Hi! I intrduce my WAN 2.2 Models 10 steps

Download

FP8/FP16 + Workflows - https://huggingface.co/StefanFalkok/Wan_2.2_10steps/tree/main

GGUF + Workflows - https://huggingface.co/StefanFalkok/Wan_2.2_10steps_GGUF/tree/main (Only Q8_0 at the moment)

Everything u need - just load model without light lora, set 10 steps (5/5), set 2cfg on High Noise and cfg1 on low noise, set 81 frame (16 framerate), set resolution from 480p to 720p

I merged original WAN 2.2 Models from ComfyUI repository with LightX T2V Rank 256 bf 16 (https://huggingface.co/Kijai/WanVideo_comfy/blob/main/Lightx2v/lightx2v_T2V_14B_cfg_step_distill_v2_lora_rank256_bf16.safetensors)

fp8 results on rtx 5080

480p - around 2.5 minutes

1024x576 - around 3.5-4 minutes

720p - around 7.5 minutes

Q8_0 and FP16 take a 25-30% more time to generate video, but you get more quality and stable result

If you need GGUF Q6, Q5, Q4 etc models - send me this in DM or leave comment

My TG Channel - https://t.me/StefanFalkokAI

My TG Chat - https://t.me/+y4R5JybDZcFjMjFi