git clone https://github.com/Wan-Video/Wan2.2.git

Quitamos flash_attn de requirements (falla en Mac por CUDA)

pip install -r requirements.txt

Instalamos los modelos usando la cli de huggingface

pip install "huggingface_hub[cli]"
huggingface-cli download Wan-AI/Wan2.2-T2V-A14B --local-dir ./Wan2.2-T2V-A14B

Prueba con –offload_model True, –convert_model_dtype and –t5_cpu

python generate.py --offload_model True --convert_model_dtype --t5_cpu --task t2v-A14B --size 1280*720 --ckpt_dir ./Wan2.2-T2V-A14B --offload_model True --convert_model_dtype --prompt "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage."

python generate.py  --task t2v-A14B --size 1280*720 --ckpt_dir ./Wan2.2-T2V-A14B --offload_model True --convert_model_dtype --prompt "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage."

Desde ComfyUI

huggingface-cli download Kijai/WanVideo_comfy umt5-xxl-enc-bf16.safetensors