Wan POV Missionary

I2V version: While the T2V model can work really well as I2V, it seems to be picky about resolutions and aspect ratios and things like that. The specifically trained I2V model just seems to work better in more situations. So, it's becoming clear to me that providing an I2V model along with the T2V model is worth it. It uses the same training data as the T2V one, minus the static images. Version 1.1 Updates: Trained at a higher resolution in an attempt to get higher quality outputs. I also added more training data so there's more movement and bouncing breasts. Important parts of the prompt: with her legs spread having sex with a man ... A man is thrusting his penis back and forth inside her vagina at the bottom of the screen {Movement is fast with bouncing breasts|Movement is slow} Her breasts are {small|medium sized|large} Sometimes it may help to put the things you don't want in the negatives. For example, if you want small breasts, putting large breasts in the negative could help. It has a tendency to include tan lines, which I don't totally understand, since most of the training data did not have them, and I captioned the ones that did. You can try adding tan lines to your negatives. A few of my T2V generations at 720p had weird blurring, so you may want to put blurred and out of focus in the negatives. I didn't do a ton of testing at 720p since it takes so long, so I don't know how well it works overall. As before, I included my training settings and a description of the method I used in the training images download. I also included a T2V workflow and an I2V workflow I had some success with. Diffusion pipe has had some updates since I originally made this lora that allows you to train at 480p on a 24GB card. It takes longer to train at this resolution, and I don't know if it's worth it, but the option is at least there.