This is the Lora taken directly from Kijai's Huggingface - https://huggingface.co/Kijai/WanVideo_comfy/blob/main/Lightx2v/lightx2v_T2V_14B_cfg_step_distill_v2_lora_rank32_bf16.safetensors

I'm just adding here so I can use it in my metadata

Been using it with Wan2.2 with the following settings to generate images, but it should work for videos:

High - 3

Low - 1.5

Having good results with 6 steps ( 3 in each )