DESCRIPTION
Technique consisting in a fine-tuned AI model [WAN 2.1 / txt2vid]. Hundreds of hours of training and testing. Still far from good (highly experimental), but hopefully getting somewhere. I'm a huge fan of this technique.The following contains:- (2) WAN 2.1 TXT2VID LORAs [512x512 / 832x480]- Dictionary/Caption files.- Best video generations [64 out of 1000+ generations] + Prompts