Worship It

An attempt to make a lora focused on worshiping big cocks. It was trained on 69 clips (not on purpose, the 70th clip had a hard cut so it was cut from the dataset last minute). Never trained a motion Lora before.

T2V is trained on Wan 2.2 T2V fp16 model
I2V is trained on Wan 2.2 I2V fp16model

I started training the model as an I2V because those lora's always gave me better results even with T2V. Due to difficulties renting a GPU, I decided to try a different service to compare speed and price so I opted to train the T2V on the second service. I figured it it worked well enough I'd throw them up on Civitai.

I believe the workflow used to generate the samples was created by a former user - playtime_ai
It utilizes the MoE ksampler.
I get best results using the following settings:

Sampler - er_sde
Scheduler - beta57
Shift - 8
Steps - 8
Lightning - i2v_lightx2v_4step_1022
Str - 1 on both high and low.
(Yes, I use the i2v lightning lora for T2V generations. I don't know why, but it always gives more more dynamic and realistic results).

Trained with the following trigger words:

cock_worship
cock_lick
cock_slap
blowjob
deepthroat
titfuck
handjob

Does somethings better than others. Slapping and titfuck it struggles with. Occasionally does some fun body horror.

Follow up edit: I've added some clarity to the description and will attach a zip file to the T2V Low noise model for all the captions used for Lora training. They all follow the same structure - start with the trigger word(s) featured in the video trained followed by solely focusing on the movement during the video. All videos were 320x320, 81 frames, 16 FPS.

Generate responsibly.