run_wan22_moe_i2v_audio.sh

#!/bin/bash

# set path and first
lightx2v_path=
model_path=

# check section
if [ -z "${CUDA_VISIBLE_DEVICES}" ]; then
    cuda_devices=0
    echo "Warn: CUDA_VISIBLE_DEVICES is not set, using default value: ${cuda_devices}, change at shell script or set env variable."
    export CUDA_VISIBLE_DEVICES=${cuda_devices}
fi

if [ -z "${lightx2v_path}" ]; then
    echo "Error: lightx2v_path is not set. Please set this variable first."
    exit 1
fi

if [ -z "${model_path}" ]; then
    echo "Error: model_path is not set. Please set this variable first."
    exit 1
fi

export TOKENIZERS_PARALLELISM=false

export PYTHONPATH=${lightx2v_path}:$PYTHONPATH
export DTYPE=BF16
export ENABLE_PROFILING_DEBUG=true
export ENABLE_GRAPH_MODE=false
export TORCH_CUDA_ARCH_LIST="9.0"
export PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True

#-m debugpy --wait-for-client --listen 0.0.0.0:15684 \

python \
-m lightx2v.infer \
--model_cls wan2.2_moe_audio \
--task i2v \
--model_path $model_path \
--config_json ${lightx2v_path}/configs/wan22/wan_moe_i2v_audio.json \
--prompt  "The video features a old lady is saying something and knitting a sweater." \
--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" \
--image_path ${lightx2v_path}/assets/inputs/audio/15.png \
--audio_path ${lightx2v_path}/assets/inputs/audio/15.wav \
--save_video_path ${lightx2v_path}/save_results/output_lightx2v_wan22_moe_i2v_audio.mp4