目前使用的版本是去年10月的1.6版本，有点老。希望支持新的特性，于是乎开始作死。从升级torch开始。先看看已有的版本：

<code>(venv) root@ubuntu-sd-server:~# pip show torch

Name: torch

Version: 2.0.1

Summary: Tensors and Dynamic neural networks in Python with strong GPU acceleration

Home-page: https://pytorch.org/

Author: PyTorch Team

Author-email: packages@pytorch.org

License: BSD-3

Location: /root/sd-webui-aki-v4.4/venv/lib/python3.10/site-packages

Requires: filelock, jinja2, networkx, nvidia-cublas-cu11, nvidia-cuda-cupti-cu11, nvidia-cuda-nvrtc-cu11, nvidia-cuda-runtime-cu11, nvidia-cudnn-cu11, nvidia-cufft-cu11, nvidia-curand-cu11, nvidia-cusolver-cu11, nvidia-cusparse-cu11, nvidia-nccl-cu11, nvidia-nvtx-cu11, sympy, triton, typing-extensions

Required-by: accelerate, basicsr, clean-fid, clip, controlnet-aux, facexlib, gfpgan, invisible-watermark, kornia, lpips, open-clip-torch, pytorch-lightning, realesrgan, thop, timm, tomesd, torchdiffeq, torchmetrics, torchsde, torchvision, triton, ultralytics, xformers

然后开始升级最新的2.1.1。幸好空间留的大，升级把一堆相关的都升上去了，好家伙，一下干了快3个G。

(venv) root@ubuntu-sd-server:~# pip install --upgrade torch torchvision

Looking in indexes: https://pypi.doubanio.com/simple

Requirement already satisfied: torch in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (2.0.1)

Collecting torch

Downloading https://mirrors.cloud.tencent.com/pypi/packages/a7/ad/fbe7d4cffb76da4e478438853b51305361c719cff929ab70a808e7fb75e7/torch-2.2.1-cp310-cp310-manylinux1_x86_64.whl (755.5 MB)

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 755.5/755.5 MB 735.0 kB/s eta 0:00:00

Requirement already satisfied: torchvision in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (0.15.2)

Collecting torchvision

Downloading https://mirrors.cloud.tencent.com/pypi/packages/1a/e8/13432ae6be567b577a4c89d1bd50084e4d989b379a7be8050380b5ab3a6e/torchvision-0.17.1-cp310-cp310-manylinux1_x86_64.whl (6.9 MB)

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 6.9/6.9 MB 4.2 MB/s eta 0:00:00

Requirement already satisfied: filelock in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from torch) (3.12.4)

Requirement already satisfied: typing-extensions>=4.8.0 in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from torch) (4.8.0)

Requirement already satisfied: sympy in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from torch) (1.12)

Requirement already satisfied: networkx in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from torch) (3.1)

Requirement already satisfied: jinja2 in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from torch) (3.1.2)

Requirement already satisfied: fsspec in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from torch) (2023.9.2)

Collecting nvidia-cuda-nvrtc-cu12==12.1.105 (from torch)

Downloading https://mirrors.cloud.tencent.com/pypi/packages/b6/9f/c64c03f49d6fbc56196664d05dba14e3a561038a81a638eeb47f4d4cfd48/nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (23.7 MB)

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 23.7/23.7 MB 5.5 MB/s eta 0:00:00

Collecting nvidia-cuda-runtime-cu12==12.1.105 (from torch)

Downloading https://mirrors.cloud.tencent.com/pypi/packages/eb/d5/c68b1d2cdfcc59e72e8a5949a37ddb22ae6cade80cd4a57a84d4c8b55472/nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (823 kB)

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 823.6/823.6 kB 6.4 MB/s eta 0:00:00

Collecting nvidia-cuda-cupti-cu12==12.1.105 (from torch)

Downloading https://mirrors.cloud.tencent.com/pypi/packages/7e/00/6b218edd739ecfc60524e585ba8e6b00554dd908de2c9c66c1af3e44e18d/nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (14.1 MB)

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 14.1/14.1 MB 5.8 MB/s eta 0:00:00

Collecting nvidia-cudnn-cu12==8.9.2.26 (from torch)

Downloading https://mirrors.cloud.tencent.com/pypi/packages/ff/74/a2e2be7fb83aaedec84f391f082cf765dfb635e7caa9b49065f73e4835d8/nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl (731.7 MB)

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 731.7/731.7 MB 825.3 kB/s eta 0:00:00

Collecting nvidia-cublas-cu12==12.1.3.1 (from torch)

Downloading https://mirrors.cloud.tencent.com/pypi/packages/37/6d/121efd7382d5b0284239f4ab1fc1590d86d34ed4a4a2fdb13b30ca8e5740/nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl (410.6 MB)

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 410.6/410.6 MB 1.1 MB/s eta 0:00:00

Collecting nvidia-cufft-cu12==11.0.2.54 (from torch)

Downloading https://mirrors.cloud.tencent.com/pypi/packages/86/94/eb540db023ce1d162e7bea9f8f5aa781d57c65aed513c33ee9a5123ead4d/nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl (121.6 MB)

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 121.6/121.6 MB 3.7 MB/s eta 0:00:00

Collecting nvidia-curand-cu12==10.3.2.106 (from torch)

Downloading https://mirrors.cloud.tencent.com/pypi/packages/44/31/4890b1c9abc496303412947fc7dcea3d14861720642b49e8ceed89636705/nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl (56.5 MB)

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 56.5/56.5 MB 5.8 MB/s eta 0:00:00

Collecting nvidia-cusolver-cu12==11.4.5.107 (from torch)

Downloading https://mirrors.cloud.tencent.com/pypi/packages/bc/1d/8de1e5c67099015c834315e333911273a8c6aaba78923dd1d1e25fc5f217/nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl (124.2 MB)

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 124.2/124.2 MB 3.0 MB/s eta 0:00:00

Collecting nvidia-cusparse-cu12==12.1.0.106 (from torch)

Downloading https://mirrors.cloud.tencent.com/pypi/packages/65/5b/cfaeebf25cd9fdec14338ccb16f6b2c4c7fa9163aefcf057d86b9cc248bb/nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl (196.0 MB)

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 196.0/196.0 MB 2.3 MB/s eta 0:00:00

Collecting nvidia-nccl-cu12==2.19.3 (from torch)

Downloading https://mirrors.cloud.tencent.com/pypi/packages/38/00/d0d4e48aef772ad5aebcf70b73028f88db6e5640b36c38e90445b7a57c45/nvidia_nccl_cu12-2.19.3-py3-none-manylinux1_x86_64.whl (166.0 MB)

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 166.0/166.0 MB 2.6 MB/s eta 0:00:00

Collecting nvidia-nvtx-cu12==12.1.105 (from torch)

Downloading https://mirrors.cloud.tencent.com/pypi/packages/da/d3/8057f0587683ed2fcd4dbfbdfdfa807b9160b809976099d36b8f60d08f03/nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (99 kB)

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 99.1/99.1 kB 15.3 MB/s eta 0:00:00

Collecting triton==2.2.0 (from torch)

Downloading https://mirrors.cloud.tencent.com/pypi/packages/95/05/ed974ce87fe8c8843855daa2136b3409ee1c126707ab54a8b72815c08b49/triton-2.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (167.9 MB)

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 167.9/167.9 MB 2.4 MB/s eta 0:00:00

Collecting nvidia-nvjitlink-cu12 (from nvidia-cusolver-cu12==11.4.5.107->torch)

Downloading https://mirrors.cloud.tencent.com/pypi/packages/58/d1/d1c80553f9d5d07b6072bc132607d75a0ef3600e28e1890e11c0f55d7346/nvidia_nvjitlink_cu12-12.4.99-py3-none-manylinux2014_x86_64.whl (21.1 MB)

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 21.1/21.1 MB 5.8 MB/s eta 0:00:00

Requirement already satisfied: numpy in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from torchvision) (1.23.5)

Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from torchvision) (9.5.0)

Requirement already satisfied: MarkupSafe>=2.0 in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from jinja2->torch) (2.1.3)

Requirement already satisfied: mpmath>=0.19 in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from sympy->torch) (1.3.0)

DEPRECATION: torchsde 0.2.5 has a non-standard dependency specifier numpy>=1.19.*; python_version >= "3.7". pip 24.1 will enforce this behaviour change. A possible replacement is to upgrade to a newer version of torchsde or contact the author to suggest that they release a version with a conforming dependency specifiers. Discussion can be found at https://github.com/pypa/pip/issues/12063

Installing collected packages: triton, nvidia-nvtx-cu12, nvidia-nvjitlink-cu12, nvidia-nccl-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, nvidia-cusparse-cu12, nvidia-cudnn-cu12, nvidia-cusolver-cu12, torch, torchvision

Attempting uninstall: triton

Found existing installation: triton 2.0.0

Uninstalling triton-2.0.0:

Successfully uninstalled triton-2.0.0

Attempting uninstall: torch

Found existing installation: torch 2.0.1

Uninstalling torch-2.0.1:

Successfully uninstalled torch-2.0.1

Attempting uninstall: torchvision

Found existing installation: torchvision 0.15.2

Uninstalling torchvision-0.15.2:

Successfully uninstalled torchvision-0.15.2

ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.

xformers 0.0.20 requires pyre-extensions==0.0.29, which is not installed.

xformers 0.0.20 requires torch==2.0.1, but you have torch 2.2.1 which is incompatible.

Successfully installed nvidia-cublas-cu12-12.1.3.1 nvidia-cuda-cupti-cu12-12.1.105 nvidia-cuda-nvrtc-cu12-12.1.105 nvidia-cuda-runtime-cu12-12.1.105 nvidia-cudnn-cu12-8.9.2.26 nvidia-cufft-cu12-11.0.2.54 nvidia-curand-cu12-10.3.2.106 nvidia-cusolver-cu12-11.4.5.107 nvidia-cusparse-cu12-12.1.0.106 nvidia-nccl-cu12-2.19.3 nvidia-nvjitlink-cu12-12.4.99 nvidia-nvtx-cu12-12.1.105 torch-2.2.1 torchvision-0.17.1 triton-2.2.0

最后还ERROR了，友善的告诉我，xformers要挂了（之前为了节约内存和加速安装了xformers，看了下，最新的版本正好支持torch 2.2.1，于是顺便把xformers也升级了：

(venv) root@ubuntu-sd-server:~# pip install --upgrade xformers

Looking in indexes: https://pypi.doubanio.com/simple

Requirement already satisfied: xformers in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (0.0.20)

Collecting xformers

Downloading https://mirrors.cloud.tencent.com/pypi/packages/81/29/df65a2933a6a9acf19a90e0aef74b0bc69635bbe890204d5d03e7d89c85d/xformers-0.0.25-cp310-cp310-manylinux2014_x86_64.whl (222.5 MB)

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 222.5/222.5 MB 1.6 MB/s eta 0:00:00

Requirement already satisfied: numpy in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from xformers) (1.23.5)

Requirement already satisfied: torch==2.2.1 in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from xformers) (2.2.1)

Requirement already satisfied: filelock in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from torch==2.2.1->xformers) (3.12.4)

Requirement already satisfied: typing-extensions>=4.8.0 in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from torch==2.2.1->xformers) (4.8.0)

Requirement already satisfied: sympy in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from torch==2.2.1->xformers) (1.12)

Requirement already satisfied: networkx in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from torch==2.2.1->xformers) (3.1)

Requirement already satisfied: jinja2 in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from torch==2.2.1->xformers) (3.1.2)

Requirement already satisfied: fsspec in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from torch==2.2.1->xformers) (2023.9.2)

Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from torch==2.2.1->xformers) (12.1.105)

Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from torch==2.2.1->xformers) (12.1.105)

Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from torch==2.2.1->xformers) (12.1.105)

Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from torch==2.2.1->xformers) (8.9.2.26)

Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from torch==2.2.1->xformers) (12.1.3.1)

Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from torch==2.2.1->xformers) (11.0.2.54)

Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from torch==2.2.1->xformers) (10.3.2.106)

Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from torch==2.2.1->xformers) (11.4.5.107)

Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from torch==2.2.1->xformers) (12.1.0.106)

Requirement already satisfied: nvidia-nccl-cu12==2.19.3 in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from torch==2.2.1->xformers) (2.19.3)

Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from torch==2.2.1->xformers) (12.1.105)

Requirement already satisfied: triton==2.2.0 in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from torch==2.2.1->xformers) (2.2.0)

Requirement already satisfied: nvidia-nvjitlink-cu12 in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from nvidia-cusolver-cu12==11.4.5.107->torch==2.2.1->xformers) (12.4.99)

Requirement already satisfied: MarkupSafe>=2.0 in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from jinja2->torch==2.2.1->xformers) (2.1.3)

Requirement already satisfied: mpmath>=0.19 in ./sd-webui-aki-v4.4/venv/lib/python3.10/site-packages (from sympy->torch==2.2.1->xformers) (1.3.0)

DEPRECATION: torchsde 0.2.5 has a non-standard dependency specifier numpy>=1.19.*; python_version >= "3.7". pip 24.1 will enforce this behaviour change. A possible replacement is to upgrade to a newer version of torchsde or contact the author to suggest that they release a version with a conforming dependency specifiers. Discussion can be found at https://github.com/pypa/pip/issues/12063

Installing collected packages: xformers

Attempting uninstall: xformers

Found existing installation: xformers 0.0.20

Uninstalling xformers-0.0.20:

Successfully uninstalled xformers-0.0.20

Successfully installed xformers-0.0.25

又干去222M。。

还有个pyre-extensions提示没装，顺手也装上。

然后拉了最新的ComfyUI，纯净没插件的能跑正常。

把SDWebUI 1.6也启动起来，不出意料的挂了：

################################################################

Launching launch.py...

################################################################

Python 3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]

Version: v1.6.0

Commit hash: 5ef669de080814067961f28357256e8fe27544f4

loading WD14-tagger reqs from /root/sd-webui-aki-v4.4/extensions/stable-diffusion-webui-wd14-tagger/requirements.txt

Checking WD14-tagger requirements.

ReActor preheating... Device: CUDA

Launching Web UI with arguments: --listen --skip-torch-cuda-test --disable-nan-check --skip-version-check --skip-python-version-check --enable-insecure-extension-access --api --xformers --xformers-flash-attention --opt-sdp-attention --no-half-vae --theme=dark --lora-dir /data/models/Lora --vae-dir /data/models/VAE --ckpt-dir /data/models/checkpoint --controlnet-dir /data/models/ControlNet --embeddings-dir /data/models/embeddings

2024-03-26 15:43:54.846349: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.

To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.

*** Error setting up CodeFormer

Traceback (most recent call last):

File "/root/sd-webui-aki-v4.4/modules/codeformer_model.py", line 30, in setup_model

from modules.codeformer.codeformer_arch import CodeFormer

File "/root/sd-webui-aki-v4.4/modules/codeformer/codeformer_arch.py", line 9, in <module>

from modules.codeformer.vqgan_arch import VQAutoEncoder, ResBlock

File "/root/sd-webui-aki-v4.4/modules/codeformer/vqgan_arch.py", line 11, in <module>

from basicsr.utils import get_root_logger

File "/root/sd-webui-aki-v4.4/venv/lib/python3.10/site-packages/basicsr/__init__.py", line 4, in <module>

from .data import *

File "/root/sd-webui-aki-v4.4/venv/lib/python3.10/site-packages/basicsr/data/__init__.py", line 22, in <module>

_dataset_modules = [importlib.import_module(f'basicsr.data.{file_name}') for file_name in dataset_filenames]

File "/root/sd-webui-aki-v4.4/venv/lib/python3.10/site-packages/basicsr/data/__init__.py", line 22, in <listcomp>

_dataset_modules = [importlib.import_module(f'basicsr.data.{file_name}') for file_name in dataset_filenames]

File "/usr/lib/python3.10/importlib/__init__.py", line 126, in import_module

return _bootstrap._gcd_import(name[level:], package, level)

File "/root/sd-webui-aki-v4.4/venv/lib/python3.10/site-packages/basicsr/data/realesrgan_dataset.py", line 11, in <module>

from basicsr.data.degradations import circular_lowpass_kernel, random_mixed_kernels

File "/root/sd-webui-aki-v4.4/venv/lib/python3.10/site-packages/basicsr/data/degradations.py", line 8, in <module>

from torchvision.transforms.functional_tensor import rgb_to_grayscale

ModuleNotFoundError: No module named 'torchvision.transforms.functional_tensor'

---

Traceback (most recent call last):

File "/root/sd-webui-aki-v4.4/launch.py", line 48, in <module>

main()

File "/root/sd-webui-aki-v4.4/launch.py", line 44, in main

start()

File "/root/sd-webui-aki-v4.4/modules/launch_utils.py", line 436, in start

webui.webui()

File "/root/sd-webui-aki-v4.4/webui.py", line 52, in webui

initialize.initialize()

File "/root/sd-webui-aki-v4.4/modules/initialize.py", line 71, in initialize

from modules import gfpgan_model

File "/root/sd-webui-aki-v4.4/modules/gfpgan_model.py", line 4, in <module>

import gfpgan

File "/root/sd-webui-aki-v4.4/venv/lib/python3.10/site-packages/gfpgan/__init__.py", line 3, in <module>

from .data import *

File "/root/sd-webui-aki-v4.4/venv/lib/python3.10/site-packages/gfpgan/data/__init__.py", line 10, in <module>

_dataset_modules = [importlib.import_module(f'gfpgan.data.{file_name}') for file_name in dataset_filenames]

File "/root/sd-webui-aki-v4.4/venv/lib/python3.10/site-packages/gfpgan/data/__init__.py", line 10, in <listcomp>

_dataset_modules = [importlib.import_module(f'gfpgan.data.{file_name}') for file_name in dataset_filenames]

File "/usr/lib/python3.10/importlib/__init__.py", line 126, in import_module

return _bootstrap._gcd_import(name[level:], package, level)

File "/root/sd-webui-aki-v4.4/venv/lib/python3.10/site-packages/gfpgan/data/ffhq_degradation_dataset.py", line 7, in <module>

from basicsr.data import degradations as degradations

File "/root/sd-webui-aki-v4.4/venv/lib/python3.10/site-packages/basicsr/__init__.py", line 4, in <module>

from .data import *

File "/root/sd-webui-aki-v4.4/venv/lib/python3.10/site-packages/basicsr/data/__init__.py", line 22, in <module>

_dataset_modules = [importlib.import_module(f'basicsr.data.{file_name}') for file_name in dataset_filenames]

File "/root/sd-webui-aki-v4.4/venv/lib/python3.10/site-packages/basicsr/data/__init__.py", line 22, in <listcomp>

_dataset_modules = [importlib.import_module(f'basicsr.data.{file_name}') for file_name in dataset_filenames]

File "/usr/lib/python3.10/importlib/__init__.py", line 126, in import_module

return _bootstrap._gcd_import(name[level:], package, level)

File "/root/sd-webui-aki-v4.4/venv/lib/python3.10/site-packages/basicsr/data/realesrgan_dataset.py", line 11, in <module>

from basicsr.data.degradations import circular_lowpass_kernel, random_mixed_kernels

File "/root/sd-webui-aki-v4.4/venv/lib/python3.10/site-packages/basicsr/data/degradations.py", line 8, in <module>

from torchvision.transforms.functional_tensor import rgb_to_grayscale

ModuleNotFoundError: No module named 'torchvision.transforms.functional_tensor'

网上查了一下报错，原来是torch新版本的functional_tensor改成_functional_tensor了，于是vi一下/root/sd-webui-aki-v4.4/venv/lib/python3.10/site-packages/basicsr/data/degradations.py，把文件里的调用修改一下，再启动。

很好，SDWebUI启动起来了

试了下--fp8_e4m3fn-text-enc --fp8_e4m3fn-unet参数启动ComfyUI开启前fp8精度，也貌似正常，明天再继续实测

有惊无险，睡觉。。。