按官方的配置部署完成后，运行不起来呀？是不是配置不对呢？

根据官方配置在windows11上总卡在pip install flash_attn==2.7.4.post1“”，用wsl部署能成功完成，但运行时失，提示如下： python generate_infinitetalk.py
--ckpt_dir weights/Wan2.1-I2V-14B-480P
--wav2vec_dir 'weights/chinese-wav2vec2-base'
--infinitetalk_dir weights/InfiniteTalk/single/infinitetalk.safetensors
--input_json examples/single_example_image.json
--size infinitetalk-480
--sample_steps 40
--mode streaming
--motion_frame 9
--save_file infinitetalk_res Traceback (most recent call last): File "/mnt/d/AI/projects/digital-human/InfiniteTalk/generate_infinitetalk.py", line 19, in import wan File "/mnt/d/AI/projects/digital-human/InfiniteTalk/wan/init.py", line 1, in from . import configs, distributed, modules File "/mnt/d/AI/projects/digital-human/InfiniteTalk/wan/modules/init.py", line 1, in from .attention import flash_attention File "/mnt/d/AI/projects/digital-human/InfiniteTalk/wan/modules/attention.py", line 5, in from ..utils.multitalk_utils import RotaryPositionalEmbedding1D, normalize_and_scale, split_token_counts_and_frame_ids File "/mnt/d/AI/projects/digital-human/InfiniteTalk/wan/utils/init.py", line 7, in from .vace_processor import VaceVideoProcessor File "/mnt/d/AI/projects/digital-human/InfiniteTalk/wan/utils/vace_processor.py", line 5, in import torchvision.transforms.functional as TF File "/home/sand/miniconda3/envs/ai-infintetalk/lib/python3.10/site-packages/torchvision/init.py", line 10, in from torchvision import _meta_registrations, datasets, io, models, ops, transforms, utils # usort:skip File "/home/sand/miniconda3/envs/ai-infintetalk/lib/python3.10/site-packages/torchvision/_meta_registrations.py", line 164, in def meta_nms(dets, scores, iou_threshold): File "/home/sand/miniconda3/envs/ai-infintetalk/lib/python3.10/site-packages/torch/library.py", line 828, in register use_lib._register_fake(op_name, func, _stacklevel=stacklevel + 1) File "/home/sand/miniconda3/envs/ai-infintetalk/lib/python3.10/site-packages/torch/library.py", line 198, in _register_fake handle = entry.fake_impl.register(func_to_register, source) File "/home/sand/miniconda3/envs/ai-infintetalk/lib/python3.10/site-packages/torch/_library/fake_impl.py", line 31, in register if torch._C._dispatch_has_kernel_for_dispatch_key(self.qualname, "Meta"): RuntimeError: operator torchvision::nms does not exist (ai-infintetalk) sand@XiaoQiang10:/mnt/d/AI/projects/digital-human/InfiniteTalk$ python generate_infinitetalk.py
--ckpt_dir weights/Wan2.1-I2V-14B-480P
--wav2vec_dir 'weights/chinese-wav2vec2-base'
--infinitetalk_dir weights/InfiniteTalk/single/infinitetalk.safetensors
--input_json examples/single_example_image.json
--size infinitetalk-480
--sample_steps 40
--mode streaming
--motion_frame 9
--save_file infinitetalk_res

Traceback (most recent call last): File "/mnt/d/AI/projects/digital-human/InfiniteTalk/generate_infinitetalk.py", line 19, in import wan File "/mnt/d/AI/projects/digital-human/InfiniteTalk/wan/init.py", line 1, in from . import configs, distributed, modules File "/mnt/d/AI/projects/digital-human/InfiniteTalk/wan/modules/init.py", line 1, in from .attention import flash_attention File "/mnt/d/AI/projects/digital-human/InfiniteTalk/wan/modules/attention.py", line 5, in from ..utils.multitalk_utils import RotaryPositionalEmbedding1D, normalize_and_scale, split_token_counts_and_frame_ids File "/mnt/d/AI/projects/digital-human/InfiniteTalk/wan/utils/init.py", line 7, in from .vace_processor import VaceVideoProcessor File "/mnt/d/AI/projects/digital-human/InfiniteTalk/wan/utils/vace_processor.py", line 5, in import torchvision.transforms.functional as TF File "/home/sand/miniconda3/envs/ai-infintetalk/lib/python3.10/site-packages/torchvision/init.py", line 10, in from torchvision import _meta_registrations, datasets, io, models, ops, transforms, utils # usort:skip File "/home/sand/miniconda3/envs/ai-infintetalk/lib/python3.10/site-packages/torchvision/_meta_registrations.py", line 164, in def meta_nms(dets, scores, iou_threshold): File "/home/sand/miniconda3/envs/ai-infintetalk/lib/python3.10/site-packages/torch/library.py", line 828, in register use_lib._register_fake(op_name, func, _stacklevel=stacklevel + 1) File "/home/sand/miniconda3/envs/ai-infintetalk/lib/python3.10/site-packages/torch/library.py", line 198, in _register_fake handle = entry.fake_impl.register(func_to_register, source) File "/home/sand/miniconda3/envs/ai-infintetalk/lib/python3.10/site-packages/torch/_library/fake_impl.py", line 31, in register if torch._C._dispatch_has_kernel_for_dispatch_key(self.qualname, "Meta"): RuntimeError: operator torchvision::nms does not exist