MiniMax H3 T2V/I2V
V2.0

Finally got around to fixing some of the weird shit this LoRa was doing. in this new version we have:

• Better shape overall.

• More realistic movement and placement.

• More diverse body types. (It'll still default to hunky, but you can prompt otherwise and it wont fight you as much as the first one.)

• Less "joggin' in place" and weird zoom ins. I was FINALLY able to remove this. Can't wait to see what weird shit it inadvertentlylearned this time...

Let me know how it works for you!

If you want to help me out you can use my Runpod referal link (HERE) to get some free credits for you and for me. I used THIS template to generate all the samples you see above.

If you enjoyed this Lora, consider kicking a few bucks my way!
https://ko-fi.com/jouhellerxxx

V1.0

Took me a while to figure this one out, but I think this is a solid first version.

MiniMax is amazing, but a bitch to train for. Mainly because it learns too much and one or two items in your dataset can lead to weird behaviour.

For instance, too many closeups in this one makes it want to constanly zoom in or focus on the dick (which is kind of anoying when you don't want that). Ajusting the lora stregnth can help with this; you can get away with a as little as 0.6 strength if the subject is not in the forefront.

Keep in mind that the keyword is necessary for this one, otherwise you'll just get lumpy blobs.

I'll probably come back to this for a V2, but not until next month, Training is expensive as fuck, especially for video models.