No module named 'xformers'

[MoonMoon82]

Hi,

I'm trying to run it the first time, but all I get is the following error message. Any ideas? Thanks in advance!

ComfyUI Error Report

Error Details

• Node Type: DownloadXPortraitModel
• Exception Type: ModuleNotFoundError

• Exception Message: No module named 'xformers'

  Stack Trace

  
  File "E:\StableDiffusion\ComfyUI_windows_portable\ComfyUI\execution.py", line 323, in execute
  output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
                                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  
  File "E:\StableDiffusion\ComfyUI_windows_portable\ComfyUI\execution.py", line 198, in get_output_data
  return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  
  File "E:\StableDiffusion\ComfyUI_windows_portable\ComfyUI\execution.py", line 165, in _map_node_over_list
  process_inputs({})
  
  File "E:\StableDiffusion\ComfyUI_windows_portable\ComfyUI\execution.py", line 158, in process_inputs
  results.append(getattr(obj, func)(**inputs))
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  
  File "E:\StableDiffusion\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-X-Portrait-Nodes\nodes.py", line 82, in load_model
  model = create_model(self.model_config).cpu()
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  
  File "E:\StableDiffusion\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-X-Portrait-Nodes\model_lib\ControlNet\cldm\model.py", line 24, in create_model
  model = instantiate_from_config(config.model).cpu()
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  
  File "E:\StableDiffusion\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-X-Portrait-Nodes\model_lib\ControlNet\ldm\util.py", line 79, in instantiate_from_config
  return get_obj_from_str(config["target"])(**config.get("params", dict()))
         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  
  File "E:\StableDiffusion\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-X-Portrait-Nodes\model_lib\ControlNet\ldm\util.py", line 87, in get_obj_from_str
  return getattr(importlib.import_module(module, package=None), cls)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  
  File "importlib\__init__.py", line 126, in import_module
  
  File "<frozen importlib._bootstrap>", line 1204, in _gcd_import
  
  File "<frozen importlib._bootstrap>", line 1176, in _find_and_load
  
  File "<frozen importlib._bootstrap>", line 1147, in _find_and_load_unlocked
  
  File "<frozen importlib._bootstrap>", line 690, in _load_unlocked
  
  File "<frozen importlib._bootstrap_external>", line 940, in exec_module
  
  File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed
  
  File "E:\StableDiffusion\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-X-Portrait-Nodes\model_lib\ControlNet\cldm\cldm.py", line 14, in <module>
  from model_lib.ControlNet.ldm.models.diffusion.ddpm import LatentDiffusionReferenceOnly
  
  File "E:\StableDiffusion\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-X-Portrait-Nodes\model_lib\ControlNet\ldm\models\diffusion\ddpm.py", line 26, in <module>
  from model_lib.ControlNet.ldm.models.autoencoder import IdentityFirstStage, AutoencoderKL
  
  File "E:\StableDiffusion\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-X-Portrait-Nodes\model_lib\ControlNet\ldm\models\autoencoder.py", line 6, in <module>
  from model_lib.ControlNet.ldm.modules.diffusionmodules.model import Encoder, Decoder
  
  File "E:\StableDiffusion\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-X-Portrait-Nodes\model_lib\ControlNet\ldm\modules\diffusionmodules\model.py", line 12, in <module>
  import xformers

## System Information
- **ComfyUI Version:** v0.2.7-22-g122c9ca
- **Arguments:** ComfyUI\main.py --windows-standalone-build --listen --disable-auto-launch --preview-method auto
- **OS:** nt
- **Python Version:** 3.11.8 (tags/v3.11.8:db85d51, Feb  6 2024, 22:03:32) [MSC v.1937 64 bit (AMD64)]
- **Embedded Python:** true
- **PyTorch Version:** 2.4.1+cu124
## Devices

- **Name:** cuda:0 NVIDIA GeForce RTX 3090 : cudaMallocAsync
  - **Type:** cuda
  - **VRAM Total:** 25769148416
  - **VRAM Free:** 24035646204
  - **Torch VRAM Total:** 402653184
  - **Torch VRAM Free:** 12770044

[akatz-ai]

Hi @MoonMoon82, you will need to install xformers in your comfyui environment. Installing xformers can cause other dependencies to change (like torch versions) so it might be best to try creating a new comfyui environment and trying to install this node first before any others.

[MoonMoon82]

@akatz-ai So I cannot combine the X-Portrait nodes with all my already installed custom nodes? I need to create a new comyUI enviromnet dedicated for the X-Portrait nodes ? Anything else I guess would mess up all the dependencies of my custom nodes.

[OlivioSarikas]

I'm having the same problem and no matter what i try so far, xformers is giving me errors like this: ` RuntimeError: Error compiling objects for extension [end of output]

note: This error originates from a subprocess, and is likely not a problem with pip. ERROR: Failed building wheel for xformers Failed to build xformers ERROR: ERROR: Failed to build installable wheels for some pyproject.toml based projects (xformers)`

[akatz-ai]

Hi all, installing xformers on windows is a challenge due to needing to match the current cuda and pytorch versions I believe, so if there is no wheel found pip tries to compile xformers which requires build tools to be installed. I'm working on a comfyui environment manager that I hope to share soon that should help with environment-specific install issues.