This model is a merger of Wan-AI/Wan2.2-T2V-A14B-Diffusers and Wan2.2-Lightning v1 model, it can be run with diffusers pipeline.
Running with FastDM:
python gen.py --model-path FastDM/Wan2.2-T2V-A14B-Merge-Lightning-V1.1-Diffusers --architecture wan --guidance-scale 1.0 --height 720 --width 1280 --steps 4 --use-fp8 --output-path ./wan-a14b-lightningv1.1-fp8-guid1.mp4 --num-frames 81 --fps 16 --prompts "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage."
Running with diffusers:
import torch
import numpy as np
from diffusers import WanPipeline, AutoencoderKLWan
from diffusers.utils import export_to_video, load_image
dtype = torch.bfloat16
device = "cuda:2"
vae = AutoencoderKLWan.from_pretrained("FastDM/Wan2.2-T2V-A14B-Merge-Lightning-V1.1-Diffusers", subfolder="vae", torch_dtype=torch.float32)
pipe = WanPipeline.from_pretrained("FastDM/Wan2.2-T2V-A14B-Merge-Lightning-V1.1-Diffusers", vae=vae, torch_dtype=dtype)
pipe.to(device)
height = 720
width = 1280
prompt = "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage."
negative_prompt = "色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走"
output = pipe(
prompt=prompt,
negative_prompt=negative_prompt,
height=height,
width=width,
num_frames=81,
guidance_scale=1.0,
num_inference_steps=4,
).frames[0]
export_to_video(output, "t2v_out.mp4", fps=16)