From Civitai:

UPDATE: This took a lot of experimenting. Rebuilt the entire dataset. Results came out quite nicely. this was trained on about 500ish synthetically generated images on a 'expected' look of pussy and labia detail. real vaginas are so wildly varied it's tough to build a dataset which a model can easily learn - so I made a Synth dataset I more accurately control and thus it learnt better. All images in dataset generated by Krea2. Most if the dataset is pussy shots front and rear. I included closed legs standing as well as lying down spread legs for positioning variation. As a bonus I included some fingering and vulva spreading and object insertion images. This helps teach the model what a pussy looks like under those conditions and I think it worked out very well. 0 videos were used in the training yet you can prompt for some actions like fingering and spreading and they just work. Dildo actions will still need additional lora help, but you are able to promt objects inserted and the pussy will deform mostly correctly.

Enjoy! Go make stuff and post it here.

OLD VERSION: T2V, but may work with other models.

Like everyone else - this is very early experiment. Turned out pretty decent actually.Trained with a fork of Musubi trainer Pyro posted and a custom UI I built for it.All samples are T2V . Havent tested with any of the other modes like ref or i2v but I did run samples with both models.Samples are a little low quality because I was impatient to find the perfect balance. Good thing is that it seems to work with or without all the comfyui cache tricks.Still very early days and I'll keep at it as the training tech develops. Was happy enough to post this early versions