Busty Women - Wan

Wan 2.2 Notes - This model works well with Wan 2.2, but it works best at higher resolutions. At lower resolutions, the character's features are not as true to the model and may have blurring and artifacts. In this case, a 480x720 video counts as a low resolution that didn't look very good. If you can render with 960 on the long edge, you will get better results. Output with plain wan 2.2, causvid v2, and lightx2v all seem to work well. Videos using Wan 2.2 are being posted and will be visible once Civitai's processor gets around to it. I'm still trying out different settings, but for now I recommend using a strength of 1.15 or 1.2 when using this LoRA with Wan 2.2.

Based on the Busty Women Flux LoRA, this model will enhance the bustlines of women in Wan video clips. Trained on Wan 2.1 14b text-to-video, it will work best in that setting. In my testing, it appears to play well with other Wan LoRAs like character and motion models. All of my sample clips were rendered with Boob Physics, for example.

Important: This model is 100% fictitious and is not based on images of any real person. The data set for this model originated with images generated from still image checkpoints and has evolved from there using only AI rendering. No images (neither actual nor AI-generated) of any real person was ever involved in the making of this model.

The data set does include faces because trimming them out was more effort than I wanted to invest at this point so you can expect faces from the stock Wan render to be changed by this LoRA. When I've mixed this model with character models, though, the face change effect is slight and can be improved further by reducing the strength of the Busty Women model.

This model works at any strength from 0.10 to 1.5. Beyond 1.5, the rendering starts to look a little off, but you can play with the strength level and the CFG to find what works best for your situation.

Edit: After more experimentation, it looks like 0.75 is a good strength that still provides a good effect while minimizing interference with other LoRAs and retaining good face diversity.

No keywords are needed. The effect can be enhanced by including words like "busty", "very busty", "large breasts", "huge breasts", etc.

As always, please post your videos back to this model page or at least tag this model in your video posting so I can see what other people are making with the model. I hope you enjoy.