As you might expect, this LoRA will add a cameltoe look to any woman wearing tight enough clothes to support it. The model works equally well in Wan 2.1 and 2.2. This model adds the cameltoe without significant changes to any of the rest of the video. Faces, backgrounds, and motions all look nearly identical at 1.00 strength. See usage notes below.

Important: This model is 100% fictitious and is not based on images of any real person. All source images were generated from still image checkpoints using Stable Diffusion. No images (neither actual nor AI-generated) of any real person was ever involved in the making of this model.

For Wan 2.1, a strength of 1.00 is plenty. For Wan 2.2, a strength of 1.00 also works well and it is only needed in the Low Noise (final stage) model pipeline. You don't need to apply the LoRA to the High Noise section, which helps preserve all the same motion and appearance that you would have without the LoRA. In my testing, the model worked well with any kind of tight clothing. You can reduce the strength for a more subtle effect, or boost the strength above 1.00 for more pronounced look. One of the sample videos used 1.75 strength to illustrate this.

If the woman is wearing loose clothing like a skirt, then do not raise the strength above 1.5 or the model will try and add the cameltoe even to clothing that shouldn't have it. So be aware of the context when you boost strength above 1.0.

The model cooperates well with other LoRAs as you can see in some of the sample videos. It also works from behind, given the right posture and camera angle.

ComfyUI workflow guidance

For my current favorite ComfyUI configuration, please refer to my article for all the necessary info you'll need to make the most of my Wan 2.1 LoRAs in Wan 2.2 videos.

I hope you all find this model helpful, and please don't forgot to link your posts back to this model so I can see the results of everyone's work.