i cant install these nodes (anymore)

[lost-in-emotions]

after the comfy update i get red borders on my nodes.
even when i try to install a other version, it wont help.
with the new manager im even not able to change another version.
is there a solution in the making? thats would be great.

[naxci1]

Manual installation is more accurate; sometimes the Manager fails to install correctly. First, close comfyui, then open the terminal in the comfyui installation directory. Delete the seedvr2 directory completely within the custom_nodes directory (etc: C:\ComfyUI\ComfyUI\custom_nodes\seedvr2_videoupscaler). Afterwards, download it again using the following command in the terminal.

git clone https://github.com/numz/ComfyUI-SeedVR2_VideoUpscaler.git seedvr2_videoupscaler

.venv\Scripts\python.exe -m pip install -r seedvr2_videoupscaler\requirements.txt

If the second command doesn't work, you should run portable comfyui from a subdirectory if you're using it.

..\..\python_embeded\python.exe -m pip install -r seedvr2_videoupscaler\requirements.txt

You can open Comfyui after the installation is complete.

[Winnougan]

Still doesn't work. Even in a conda environment. We need this repo updated

[lost-in-emotions]

Just done the manually installation (with step 2), but its still not working:

[naxci1]

uninstall - restart - install

[lost-in-emotions]

@naxci1 install: what Version?

EDIT: i restartet and refreshed comfy (portable) and its still there.
it was not uninstalled, even that i done this ...?!

[naxci1]

You need to check the ComfyUI installation directory. For example, is seedvr2 present in that directory? If so, delete it. Then download it manually, or download it as a zip file, create a directory there, and add it. Or clone it using Git. After that, install the requirements file, as I mentioned above.

C:\ComfyUI\ComfyUI\custom_nodes

[lost-in-emotions]

@naxci1 yes, yes...
but i have done it exactly what you say, and now its "locked".
it would be the same procedure as i have done before:

1.) closed Comfy

2.) deleted the Folder in custom_nodes (and .disabled)

3.) git clone https://github.com/numz/ComfyUI-SeedVR2_VideoUpscaler.git seedvr2_videoupscaler

4.) ....\python_embeded\python.exe -m pip install -r seedvr2_videoupscaler\requirements.txt

5.) opened Comfy - still Error

6.) i made the Screenshot from above

7.) i want to deinstall over the manager, restart and refresh, but its still there.

What Version ist the correct Version to install? -> the LATEST: 2.5.22 ?

[naxci1]

send me full comfyui log

[lost-in-emotions]

** Log path: E:\Working\ComfyUI_windows_portable\ComfyUI\user\comfyui.log

Prestartup times for custom nodes:
   0.0 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-easy-use
   0.0 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\rgthree-comfy
   2.4 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-manager

E:\Working\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\cuda\__init__.py:65: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
  import pynvml  # type: ignore[import]
Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_mxfp8', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'scaled_mm_mxfp8', 'scaled_mm_nvfp4']}
Found comfy_kitchen backend triton: {'available': True, 'disabled': True, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8']}
Found comfy_kitchen backend cuda: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'scaled_mm_nvfp4']}
Checkpoint files will always be loaded safely.
Total VRAM 8192 MB, total RAM 32133 MB
pytorch version: 2.10.0+cu130
WARNING[XFORMERS]: xFormers can't load C++/CUDA extensions. xFormers was built for:
    PyTorch 2.10.0+cu128 with CUDA 1208 (you have 2.10.0+cu130)
    Python  3.10.11 (you have 3.13.9)
  Please reinstall xformers (see https://github.com/facebookresearch/xformers#installing-xformers)
  Memory-efficient attention, SwiGLU, sparse and more won't be available.
  Set XFORMERS_MORE_DETAILS=1 for more details
Set vram state to: LOW_VRAM
Device: cuda:0 NVIDIA GeForce RTX 3060 Ti : cudaMallocAsync
Using async weight offloading with 2 streams
Enabled pinned memory 12853.0
working around nvidia conv3d memory bug.
Using pytorch attention
DynamicVRAM support detected and enabled
Python version: 3.13.9 (tags/v3.13.9:8183fa5, Oct 14 2025, 14:09:13) [MSC v.1944 64 bit (AMD64)]
ComfyUI version: 0.18.1
comfy-aimdo version: 0.2.12
comfy-kitchen version: 0.2.8
ComfyUI frontend version: 1.42.8
[Prompt Server] web root: E:\Working\ComfyUI_windows_portable\python_embeded\Lib\site-packages\comfyui_frontend_package\static
Asset seeder disabled
Skipping import of cpp extensions due to incompatible torch version 2.10.0+cu130 for torchao version 0.15.0             Please see https://github.com/pytorch/ao/issues/2919 for more info
W0409 14:48:49.878000 15916 Lib\site-packages\torch\distributed\elastic\multiprocessing\redirects.py:29] NOTE: Redirects are currently not supported in Windows or MacOs.
[E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfy-mtb] | INFO -> loaded 103 nodes successfuly
[E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfy-mtb] | INFO -> Some nodes (5) could not be loaded. This can be ignored, but go to http://127.0.0.1:8188/mtb if you want more information.
Adding E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes to sys.path
Could not find efficiency nodes
[comfyui_controlnet_aux] | INFO -> Using ckpts path: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\ckpts
[comfyui_controlnet_aux] | INFO -> Using symlinks: False
[comfyui_controlnet_aux] | INFO -> Using ort providers: ['CUDAExecutionProvider', 'DirectMLExecutionProvider', 'OpenVINOExecutionProvider', 'ROCMExecutionProvider', 'MIGraphXExecutionProvider', 'CPUExecutionProvider', 'CoreMLExecutionProvider']
DWPose: Onnxruntime with acceleration providers detected
Loaded comfyui_controlnet_aux nodes from E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux
Could not find AdvancedControlNet nodes
Could not find AnimateDiff nodes
Could not find IPAdapter nodes
Could not find VideoHelperSuite nodes
### Loading: ComfyUI-Impact-Pack (V8.28.2)
### Loading: ComfyUI-Impact-Pack (V8.28.2)
[Impact Pack] Wildcard total size (0.00 MB) is within cache limit (50.00 MB). Using full cache mode.
Loaded ImpactPack nodes from E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-impact-pack
[Impact Pack] Wildcards loading done.
[Impact Pack] Wildcard total size (0.00 MB) is within cache limit (50.00 MB). Using full cache mode.
[Impact Pack] Wildcards loading done.
Module 'diffusers' load failed. If you don't have it installed, do it:
pip install diffusers
[ComfyUI-Easy-Use] server: v1.3.6 Loaded
[ComfyUI-Easy-Use] web root: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-easy-use\web_version/v2 Loaded
ComfyUI-GGUF: Allowing full torch compile
### Loading: ComfyUI-Impact-Pack (V8.28.2)
[Impact Pack] Wildcard total size (0.00 MB) is within cache limit (50.00 MB). Using full cache mode.
[Impact Pack] Wildcards loading done.
### Loading: ComfyUI-Impact-Subpack (V1.3.5)
[Impact Pack/Subpack] Using folder_paths to determine whitelist path: E:\Working\ComfyUI_windows_portable\ComfyUI\user\default\ComfyUI-Impact-Subpack\model-whitelist.txt
[Impact Pack/Subpack] Ensured whitelist directory exists: E:\Working\ComfyUI_windows_portable\ComfyUI\user\default\ComfyUI-Impact-Subpack
[Impact Pack/Subpack] Loaded 0 model(s) from whitelist: E:\Working\ComfyUI_windows_portable\ComfyUI\user\default\ComfyUI-Impact-Subpack\model-whitelist.txt
[Impact Subpack] ultralytics_bbox: E:\Working\ComfyUI_windows_portable\ComfyUI\models\ultralytics\bbox
[Impact Subpack] ultralytics_segm: E:\Working\ComfyUI_windows_portable\ComfyUI\models\ultralytics\segm
### Loading: ComfyUI-Manager (V3.39.2)
[ComfyUI-Manager] network_mode: public
[ComfyUI-Manager] ComfyUI per-queue preview override detected (PR #11261). Manager's preview method feature is disabled. Use ComfyUI's --preview-method CLI option or 'Settings > Execution > Live preview method'.
### ComfyUI Version: v0.18.1-53-gb615af1c6 | Released on '2026-04-07'
Error loading module AILab_QwenVL_GGUF_PromptEnhancer: No module named 'llama_cpp'
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
Error loading E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-rmbg\SDMatte\utils\replace.py: Failed to import diffusers.models.unets.unet_2d_condition because of the following error (look up to see its traceback):
DLL load failed while importing _C: Das angegebene Modul wurde nicht gefunden.
Error loading E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-rmbg\SDMatte\utils\utils.py: DLL load failed while importing _C: Das angegebene Modul wurde nicht gefunden.
Error loading E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-rmbg\SDMatte\modeling\SDMatte\meta_arch.py: Failed to import diffusers.models.autoencoders.autoencoder_kl because of the following error (look up to see its traceback):
DLL load failed while importing _C: Das angegebene Modul wurde nicht gefunden.
Error loading E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-rmbg\sam3\model\decoder.py: attempted relative import with no known parent package
Error loading E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-rmbg\sam3\model\encoder.py: attempted relative import with no known parent package
Error loading E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-rmbg\sam3\model\geometry_encoders.py: attempted relative import with no known parent package
Error loading E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-rmbg\sam3\model\maskformer_segmentation.py: attempted relative import with no known parent package
Error loading E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-rmbg\sam3\model\memory.py: attempted relative import with no known parent package
Error loading E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-rmbg\sam3\model\sam3_image.py: attempted relative import with no known parent package
Error loading E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-rmbg\sam3\model\text_encoder_ve.py: attempted relative import with no known parent package
Error loading E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-rmbg\sam3\model\vitdet.py: attempted relative import with no known parent package
Error loading E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-rmbg\sam3\model\vl_combiner.py: attempted relative import with no known parent package
Error loading E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-rmbg\sam3\sam\mask_decoder.py: attempted relative import with no known parent package
Error loading E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-rmbg\sam3\sam\prompt_encoder.py: attempted relative import with no known parent package
Error loading E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-rmbg\sam3\sam\transformer.py: attempted relative import with no known parent package
Error loading E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-rmbg\sam3\train\trainer.py: No module named 'tensorboard'
Error loading E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-rmbg\sam3\train\data\collator.py: attempted relative import with no known parent package
Error loading E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-rmbg\sam3\train\data\sam3_image_dataset.py: attempted relative import with no known parent package
Error loading E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-rmbg\sam3\train\data\sam3_video_dataset.py: attempted relative import with no known parent package
Error loading E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-rmbg\sam3\train\loss\loss_fns.py: attempted relative import with no known parent package
Error loading E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-rmbg\sam3\train\loss\sam3_loss.py: attempted relative import with no known parent package
Error loading E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-rmbg\sam3\train\utils\logger.py: No module named 'tensorboard'
Error loading E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-rmbg\sam3\perflib\tests\tests.py: No module named 'pytest'
[ComfyUI-RMBG] v3.0.0 | 44 nodes Loaded
[UmeAiRT-Toolkit] Logic Nodes: Could not import FaceDetailer internals: No module named 'E:\\Working\\ComfyUI_windows_portable\\ComfyUI\\custom_nodes\\comfyui-umeairt-toolkit.modules.facedetailer_core'
[UmeAiRT-Toolkit] 🧩 Loaded 47 nodes.
[UmeAiRT-Toolkit] ⚡ Optimisation check: SageAttention ✅ | Flash Attention ❌ | Triton ✅
[UmeAiRT-Toolkit] 💡 Optional: pip install flash-attn
[UmeAiRT-Toolkit] 📊 Initial CUDA memory: 6.97GB free / 8.00GB total
[UmeAiRT-Toolkit] ✅ Initialization Complete.
WanVideoWrapper WARNING: FantasyPortrait nodes not available: No module named 'onnx'
------------------------------------------
Comfyroll Studio v1.76 :  175 Nodes Loaded
------------------------------------------
** For changes, please see patch notes at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/blob/main/Patch_Notes.md
** For help, please see the wiki at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/wiki
------------------------------------------
[E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using ckpts path: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\ckpts
[E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using symlinks: False
[E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using ort providers: ['CUDAExecutionProvider', 'DirectMLExecutionProvider', 'OpenVINOExecutionProvider', 'ROCMExecutionProvider', 'MIGraphXExecutionProvider', 'CPUExecutionProvider', 'CoreMLExecutionProvider']
# 😺dzNodes: LayerStyle -> Cannot import name 'guidedFilter' from 'cv2.ximgproc'
A few nodes cannot works properly, while most nodes are not affected. Please REINSTALL package 'opencv-contrib-python'.
For detail refer to https://github.com/chflame163/ComfyUI_LayerStyle/issues/5
USDU batch patches applied successfully.
USDU batch patches applied successfully.
Using pytorch attention
(RES4LYF) Init
(RES4LYF) Importing beta samplers.
(RES4LYF) Importing legacy samplers.

[rgthree-comfy] Loaded 48 extraordinary nodes. 🎉

[rgthree-comfy] ComfyUI's new Node 2.0 rendering may be incompatible with some rgthree-comfy nodes and features, breaking some rendering as well as losing the ability to access a node's properties (a vital part of many nodes). It also appears to run MUCH more slowly spiking CPU usage and causing jankiness and unresponsiveness, especially with large workflows. Personally I am not planning to use the new Nodes 2.0 and, unfortunately, am not able to invest the time to investigate and overhaul rgthree-comfy where needed. If you have issues when Nodes 2.0 is enabled, I'd urge you to switch it off as well and join me in hoping ComfyUI is not planning to deprecate the existing, stable canvas rendering all together.

⚡ SeedVR2 optimizations check: SageAttention ✅ | Flash Attention ❌ | Triton ✅
💡 Optional: pip install flash-attn
🔧 Conv3d workaround active: PyTorch 2.10.0, cuDNN 91200 (fixing VAE 3x memory bug)
📊 Initial CUDA memory: 6.91GB free / 8.00GB total
Traceback (most recent call last):
  File "E:\Working\ComfyUI_windows_portable\ComfyUI\nodes.py", line 2227, in load_custom_node
    module_spec.loader.exec_module(module)
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^
  File "<frozen importlib._bootstrap_external>", line 1027, in exec_module
  File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
  File "E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\seedvr2_videoupscaler\__init__.py", line 7, in <module>
    from .src.interfaces import comfy_entrypoint, SeedVR2Extension
  File "E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\seedvr2_videoupscaler\src\interfaces\__init__.py", line 8, in <module>
    from .video_upscaler import SeedVR2VideoUpscaler
  File "E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\seedvr2_videoupscaler\src\interfaces\video_upscaler.py", line 10, in <module>
    from ..utils.downloads import download_weight
  File "E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\seedvr2_videoupscaler\src\utils\downloads.py", line 14, in <module>
    from .model_registry import MODEL_REGISTRY, DEFAULT_VAE
  File "E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\seedvr2_videoupscaler\src\utils\model_registry.py", line 12, in <module>
    from ..models.dit_3b.nadit import NaDiT as NaDiT3B
  File "E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\seedvr2_videoupscaler\src\models\dit_3b\nadit.py", line 24, in <module>
    from .embedding import TimeEmbedding
  File "E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\seedvr2_videoupscaler\src\models\dit_3b\embedding.py", line 17, in <module>
    from diffusers.models.embeddings import get_timestep_embedding
  File "E:\Working\ComfyUI_windows_portable\python_embeded\Lib\site-packages\diffusers\models\embeddings.py", line 24, in <module>
    from .attention_processor import Attention
  File "E:\Working\ComfyUI_windows_portable\python_embeded\Lib\site-packages\diffusers\models\attention_processor.py", line 35, in <module>
    import xformers.ops
  File "E:\Working\ComfyUI_windows_portable\python_embeded\Lib\site-packages\xformers\ops\__init__.py", line 9, in <module>
    from .fmha import (
    ...<13 lines>...
    )
  File "E:\Working\ComfyUI_windows_portable\python_embeded\Lib\site-packages\xformers\ops\fmha\__init__.py", line 10, in <module>
    from . import (
    ...<8 lines>...
    )
  File "E:\Working\ComfyUI_windows_portable\python_embeded\Lib\site-packages\xformers\ops\fmha\flash3.py", line 110, in <module>
    from ...flash_attn_3 import _C  # type: ignore[attr-defined]  # noqa: F401
    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ImportError: DLL load failed while importing _C: Das angegebene Modul wurde nicht gefunden.

Cannot import E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\seedvr2_videoupscaler module for custom nodes: DLL load failed while importing _C: Das angegebene Modul wurde nicht gefunden.

Import times for custom nodes:
   0.0 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\websocket_image_save.py
   0.0 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Z-Engineer
   0.0 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-detail-daemon
   0.0 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\zimagelatent
   0.0 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\cg-use-everywhere
   0.0 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-qwenmultiangle
   0.0 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-GGUF
   0.0 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-impact-subpack
   0.0 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-various
   0.0 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-florence2
   0.0 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_essentials
   0.0 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-load-lora-from-url
   0.0 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-image-saver
   0.0 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-QwenVL
   0.0 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-custom-scripts
   0.0 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_ultimatesdupscale
   0.0 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-impact-pack
   0.0 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-frame-interpolation
   0.0 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\gguf
   0.0 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\reservedvram
   0.0 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-umeairt-toolkit
   0.0 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-kjnodes
   0.0 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux
   0.0 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_Comfyroll_CustomNodes
   0.0 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\rgthree-comfy
   0.1 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-videohelpersuite
   0.1 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-advancedliveportrait
   0.1 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_layerstyle
   0.2 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-WanVideoWrapper
   0.2 seconds (IMPORT FAILED): E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\seedvr2_videoupscaler
   0.2 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\RES4LYF
   0.2 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-manager
   0.6 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\audio-separation-nodes-comfyui
   0.7 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-art-venture
   1.5 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfy-mtb
   1.7 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-easy-use
   2.2 seconds: E:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-rmbg

Context impl SQLiteImpl.
Will assume non-transactional DDL.
Starting server

To see the GUI go to: http://127.0.0.1:8188
FETCH ComfyRegistry Data: 5/137
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/clipspace.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/groupNode.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/widgetInputs.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
ComfyUI-GGUF: Allowing full torch compile
📊 Initial CUDA memory: 6.91GB free / 8.00GB total
[UmeAiRT-Toolkit] SeedVR2: Using vendored copy
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/button.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/buttonGroup.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
FETCH ComfyRegistry Data: 10/137
FETCH ComfyRegistry Data: 15/137
FETCH ComfyRegistry Data: 20/137
FETCH ComfyRegistry Data: 25/137
FETCH ComfyRegistry Data: 30/137
FETCH ComfyRegistry Data: 35/137

[naxci1]

Based on your log files, the primary issues are version mismatches and missing dependencies, specifically regarding xFormers and the Diffusers library.

Core Problems and Solutions

1. xFormers Version Mismatch
   The log shows you are using PyTorch 2.10.0+cu130, but your xFormers was built for 2.10.0+cu128. Additionally, xFormers is struggling with Python 3.13.

Fix: Either reinstall xFormers specifically for your CUDA version or add --disable-xformers to your startup arguments to use standard PyTorch attention.

2. Diffusers and DLL Load Failures
   Many nodes (like RMBG and SeedVR2) are failing because diffusers cannot load its C++ extensions. This is often caused by missing components in the portable Python environment or incompatible versions.

Fix: Run a forced reinstall of the diffusers library using the embedded Python executable.

3. Missing Modules (llama_cpp, tensorboard, onnx)
   Several custom nodes are skipping features because specific libraries are missing from your python_embedded folder.

Fix: You need to manually install llama-cpp-python for Qwen, tensorboard for RMBG, and onnxruntime-gpu for WanVideo.

4. OpenCV Contrib Issue
   The LayerStyle nodes are failing because the standard opencv-python is installed instead of the contrib version which contains the guidedFilter algorithm.

Fix: Uninstall all OpenCV versions and install opencv-contrib-python exclusively.

Recommended Actions
Run these commands in your terminal using the path to your portable Python:

Repair Core Libraries:
E:\Working\ComfyUI_windows_portable\python_embeded\python.exe -m pip install --force-reinstall diffusers torchao xformers

Install Missing Dependencies:
E:\Working\ComfyUI_windows_portable\python_embeded\python.exe -m pip install llama-cpp-python tensorboard onnxruntime-gpu

Fix OpenCV:
E:\Working\ComfyUI_windows_portable\python_embeded\python.exe -m pip uninstall opencv-python opencv-contrib-python -y
E:\Working\ComfyUI_windows_portable\python_embeded\python.exe -m pip install opencv-contrib-python

Final Advice: Python 3.13.9 is very new for the AI ecosystem. Many compiled extensions (like those in xFormers and TorchAO) are not yet stable on this version. If these errors persist, consider using a ComfyUI build with Python 3.11 for maximum compatibility.

---

The older version of Comfyui, Python, and its packages are more stable; the latest version has many problems, requiring you to solve them one by one using artificial intelligence. Currently, you are experiencing many issues besides those with SeedVR2.

[lost-in-emotions]

Thank you!

[naxci1]

I'm currently working on the GUI interface for SeedVR 2.5, designed for easier operation. It's almost finished, and I'm running tests. I'll share the results when it's complete.

[naxci1]

#570 (comment)

[Winnougan]

I found out that the problem was having Sageattention 3 and Flashattention 2 installed. By uninstalling those two it worked again!

[JanBluePix]

On Linux, with a fresh ComfyUI installation, the ComfyUI-SeedVR2_VideoUpscaler nodes only work up to version 2.5.18. Newer versions do not work. The ComfyUI Manager only offers versions up to 2.5.22 for installation. It makes no difference whether I clone the node or install it using the ComfyUI Manager.

On an older ComfyUI installation, I can install and get everything working up to the latest version, 2.5.24.

pytorch version: 2.11.0+cu130
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 3060 : cudaMallocAsync
Using async weight offloading with 2 streams
Enabled pinned memory 57790.0
Using pytorch attention
aimdo: src/control.c:68:INFO:comfy-aimdo inited for GPU: NVIDIA GeForce RTX 3060 (VRAM: 11906 MB)
DynamicVRAM support detected and enabled
Python version: 3.11.2 (main, Apr 28 2025, 14:11:48) [GCC 12.2.0]
ComfyUI version: 0.19.3
comfy-aimdo version: 0.2.12
comfy-kitchen version: 0.2.8
ComfyUI frontend version: 1.42.11
[Prompt Server] web root: /home/jan/ComfyUI/venv/lib/python3.11/site-packages/comfyui_frontend_package/static
Asset seeder disabled

Loading: ComfyUI-Manager (V3.39.2)

[ComfyUI-Manager] network_mode: public
[ComfyUI-Manager] ComfyUI per-queue preview override detected (PR #11261). Manager's preview method feature is disabled. Use ComfyUI's --preview-method CLI option or 'Settings > Execution > Live preview method'.

ComfyUI Revision: 5047 [30860264] *DETACHED | Released on '2026-04-17'

⚠ SeedVR2 optimizations check: SageAttention ❌ | Flash Attention ❌ | Triton ✅💡 Optional: pip install sageattention flash-attn
🔧 Conv3d workaround active: PyTorch 2.11.0, cuDNN 91900 (fixing VAE 3x memory bug)
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
📊 Initial CUDA memory: 10.62GB free / 11.63GB total
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
Traceback (most recent call last):
File "/home/jan/ComfyUI/venv/lib/python3.11/site-packages/diffusers/utils/import_utils.py", line 1010, in _get_module
return importlib.import_module("." + module_name, self.name)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3.11/importlib/init.py", line 126, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "", line 1206, in _gcd_import
File "", line 1178, in _find_and_load
File "", line 1149, in _find_and_load_unlocked
File "", line 690, in _load_unlocked
File "", line 940, in exec_module
File "", line 241, in _call_with_frames_removed
File "/home/jan/ComfyUI/venv/lib/python3.11/site-packages/diffusers/loaders/single_file_model.py", line 28, in
from .single_file_utils import (
File "/home/jan/ComfyUI/venv/lib/python3.11/site-packages/diffusers/loaders/single_file_utils.py", line 53, in
from transformers import AutoImageProcessor
File "", line 1231, in _handle_fromlist
File "/home/jan/ComfyUI/venv/lib/python3.11/site-packages/transformers/utils/import_utils.py", line 2207, in getattr
module = self._get_module(self._class_to_module[name])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/jan/ComfyUI/venv/lib/python3.11/site-packages/transformers/utils/import_utils.py", line 2441, in _get_module
raise e
File "/home/jan/ComfyUI/venv/lib/python3.11/site-packages/transformers/utils/import_utils.py", line 2439, in _get_module
return importlib.import_module("." + module_name, self.name)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3.11/importlib/init.py", line 126, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/jan/ComfyUI/venv/lib/python3.11/site-packages/transformers/models/auto/image_processing_auto.py", line 24, in
from ...image_processing_utils import ImageProcessingMixin
File "/home/jan/ComfyUI/venv/lib/python3.11/site-packages/transformers/image_processing_utils.py", line 34, in
from .processing_utils import ImagesKwargs, Unpack
File "/home/jan/ComfyUI/venv/lib/python3.11/site-packages/transformers/processing_utils.py", line 62, in
from .utils.type_validators import (
File "/home/jan/ComfyUI/venv/lib/python3.11/site-packages/transformers/utils/type_validators.py", line 19, in
from ..activations import ACT2FN
File "/home/jan/ComfyUI/venv/lib/python3.11/site-packages/transformers/activations.py", line 22, in
from .integrations.hub_kernels import use_kernel_forward_from_hub
File "/home/jan/ComfyUI/venv/lib/python3.11/site-packages/transformers/integrations/hub_kernels.py", line 25, in
from .flash_attention import flash_attention_forward
File "/home/jan/ComfyUI/venv/lib/python3.11/site-packages/transformers/integrations/flash_attention.py", line 9, in
use_top_left_mask = flash_attn_supports_top_left_mask()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/jan/ComfyUI/venv/lib/python3.11/site-packages/transformers/modeling_flash_attention_utils.py", line 42, in flash_attn_supports_top_left_mask
if is_flash_attn_2_available() or is_flash_attn_3_available() or is_flash_attn_4_available():
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/jan/ComfyUI/venv/lib/python3.11/site-packages/transformers/utils/import_utils.py", line 951, in is_flash_attn_2_available
pkg.replace("", "-") for pkg in PACKAGE_DISTRIBUTION_MAPPING["flash_attn"]
~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^
KeyError: 'flash_attn'

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "/home/jan/ComfyUI/nodes.py", line 2227, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 940, in exec_module
File "", line 241, in _call_with_frames_removed
File "/home/jan/ComfyUI/custom_nodes/seedvr2_videoupscaler/init.py", line 7, in
from .src.interfaces import comfy_entrypoint, SeedVR2Extension
File "/home/jan/ComfyUI/custom_nodes/seedvr2_videoupscaler/src/interfaces/init.py", line 8, in
from .video_upscaler import SeedVR2VideoUpscaler
File "/home/jan/ComfyUI/custom_nodes/seedvr2_videoupscaler/src/interfaces/video_upscaler.py", line 10, in
from ..utils.downloads import download_weight
File "/home/jan/ComfyUI/custom_nodes/seedvr2_videoupscaler/src/utils/downloads.py", line 14, in
from .model_registry import MODEL_REGISTRY, DEFAULT_VAE
File "/home/jan/ComfyUI/custom_nodes/seedvr2_videoupscaler/src/utils/model_registry.py", line 14, in
from ..models.video_vae_v3.modules.attn_video_vae import VideoAutoencoderKLWrapper
File "/home/jan/ComfyUI/custom_nodes/seedvr2_videoupscaler/src/models/video_vae_v3/modules/attn_video_vae.py", line 20, in
from diffusers.models.autoencoders.vae import DecoderOutput, DiagonalGaussianDistribution
File "/home/jan/ComfyUI/venv/lib/python3.11/site-packages/diffusers/models/autoencoders/init.py", line 1, in
from .autoencoder_asym_kl import AsymmetricAutoencoderKL
File "/home/jan/ComfyUI/venv/lib/python3.11/site-packages/diffusers/models/autoencoders/autoencoder_asym_kl.py", line 21, in
from .vae import AutoencoderMixin, DecoderOutput, DiagonalGaussianDistribution, Encoder, MaskConditionDecoder
File "/home/jan/ComfyUI/venv/lib/python3.11/site-packages/diffusers/models/autoencoders/vae.py", line 24, in
from ..unets.unet_2d_blocks import (
File "/home/jan/ComfyUI/venv/lib/python3.11/site-packages/diffusers/models/unets/init.py", line 6, in
from .unet_2d import UNet2DModel
File "/home/jan/ComfyUI/venv/lib/python3.11/site-packages/diffusers/models/unets/unet_2d.py", line 23, in
from .unet_2d_blocks import UNetMidBlock2D, get_down_block, get_up_block
File "/home/jan/ComfyUI/venv/lib/python3.11/site-packages/diffusers/models/unets/unet_2d_blocks.py", line 36, in
from ..transformers.dual_transformer_2d import DualTransformer2DModel
File "/home/jan/ComfyUI/venv/lib/python3.11/site-packages/diffusers/models/transformers/init.py", line 5, in
from .auraflow_transformer_2d import AuraFlowTransformer2DModel
File "/home/jan/ComfyUI/venv/lib/python3.11/site-packages/diffusers/models/transformers/auraflow_transformer_2d.py", line 23, in
from ...loaders import FromOriginalModelMixin, PeftAdapterMixin
File "", line 1231, in _handle_fromlist
File "/home/jan/ComfyUI/venv/lib/python3.11/site-packages/diffusers/utils/import_utils.py", line 1000, in getattr
module = self._get_module(self._class_to_module[name])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/jan/ComfyUI/venv/lib/python3.11/site-packages/diffusers/utils/import_utils.py", line 1012, in _get_module
raise RuntimeError(
RuntimeError: Failed to import diffusers.loaders.single_file_model because of the following error (look up to see its traceback):
'flash_attn'

Cannot import /home/jan/ComfyUI/custom_nodes/seedvr2_videoupscaler module for custom nodes: Failed to import diffusers.loaders.single_file_model because of the following error (look up to see its traceback):
'flash_attn'

Import times for custom nodes:
0.0 seconds: /home/jan/ComfyUI/custom_nodes/websocket_image_save.py
0.1 seconds: /home/jan/ComfyUI/custom_nodes/comfyui-manager
0.3 seconds (IMPORT FAILED): /home/jan/ComfyUI/custom_nodes/seedvr2_videoupscaler