cuDNN error: CUDNN_STATUS_NOT_INITIALIZED

### Custom Node Testing

- [ ] I have tried disabling custom nodes and the issue persists (see [how to disable custom nodes](https://docs.comfy.org/troubleshooting/custom-node-issues#step-1%3A-test-with-all-custom-nodes-disabled) if you need help)

### Expected Behavior

To run LTX2 to generate Image to video

### Actual Behavior

I doesn't work, I'm stuck on that bug


### Steps to Reproduce

Just install comfyui (I did from 0 to be sure it was this problem because of this)

Execute LTX2 from:
https://github.com/Lightricks/LTX-2
https://github.com/Lightricks/ComfyUI-LTXVideo/tree/master/example_workflows -> run image to video full

### Debug Logs

```powershell
# ComfyUI Error Report
## Error Details
- **Node ID:** 5189:5245
- **Node Type:** LTXVImgToVideoInplace
- **Exception Type:** RuntimeError
- **Exception Message:** cuDNN error: CUDNN_STATUS_NOT_INITIALIZED

## Stack Trace

File "/teamspace/studios/this_studio/ComfyUI/execution.py", line 518, in execute
output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/teamspace/studios/this_studio/ComfyUI/execution.py", line 329, in get_output_data
return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/teamspace/studios/this_studio/ComfyUI/execution.py", line 303, in _async_map_node_over_list
await process_inputs(input_dict, i)

File "/teamspace/studios/this_studio/ComfyUI/execution.py", line 291, in process_inputs
result = f(**inputs)
^^^^^^^^^^^

File "/teamspace/studios/this_studio/ComfyUI/comfy_api/internal/__init__.py", line 149, in wrapped_func
return method(locked_class, **inputs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/teamspace/studios/this_studio/ComfyUI/comfy_api/latest/_io.py", line 1570, in EXECUTE_NORMALIZED
to_return = cls.execute(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/teamspace/studios/this_studio/ComfyUI/comfy_extras/nodes_lt.py", line 121, in execute
t = vae.encode(encode_pixels)
^^^^^^^^^^^^^^^^^^^^^^^^^

File "/teamspace/studios/this_studio/ComfyUI/comfy/sd.py", line 880, in encode
out = self.first_stage_model.encode(pixels_in).to(self.output_device).float()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/teamspace/studios/this_studio/ComfyUI/comfy/ldm/lightricks/vae/causal_video_autoencoder.py", line 1085, in encode
means, logvar = torch.chunk(self.encoder(x), 2, dim=1)
^^^^^^^^^^^^^^^

File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1786, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/teamspace/studios/this_studio/ComfyUI/comfy/ldm/lightricks/vae/causal_video_autoencoder.py", line 212, in forward
sample = self.conv_in(sample)
^^^^^^^^^^^^^^^^^^^^

File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1786, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/teamspace/studios/this_studio/ComfyUI/comfy/ldm/lightricks/vae/causal_conv3d.py", line 60, in forward
x = self.conv(x)
^^^^^^^^^^^^

File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1786, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/teamspace/studios/this_studio/ComfyUI/comfy/ops.py", line 226, in forward
return super().forward(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/conv.py", line 717, in forward
return self._conv_forward(input, self.weight, self.bias)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/teamspace/studios/this_studio/ComfyUI/comfy/ops.py", line 213, in _conv_forward
return super()._conv_forward(input, weight, bias, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/conv.py", line 712, in _conv_forward
return F.conv3d(
^^^^^^^^^

## System Information
- **ComfyUI Version:** 0.8.2
- **Arguments:** main.py --enable-manager
- **OS:** linux
- **Python Version:** 3.12.11 | packaged by Anaconda, Inc. | (main, Jun 5 2025, 13:09:17) [GCC 11.2.0]
- **Embedded Python:** false
- **PyTorch Version:** 2.9.1+cu128
## Devices

- **Name:** cuda:0 NVIDIA L40S : cudaMallocAsync
- **Type:** cuda
- **VRAM Total:** 47929425920
- **VRAM Free:** 47477882880
- **Torch VRAM Total:** 0
- **Torch VRAM Free:** 0

## Logs

2026-01-08T04:58:59.605792 - [START] Security scan2026-01-08T04:58:59.605812 -
2026-01-08T04:58:59.633382 - [ComfyUI-Manager] Using uv as Python module for pip operations.
2026-01-08T04:58:59.702636 - [DONE] Security scan2026-01-08T04:58:59.702648 -
2026-01-08T04:58:59.703819 - ** ComfyUI startup time:2026-01-08T04:58:59.703904 - 2026-01-08T04:58:59.703952 - 2026-01-08 04:58:59.7032026-01-08T04:58:59.703994 -
2026-01-08T04:58:59.704035 - ** Platform:2026-01-08T04:58:59.704076 - 2026-01-08T04:58:59.704109 - Linux2026-01-08T04:58:59.704146 -
2026-01-08T04:58:59.704190 - ** Python version:2026-01-08T04:58:59.704225 - 2026-01-08T04:58:59.704267 - 3.12.11 | packaged by Anaconda, Inc. | (main, Jun 5 2025, 13:09:17) [GCC 11.2.0]2026-01-08T04:58:59.704306 -
2026-01-08T04:58:59.704342 - ** Python executable:2026-01-08T04:58:59.704374 - 2026-01-08T04:58:59.704413 - /home/zeus/miniconda3/envs/cloudspace/bin/python2026-01-08T04:58:59.704446 -
2026-01-08T04:58:59.704483 - ** ComfyUI Path:2026-01-08T04:58:59.704518 - 2026-01-08T04:58:59.704556 - /teamspace/studios/this_studio/ComfyUI2026-01-08T04:58:59.704591 -
2026-01-08T04:58:59.704629 - ** ComfyUI Base Folder Path:2026-01-08T04:58:59.704663 - 2026-01-08T04:58:59.704697 - /teamspace/studios/this_studio/ComfyUI2026-01-08T04:58:59.704735 -
2026-01-08T04:58:59.704774 - ** User directory:2026-01-08T04:58:59.704816 - 2026-01-08T04:58:59.704850 - /teamspace/studios/this_studio/ComfyUI/user2026-01-08T04:58:59.704921 -
2026-01-08T04:58:59.704961 - ** ComfyUI-Manager config path:2026-01-08T04:58:59.704996 - 2026-01-08T04:58:59.705028 - /teamspace/studios/this_studio/ComfyUI/user/__manager/config.ini2026-01-08T04:58:59.705059 -
2026-01-08T04:58:59.705097 - ** Log path:2026-01-08T04:58:59.705138 - 2026-01-08T04:58:59.705176 - /teamspace/studios/this_studio/ComfyUI/user/comfyui.log2026-01-08T04:58:59.705220 -
2026-01-08T04:58:59.775970 - [PRE] ComfyUI-Manager
2026-01-08T04:59:00.987364 - Checkpoint files will always be loaded safely.
2026-01-08T04:59:01.124790 - Total VRAM 45709 MB, total RAM 127096 MB
2026-01-08T04:59:01.124951 - pytorch version: 2.9.1+cu128
2026-01-08T04:59:01.125278 - Set vram state to: NORMAL_VRAM
2026-01-08T04:59:01.125537 - Device: cuda:0 NVIDIA L40S : cudaMallocAsync
2026-01-08T04:59:01.125682 - Using async weight offloading with 2 streams
2026-01-08T04:59:01.125878 - Enabled pinned memory 120741.0
2026-01-08T04:59:02.109878 - WARNING: You need pytorch with cu130 or higher to use optimized CUDA operations.
2026-01-08T04:59:02.110071 - Found comfy_kitchen backend cuda: {'available': True, 'disabled': True, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'scaled_mm_nvfp4']}
2026-01-08T04:59:02.110219 - Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'scaled_mm_nvfp4']}
2026-01-08T04:59:02.110325 - Found comfy_kitchen backend triton: {'available': True, 'disabled': True, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8']}
2026-01-08T04:59:02.288452 - Using pytorch attention
2026-01-08T04:59:03.675680 - Python version: 3.12.11 | packaged by Anaconda, Inc. | (main, Jun 5 2025, 13:09:17) [GCC 11.2.0]
2026-01-08T04:59:03.675948 - ComfyUI version: 0.8.2
2026-01-08T04:59:03.679187 - ComfyUI frontend version: 1.35.9
2026-01-08T04:59:03.679922 - [Prompt Server] web root: /home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/comfyui_frontend_package/static
2026-01-08T04:59:03.680098 - [START] ComfyUI-Manager
2026-01-08T04:59:03.838283 - [ComfyUI-Manager] network_mode: public
2026-01-08T04:59:05.825552 - Total VRAM 45709 MB, total RAM 127096 MB
2026-01-08T04:59:05.825700 - pytorch version: 2.9.1+cu128
2026-01-08T04:59:05.825967 - Set vram state to: NORMAL_VRAM
2026-01-08T04:59:05.826105 - Device: cuda:0 NVIDIA L40S : cudaMallocAsync
2026-01-08T04:59:05.826238 - Using async weight offloading with 2 streams
2026-01-08T04:59:05.826396 - Enabled pinned memory 120741.0
2026-01-08T04:59:06.536903 - ### Loading: ComfyUI-Impact-Pack (V8.28.2)
2026-01-08T04:59:06.901976 - [Impact Pack] Wildcard total size (0.00 MB) is within cache limit (50.00 MB). Using full cache mode.
2026-01-08T04:59:06.903309 - [Impact Pack] Wildcards loading done.
2026-01-08T04:59:06.903966 -
Import times for custom nodes:
2026-01-08T04:59:06.904066 - 0.0 seconds: /teamspace/studios/this_studio/ComfyUI/custom_nodes/websocket_image_save.py
2026-01-08T04:59:06.904145 - 0.0 seconds: /teamspace/studios/this_studio/ComfyUI/custom_nodes/ComfyMath
2026-01-08T04:59:06.904234 - 0.2 seconds: /teamspace/studios/this_studio/ComfyUI/custom_nodes/ComfyUI-LTXVideo
2026-01-08T04:59:06.904316 - 0.4 seconds: /teamspace/studios/this_studio/ComfyUI/custom_nodes/comfyui-impact-pack
2026-01-08T04:59:06.904402 -
2026-01-08T04:59:07.148474 - Context impl SQLiteImpl.
2026-01-08T04:59:07.148628 - Will assume non-transactional DDL.
2026-01-08T04:59:07.149575 - No target revision found.
2026-01-08T04:59:07.179500 - Starting server

2026-01-08T04:59:07.179778 - To see the GUI go to: http://127.0.0.1:8188
2026-01-08T04:59:15.637504 - [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.
2026-01-08T04:59:15.639127 - [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.
2026-01-08T04:59:35.748768 - got prompt
2026-01-08T04:59:36.080214 - Failed to validate prompt for output 4958:
2026-01-08T04:59:36.080342 - * KSamplerSelect 5189:5099:
2026-01-08T04:59:36.080441 - - Value not in list: sampler_name: 'res_2s' not in (list of length 44)
2026-01-08T04:59:36.080547 - * KSamplerSelect 5189:5109:
2026-01-08T04:59:36.080645 - - Value not in list: sampler_name: 'res_2s' not in (list of length 44)
2026-01-08T04:59:36.080739 - Output will be ignored
2026-01-08T04:59:36.258125 - Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
2026-01-08T04:59:37.383456 - Loaded processor from /teamspace/studios/this_studio/ComfyUI/models/text_encoders - enhancement enabled
2026-01-08T04:59:37.384173 - `torch_dtype` is deprecated! Use `dtype` instead!
2026-01-08T04:59:37.750919 -
Loading checkpoint shards: 100%|████████████████████████████████████████████████████████████| 5/5 [00:00<00:00, 20.43it/s]2026-01-08T04:59:37.751219 -
Loading checkpoint shards: 100%|████████████████████████████████████████████████████████████| 5/5 [00:00<00:00, 19.70it/s]2026-01-08T04:59:37.751278 -
2026-01-08T04:59:44.836663 - CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
2026-01-08T04:59:44.837457 - Requested to load _LTXVGemmaTextEncoderModel
2026-01-08T05:00:05.510529 - loaded completely; 44059.24 MB usable, 27885.96 MB loaded, full load: True
2026-01-08T05:00:05.754104 - Token indices sequence length is longer than the specified maximum sequence length for this model (1088 > 1024). Running this sequence through the model will result in indexing errors
2026-01-08T05:00:05.761176 - Setting `pad_token_id` to `eos_token_id`:1 for open-end generation.
2026-01-08T05:00:05.835801 - !!! Exception during processing !!! cuDNN error: CUDNN_STATUS_NOT_INITIALIZED
2026-01-08T05:00:05.840080 - Traceback (most recent call last):
File "/teamspace/studios/this_studio/ComfyUI/execution.py", line 518, in execute
output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/execution.py", line 329, in get_output_data
return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/execution.py", line 303, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "/teamspace/studios/this_studio/ComfyUI/execution.py", line 291, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/custom_nodes/ComfyUI-LTXVideo/gemma_encoder.py", line 697, in enhance
enhanced_prompt = encoder.enhance_i2v(
^^^^^^^^^^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/custom_nodes/ComfyUI-LTXVideo/gemma_encoder.py", line 480, in enhance_i2v
return self._enhance(
^^^^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/custom_nodes/ComfyUI-LTXVideo/gemma_encoder.py", line 434, in _enhance
outputs = self.model.generate(
^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 120, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/transformers/generation/utils.py", line 2564, in generate
result = decoding_method(
^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/transformers/generation/utils.py", line 2784, in _sample
outputs = self(**model_inputs, return_dict=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1786, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/transformers/models/gemma3/modeling_gemma3.py", line 1100, in forward
outputs = self.model(
^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1786, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/transformers/utils/generic.py", line 918, in wrapper
output = func(self, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/transformers/models/gemma3/modeling_gemma3.py", line 908, in forward
image_features = self.get_image_features(pixel_values)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/transformers/models/gemma3/modeling_gemma3.py", line 806, in get_image_features
vision_outputs = self.vision_tower(pixel_values=pixel_values).last_hidden_state
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1786, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/transformers/utils/generic.py", line 1072, in wrapper
outputs = func(self, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/transformers/models/siglip/modeling_siglip.py", line 789, in forward
return self.vision_model(
^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1786, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/transformers/models/siglip/modeling_siglip.py", line 698, in forward
hidden_states = self.embeddings(pixel_values, interpolate_pos_encoding=interpolate_pos_encoding)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1786, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/transformers/models/siglip/modeling_siglip.py", line 278, in forward
patch_embeds = self.patch_embedding(pixel_values.to(dtype=target_dtype)) # shape = [*, width, grid, grid]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1786, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/conv.py", line 548, in forward
return self._conv_forward(input, self.weight, self.bias)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/conv.py", line 543, in _conv_forward
return F.conv2d(
^^^^^^^^^
RuntimeError: cuDNN error: CUDNN_STATUS_NOT_INITIALIZED

2026-01-08T05:00:05.842020 - Prompt executed in 29.76 seconds
2026-01-08T05:00:20.796105 - FETCH ComfyRegistry Data [DONE]
2026-01-08T05:00:20.954491 - [ComfyUI-Manager] default cache updated: https://api.comfy.org/nodes
2026-01-08T05:00:20.965490 - FETCH DATA from: /teamspace/studios/this_studio/ComfyUI/user/__manager/cache/1514988643_custom-node-list.json2026-01-08T05:00:20.965538 - 2026-01-08T05:00:20.976017 - [DONE]2026-01-08T05:00:20.976078 -
2026-01-08T05:00:20.993774 - [ComfyUI-Manager] All startup tasks have been completed.
2026-01-08T05:00:47.677824 - got prompt
2026-01-08T05:00:47.800796 - Failed to validate prompt for output 4958:
2026-01-08T05:00:47.800930 - * KSamplerSelect 5189:5099:
2026-01-08T05:00:47.801038 - - Value not in list: sampler_name: 'res_2s' not in (list of length 44)
2026-01-08T05:00:47.801138 - * KSamplerSelect 5189:5109:
2026-01-08T05:00:47.801224 - - Value not in list: sampler_name: 'res_2s' not in (list of length 44)
2026-01-08T05:00:47.801312 - Output will be ignored
2026-01-08T05:00:47.885788 - Setting `pad_token_id` to `eos_token_id`:1 for open-end generation.
2026-01-08T05:00:47.888368 - !!! Exception during processing !!! cuDNN error: CUDNN_STATUS_NOT_INITIALIZED
2026-01-08T05:00:47.890144 - Traceback (most recent call last):
File "/teamspace/studios/this_studio/ComfyUI/execution.py", line 518, in execute
output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/execution.py", line 329, in get_output_data
return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/execution.py", line 303, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "/teamspace/studios/this_studio/ComfyUI/execution.py", line 291, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/custom_nodes/ComfyUI-LTXVideo/gemma_encoder.py", line 697, in enhance
enhanced_prompt = encoder.enhance_i2v(
^^^^^^^^^^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/custom_nodes/ComfyUI-LTXVideo/gemma_encoder.py", line 480, in enhance_i2v
return self._enhance(
^^^^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/custom_nodes/ComfyUI-LTXVideo/gemma_encoder.py", line 434, in _enhance
outputs = self.model.generate(
^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 120, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/transformers/generation/utils.py", line 2564, in generate
result = decoding_method(
^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/transformers/generation/utils.py", line 2784, in _sample
outputs = self(**model_inputs, return_dict=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1786, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/transformers/models/gemma3/modeling_gemma3.py", line 1100, in forward
outputs = self.model(
^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1786, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/transformers/utils/generic.py", line 918, in wrapper
output = func(self, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/transformers/models/gemma3/modeling_gemma3.py", line 908, in forward
image_features = self.get_image_features(pixel_values)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/transformers/models/gemma3/modeling_gemma3.py", line 806, in get_image_features
vision_outputs = self.vision_tower(pixel_values=pixel_values).last_hidden_state
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1786, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/transformers/utils/generic.py", line 1072, in wrapper
outputs = func(self, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/transformers/models/siglip/modeling_siglip.py", line 789, in forward
return self.vision_model(
^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1786, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/transformers/models/siglip/modeling_siglip.py", line 698, in forward
hidden_states = self.embeddings(pixel_values, interpolate_pos_encoding=interpolate_pos_encoding)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1786, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/transformers/models/siglip/modeling_siglip.py", line 278, in forward
patch_embeds = self.patch_embedding(pixel_values.to(dtype=target_dtype)) # shape = [*, width, grid, grid]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1786, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/conv.py", line 548, in forward
return self._conv_forward(input, self.weight, self.bias)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/conv.py", line 543, in _conv_forward
return F.conv2d(
^^^^^^^^^
RuntimeError: cuDNN error: CUDNN_STATUS_NOT_INITIALIZED

2026-01-08T05:00:47.892323 - Prompt executed in 0.09 seconds
2026-01-08T05:01:18.741726 - got prompt
2026-01-08T05:01:18.857918 - Failed to validate prompt for output 4958:
2026-01-08T05:01:18.858042 - * KSamplerSelect 5189:5099:
2026-01-08T05:01:18.858142 - - Value not in list: sampler_name: 'res_2s' not in (list of length 44)
2026-01-08T05:01:18.858232 - * KSamplerSelect 5189:5109:
2026-01-08T05:01:18.858316 - - Value not in list: sampler_name: 'res_2s' not in (list of length 44)
2026-01-08T05:01:18.858408 - Output will be ignored
2026-01-08T05:01:18.858511 - invalid prompt: {'type': 'prompt_outputs_failed_validation', 'message': 'Prompt outputs failed validation', 'details': '', 'extra_info': {}}
2026-01-08T05:01:35.532608 - got prompt
2026-01-08T05:01:36.213471 - model weight dtype torch.bfloat16, manual cast: None
2026-01-08T05:01:36.214109 - model_type FLUX
2026-01-08T05:02:29.044104 - unet unexpected: ['audio_embeddings_connector.learnable_registers', 'audio_embeddings_connector.transformer_1d_blocks.0.attn1.k_norm.weight', 'audio_embeddings_connector.transformer_1d_blocks.0.attn1.q_norm.weight', 'audio_embeddings_connector.transformer_1d_blocks.0.attn1.to_k.bias', 'audio_embeddings_connector.transformer_1d_blocks.0.attn1.to_k.weight', 'audio_embeddings_connector.transformer_1d_blocks.0.attn1.to_out.0.bias', 'audio_embeddings_connector.transformer_1d_blocks.0.attn1.to_out.0.weight', 'audio_embeddings_connector.transformer_1d_blocks.0.attn1.to_q.bias', 'audio_embeddings_connector.transformer_1d_blocks.0.attn1.to_q.weight', 'audio_embeddings_connector.transformer_1d_blocks.0.attn1.to_v.bias', 'audio_embeddings_connector.transformer_1d_blocks.0.attn1.to_v.weight', 'audio_embeddings_connector.transformer_1d_blocks.0.ff.net.0.proj.bias', 'audio_embeddings_connector.transformer_1d_blocks.0.ff.net.0.proj.weight', 'audio_embeddings_connector.transformer_1d_blocks.0.ff.net.2.bias', 'audio_embeddings_connector.transformer_1d_blocks.0.ff.net.2.weight', 'audio_embeddings_connector.transformer_1d_blocks.1.attn1.k_norm.weight', 'audio_embeddings_connector.transformer_1d_blocks.1.attn1.q_norm.weight', 'audio_embeddings_connector.transformer_1d_blocks.1.attn1.to_k.bias', 'audio_embeddings_connector.transformer_1d_blocks.1.attn1.to_k.weight', 'audio_embeddings_connector.transformer_1d_blocks.1.attn1.to_out.0.bias', 'audio_embeddings_connector.transformer_1d_blocks.1.attn1.to_out.0.weight', 'audio_embeddings_connector.transformer_1d_blocks.1.attn1.to_q.bias', 'audio_embeddings_connector.transformer_1d_blocks.1.attn1.to_q.weight', 'audio_embeddings_connector.transformer_1d_blocks.1.attn1.to_v.bias', 'audio_embeddings_connector.transformer_1d_blocks.1.attn1.to_v.weight', 'audio_embeddings_connector.transformer_1d_blocks.1.ff.net.0.proj.bias', 'audio_embeddings_connector.transformer_1d_blocks.1.ff.net.0.proj.weight', 'audio_embeddings_connector.transformer_1d_blocks.1.ff.net.2.bias', 'audio_embeddings_connector.transformer_1d_blocks.1.ff.net.2.weight', 'video_embeddings_connector.learnable_registers', 'video_embeddings_connector.transformer_1d_blocks.0.attn1.k_norm.weight', 'video_embeddings_connector.transformer_1d_blocks.0.attn1.q_norm.weight', 'video_embeddings_connector.transformer_1d_blocks.0.attn1.to_k.bias', 'video_embeddings_connector.transformer_1d_blocks.0.attn1.to_k.weight', 'video_embeddings_connector.transformer_1d_blocks.0.attn1.to_out.0.bias', 'video_embeddings_connector.transformer_1d_blocks.0.attn1.to_out.0.weight', 'video_embeddings_connector.transformer_1d_blocks.0.attn1.to_q.bias', 'video_embeddings_connector.transformer_1d_blocks.0.attn1.to_q.weight', 'video_embeddings_connector.transformer_1d_blocks.0.attn1.to_v.bias', 'video_embeddings_connector.transformer_1d_blocks.0.attn1.to_v.weight', 'video_embeddings_connector.transformer_1d_blocks.0.ff.net.0.proj.bias', 'video_embeddings_connector.transformer_1d_blocks.0.ff.net.0.proj.weight', 'video_embeddings_connector.transformer_1d_blocks.0.ff.net.2.bias', 'video_embeddings_connector.transformer_1d_blocks.0.ff.net.2.weight', 'video_embeddings_connector.transformer_1d_blocks.1.attn1.k_norm.weight', 'video_embeddings_connector.transformer_1d_blocks.1.attn1.q_norm.weight', 'video_embeddings_connector.transformer_1d_blocks.1.attn1.to_k.bias', 'video_embeddings_connector.transformer_1d_blocks.1.attn1.to_k.weight', 'video_embeddings_connector.transformer_1d_blocks.1.attn1.to_out.0.bias', 'video_embeddings_connector.transformer_1d_blocks.1.attn1.to_out.0.weight', 'video_embeddings_connector.transformer_1d_blocks.1.attn1.to_q.bias', 'video_embeddings_connector.transformer_1d_blocks.1.attn1.to_q.weight', 'video_embeddings_connector.transformer_1d_blocks.1.attn1.to_v.bias', 'video_embeddings_connector.transformer_1d_blocks.1.attn1.to_v.weight', 'video_embeddings_connector.transformer_1d_blocks.1.ff.net.0.proj.bias', 'video_embeddings_connector.transformer_1d_blocks.1.ff.net.0.proj.weight', 'video_embeddings_connector.transformer_1d_blocks.1.ff.net.2.bias', 'video_embeddings_connector.transformer_1d_blocks.1.ff.net.2.weight']
2026-01-08T05:02:39.693458 - VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
2026-01-08T05:02:39.695758 - no CLIP/text encoder weights in checkpoint, the text encoder model will not be loaded.
2026-01-08T05:02:41.973068 - Requested to load VideoVAE
2026-01-08T05:02:42.313306 - loaded completely; 17940.26 MB usable, 2331.69 MB loaded, full load: True
2026-01-08T05:02:42.369248 - !!! Exception during processing !!! cuDNN error: CUDNN_STATUS_NOT_INITIALIZED
2026-01-08T05:02:42.373529 - Traceback (most recent call last):
File "/teamspace/studios/this_studio/ComfyUI/execution.py", line 518, in execute
output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/execution.py", line 329, in get_output_data
return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/execution.py", line 303, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "/teamspace/studios/this_studio/ComfyUI/execution.py", line 291, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/comfy_api/internal/__init__.py", line 149, in wrapped_func
return method(locked_class, **inputs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/comfy_api/latest/_io.py", line 1570, in EXECUTE_NORMALIZED
to_return = cls.execute(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/comfy_extras/nodes_lt.py", line 121, in execute
t = vae.encode(encode_pixels)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/comfy/sd.py", line 880, in encode
out = self.first_stage_model.encode(pixels_in).to(self.output_device).float()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/comfy/ldm/lightricks/vae/causal_video_autoencoder.py", line 1085, in encode
means, logvar = torch.chunk(self.encoder(x), 2, dim=1)
^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1786, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/comfy/ldm/lightricks/vae/causal_video_autoencoder.py", line 212, in forward
sample = self.conv_in(sample)
^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1786, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/comfy/ldm/lightricks/vae/causal_conv3d.py", line 60, in forward
x = self.conv(x)
^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1786, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/comfy/ops.py", line 226, in forward
return super().forward(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/conv.py", line 717, in forward
return self._conv_forward(input, self.weight, self.bias)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/comfy/ops.py", line 213, in _conv_forward
return super()._conv_forward(input, weight, bias, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/conv.py", line 712, in _conv_forward
return F.conv3d(
^^^^^^^^^
RuntimeError: cuDNN error: CUDNN_STATUS_NOT_INITIALIZED

2026-01-08T05:02:42.376214 - Prompt executed in 66.72 seconds
2026-01-08T05:02:58.926547 - got prompt
2026-01-08T05:02:59.037769 - !!! Exception during processing !!! cuDNN error: CUDNN_STATUS_NOT_INITIALIZED
2026-01-08T05:02:59.039494 - Traceback (most recent call last):
File "/teamspace/studios/this_studio/ComfyUI/execution.py", line 518, in execute
output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/execution.py", line 329, in get_output_data
return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/execution.py", line 303, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "/teamspace/studios/this_studio/ComfyUI/execution.py", line 291, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/comfy_api/internal/__init__.py", line 149, in wrapped_func
return method(locked_class, **inputs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/comfy_api/latest/_io.py", line 1570, in EXECUTE_NORMALIZED
to_return = cls.execute(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/comfy_extras/nodes_lt.py", line 121, in execute
t = vae.encode(encode_pixels)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/comfy/sd.py", line 880, in encode
out = self.first_stage_model.encode(pixels_in).to(self.output_device).float()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/comfy/ldm/lightricks/vae/causal_video_autoencoder.py", line 1085, in encode
means, logvar = torch.chunk(self.encoder(x), 2, dim=1)
^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1786, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/comfy/ldm/lightricks/vae/causal_video_autoencoder.py", line 212, in forward
sample = self.conv_in(sample)
^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1786, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/comfy/ldm/lightricks/vae/causal_conv3d.py", line 60, in forward
x = self.conv(x)
^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1786, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/comfy/ops.py", line 226, in forward
return super().forward(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/conv.py", line 717, in forward
return self._conv_forward(input, self.weight, self.bias)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/teamspace/studios/this_studio/ComfyUI/comfy/ops.py", line 213, in _conv_forward
return super()._conv_forward(input, weight, bias, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/nn/modules/conv.py", line 712, in _conv_forward
return F.conv3d(
^^^^^^^^^
RuntimeError: cuDNN error: CUDNN_STATUS_NOT_INITIALIZED

2026-01-08T05:02:59.041087 - Prompt executed in 0.04 seconds

## Attached Workflow
Please make sure that workflow does not contain any sensitive information such as API keys or passwords.

Workflow too large. Please manually upload the workflow from local file system.

## Additional Context
(Please add any additional context or steps to reproduce the error here)
```

### Other

_No response_