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
This is a helper lora to be used with version 2.0 but can also be used by itself.
FAQ
Comments (9)
It's amazing, works great with anything. I use it a lot with I2V.
Awesome work!
Do you know if I must type the 'magic paragraph' verbatim for it to work or can I insert words (to make the penis bigger) or remove stuff (like removing smooth penis)?
In the description - "Long prompts are not required. You can keep it simple with a description of the penis you want to see and it should work."
@screamlouder Ah cool... sometimes trigger words are mandatory and in this case I can just describe the penis and it should work... awesome!
Wow this is actually incredible.. I've never seen a lora work so well, It can literally adapt to dam near anything. I'm sure it could make a Futa Christmas tree if you wanted, jeez.
Hot lora!! Amazing work dude!! Can you make one without testicles?
If you can send me a dataset, I'll train it.
Can you link to the workflow anywhere? I tried downloading the video and dropping it into comfyui but it doesn't work
I've downloaded every video that I've posted and it always provides the workflow when dropping it into comfyui. But if it is not working for you, you can use this workflow: https://civitai.com/models/1824577/img-to-video-simple-workflow-wan22-or-gguf-or-lora-or-upscale-or-fast
My workflow uses the above as a base with some helper nodes to make changes to the final video.