with my own loras that wan 2.2 often didn't get the concept as good as wan 2.1 did. At least with the same exact dataset
@WhatTheGuy Well it won’t hurt anything and I may have the training budget to throw this in the oven to see if we can make a better update. Stay tuned.
I want now! I want now! I have 3k energy but I can't spend it fo rsome reason. Give now! Best team for Loras and hopefully we see checkpoint in future!!
Only yellow buzz work for this
BJ is a little generic and boring but this is the least destructive BJ LORA I've messed with to date. Does a great job retaining the I2V subjects.
thanks?
It was trained with images containing the 🍆 inside the frame right?
Nope only on frames of Barney the dinosaur
@c0ur4ge as much as I appreciate the humor I ask because there's another lora with the 🍆 out of frame so the prompt acknowledge "man enters the frame" kind of prompts and I want to know if your does...
@dxjaymz Yup - those prompts work just dandy :)
@c0ur4ge what about a penis already in frame? what WF are we to use?
what WF are we using here?
Does the I2V work with wan2.1 480p ?
How does one get rid of the vague black stripes in the first few frames of the video output? Asking for a friend
seems like the newest update to comfy messed something up on this and dreamlay. i had my settings dialed in and now nothing works well at all. what settings are you guys using? still working for you?
It screwed other models and loras up too. I've reverted back to 3.59 until something gets fixed.
omg same here wtf.
if you're getting upside down penis, try combining/merging or replacing the low lora with Oral Insertion lora https://civitai.com/models/1874153/oral-insertion-wan-22 or Penis Lora https://civitai.com/models/1476909?modelVersionId=2284083
I didn't find your workflow anywhere so I used the WAN 2.2 I2V 14B and used the Loras but for some reason the video gets blurry after the first second. Any fix for this? has anyone figured out the WF?
I had this same problem a few months ago, what you need is a workflow that will combine the lightning loras and the nsfw loras together, I made one specifically for it, it's on my profile with instructions if you wanna give it a shot.
Had the same issue for quite some time. I replaced the lighting Lora altogether with this NSFW lora and changed the start_at_step, end_at_step. I used total 20 steps, 10 for high and 10 for low and the results were pretty good. Open to hearing solutions with lightning with far fewer steps.
When is the wan 2.2 14b t2v version coming champion?
I’d say “maybe next” and for now say to try out DR34ML4Y T2V, tbh if you haven’t yet! It’s got it baked in. :)
Can someone share how to config the accelerators, stes, cfg, shift and LoRA weight?
I would love to use this, but I am new generating videos and I don't know how to configure this LoRA to generate a good video. I have tried others that worked for me, using this specific configuration: 'Lighting v2025 3 phases with 8 steps, CFG 3.5, shift 5, and LoRA weights set to 1.0 (High and Low) in their respective steps.
I am sure my current configuration is wrong for this particular LoRA. In other posts that I can make them work the recommended configuration is posted by the owner, please, Can someone share a config setup or appropriate parameters values for using this LoRA effectively?
Thank you in advance!
I am also a giga noob but I have seen that LoRA weights need to be separate in numbers. High makes the calculation while Low makes computation and refinery, so 0.70-0.30 \ 0.50-0.25 and so on. I did 1-1 and 0.50-0.25 in workflow but did not see any changes in output 🤷♂️
Any workflow for this plz ?
Nice
hen'banghenbanghenbang
Just a note also question ; i was getting blurred results with enhanced q8 model (which it should have lighting loras). then i start testing. only way to reduce blur was lowering low noise weight. i got not bad result at 0.4 low noise lora. If there s another solution im open to listen. btw i used dreamlay lora which it says it has every concept but i couldnt get same saliva effect from it. But also dreamlay doesnt cost any blur on result. it works great. just didnt give me what i liked in dreamjob.
Thanks, it seems that this was the only way to get it to work... was onyl getting noise
hi, i am tying to get a scene to be as close as possible to the cover video - with precum and all. it is almost impossible - i just get bucket load of cum instead of saliva strands, any pointers?
That's an I2V so starting with an image that has it might be in your best bet.
works pretty good, thx a lot !!
Details
Files
DR34MJOB_I2V_14b_HighNoise.safetensors
Mirrors
DR34MJOB_I2V_14b_HighNoise(1).safetensors
DR34MJOB_I2V_14b_HighNoise.safetensors
DR34MJOB_I2V_14b_HighNoise.safetensors
DR34MJOB_I2V_14b_HighNoise.safetensors
DR34MJOB_I2V_14b_HighNoise.safetensors
high.safetensors
DR34MJOB_I2V_14b_HighNoise.safetensors
DR34MJOB_I2V_14b_HighNoise.safetensors
DJ_I2V_14b_HighNoise.safetensors
DR34MJOB_I2V_14b_HighNoise.safetensors
DR34MJOB_I2V_14b_HighNoise.safetensors
DR34MJOB_I2V_14b_HighNoise.safetensors
DR34MJOB_I2V_14b_HighNoise.safetensors
DR34MJOB_I2V_14b_HighNoise.safetensors
DR34MJOB_I2V_14b_HighNoise.safetensors
DR34MJOB_I2V_14b_HighNoise.safetensors
DR34MJOB_I2V_14b_HighNoise.safetensors
DR34MJOB_I2V_14b_HighNoise.safetensors
DR34MJOB_I2V_14b_HighNoise.safetensors
DR34MJOB_I2V_14b_HighNoise.safetensors
DR34MJOB_I2V_14b_HighNoise.safetensors
DR34MJOB_I2V_14b_HighNoise.safetensors
DR34MJOB_I2V_14b_HighNoise.safetensors
DR34MJOB_I2V_14b_HighNoise.safetensors