Sign In

WAN2.2-14B T2V-T2I Prehistoric -> Futuristic slider - v1.0 Low noise Showcase

futuristic_lora_v1_01.jpg
futuristic_lora_v1_02.jpg
futuristic_lora_v1_03.jpg
futuristic_lora_v1_04.jpg
futuristic_lora_v1_05.jpg
futuristic_lora_v1_06.jpg
futuristic_lora_v1_07.jpg
futuristic_lora_v1_14.jpg
futuristic_lora_v1_09.jpg
futuristic_lora_v1_10.jpg
futuristic_lora_v1_11.jpg
futuristic_lora_v1_12.jpg
futuristic_lora_v1_13.jpg

What you must know :
I didn't use WAN for video generation, but only for image generation, by the way, the High-noise lora was not tested, as I use only the low-noise checkpoint.

Made with Ostris AI-Toolkit on a low-end hardware(*1). 75 steps used as it seems to me the best results (I've tested from 25 steps to 300 steps).

Recommended maximum strength is -7.5 / +7.5, but you can test further, it will depend on other loras and/or prompt.

At high positive strength, the persons could become like puppets.


Comments appreciated.

(*1) : Made on a laptop with 32Gb of RAM, and mobile RTX4060 with 8Gb of VRAM.

Comments