WOOOOOOOOOOO! I got LTX-2 working on my potato of a computer! I am using the Q6 GGUF from Kijai, but it took 18 minutes to generate my first 7 second video. However, the quality was good to great and the sound was perfect with no weirdness and the spoken parts were in sync with lip movements! Granted, Grok Imagine can do this in about 30-40 seconds, but this is on a POTATO!
I am recreating my first video because I didn't use enough descriptive language in the prompt. I got a rather homely looking woman that was slightly overweight screaming into the camera while her boobs jiggled. Changed some of the wording to see if the new video is better. If it has better prompt adherence it may still replace WAN as my go-to depending on how well it handles NSFW content.
FINALLY HIT THE PINNACLE of audio and video, like I imagined!
Punchy