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
Initial Version - Supports both single and double character BJs
Trigger(s) -
single: bl0wj0b
double: d0ub13_bj
FAQ
Comments (25)
I tried it on 14b t2v, but I get an error and I can't generate videos.
Which error did you get? Just curious? I’ve not really tried it for T2V aside from like two quick tests which worked “okay”.
If you use either the RGThree's Power Lora Loader or the GetNode/Set Node plugins, it won't work. If you hook it all up with default nodes, after updating, it should work. Then you slowly put your flow back together to find what nodes are meanie pants >:(
@argkiller97610 - the t2v variant is in training and should be up in a couple/few days
Did you train this with the I2V model? If you train with the T2V model, the lora will work for both T2V and I2V. If you train with the I2V model, it will not work for T2V.
Ii did train on T2V and it was fine. This was I2V - I did a few test generations and they came out alright so I’m not sure what you mean by “it will not work”
I’ll do a specifically T2V variant soon though for testing purposes. Working on FLUX a bit more next.
@c0ur4ge Your answer is confusing. You say "did train on T2V" then "This was I2V"
Not compatible statements. The OP was asking what it was trained on, and if it is T2V that is fine, but if it was I2V then those of us who don't use I2V can pass on downloading. If you mean that it was trained on T2V but your samples were I2V, great! As noted T2V-trained models work universally. I don't understand why people even consider I2V training; I don't see any advantage, and it cuts out a lot of potential users.
@jpXerxes If a lora is trained on the T2V model, it should work for both T2V and I2V. If a model is trained on the I2V model, it will NOT work with T2V.
They said that this lora was trained with the T2V model so in theory it should work on T2V and I2V. I can't get it to work well at all with T2v but it does great with I2V.
@switch_ai Yeah, I expect it doesn't do great without the source image. I can throw a T2V version in the hopper with the same dataset if folks want it!
@c0ur4ge Folks want it. lol
@switch_ai She's in the oven. Now to be patient. :)
Extremely high quality compared to the others out, great job!
Thanks - I thought so too! I was surprised not only are the single concept LoRA “not great” I hated swapping between them when the concepts train better together.
I’m hearing that it even does triple fine? Unexpected but to the point exactly! :)
Nice! It does cumshots too
It sure does - tried to hit all the bases without making the rank/dim/file size too large. I probably should’ve mentioned that in the description :)
Cool, good to know! Any surefire prompts to achieve cumshots? Can it do handjobs too?
@sunburnt_toasty It wasn't trained on the phrase but lots of the captions describe that as part of what's going on so I'd say "yes" if you specifically tell it the subject has their hands on something and are moving them up and down. If you specify that their head/face are near/away from the action, I think it may do what you're asking.
Yes. This is good work. Please continue; I don't quite have a system that can train for Wan.
Wow, clearly know what you're doing! Hunyuan version please!
Thanks a bunch! Be sure to share the best of your batch! ;)
We’ve actually got Hunyuan versions of Double and I’ve got an unreleased single I need to evaluate. I’ll link them here or you can find them on my or @ERA5ER’s profile.
Stay tuned!
Find 'er right here -
HunyuanVideo - Oral - v1.0 | Hunyuan Video LoRA | Civitai
I didn't expect anything less from the guy who made C4PACITOR, one of the very few Flux models that provides almost real freedom to generations. Thank you mate, your LoRA is great and I would wish you could create more LoRAs like this for WAN cause most of what exists is low-to-mid quality.
Cheers - we have fun learning new tech and trying new training techniques. Glad you enjoy. Hoping to give Flux some attention soon… :)
Which version of C4PACITOR are you using?
@Kiefstorm Looking at new “d” variant - we originally were going to release 2.1 (might still). But focusing on a new fine tune of that.
Details
Files
WAN_dr34mj0b.safetensors
Mirrors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
jk.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
dr34mj0b-wan22_14b_i2v_720p.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
dreamjob.safetensors
WAN_dr34mj0b.safetensors
bj-v1-1610465.safetensors
bj-v2-vid.safetensors
bj-v2.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
Dreamjob.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
WAN_dr34mj0b.safetensors
bj.safetensors
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.