Update 1/19:
Version 2.0 was retrained on a larger video dataset.
Version 3.0 are helper loras trained on image only dataset. These loras to be used with the Version 2.0 loras. These loras work by themselves but you might not get the motion/ penis shape you're looking for.
Works on both T2V and I2V.
Sample workflow is provided in the attached videos. (Drag and drop the video into your comfyui tab)
Training details are available here: https://civarchive.com/articles/19881
Long prompts are not required. You can keep it simple with a description of the penis you want to see and it should work.
Description
FAQ
Comments (15)
can you make the penis small?
If you provide the dataset, I'll train it.
Does this work for any face, or the training data only have the face shown in the previews videos?
I think I put too much Tifa Lockhart into the dataset. You may need to combine with other character loras to get different faces.
@screamlouder ok, ty
This is great! Getting good motion out of this one.
i am sad to didnt find İ2V at your page
Didn't read the instructions carefully!
It works really well on I2V, besides causing realistic lips to appear in anime characters.
thank you thank you thank you thank you a thousand thank you!!!
I2V?
T2V works for I2V as well.
@screamlouder Is it common for T2V Loras to work for I2V (or is it just in this isolated case?)
@BigJuggsAI I'm not sure but all of my loras that I've trained on T2V work on I2V
@screamlouder Oh super cool. Thanks for the trailblazing work!!
Details
Files
WAN2.2-T2V-Futanari-Flaccid-v1.0.1_HighNoise.safetensors
Mirrors
WAN2.2-T2V-Futanari-Flaccid-v1.0.1_HighNoise.safetensors
WAN2.2-T2V-Futanari-Flaccid-v1.0.1_HighNoise.safetensors
WAN2.2-T2V-Futanari-Flaccid-v1.0.1_HighNoise.safetensors
FlaccidFutanari_HIGH.safetensors
WAN2.2-T2V-Futanari-Flaccid-v1.0.1_HighNoise.safetensors
WAN2.2-T2V-Futanari-Flaccid-v1.0.1_HighNoise.safetensors