Comfy-Org / Comfy-Org/ComfyUI

WanMoeKSampler

Open
#10,598 0 comments 0 reactions 0 assignees View on GitHub
Potential Bug
Dominant language
Python
Stars
133k
Forks
15.7k
Avg merge
1d 7h
Merged PRs (30d)
158

Description

### 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

CUDA error: no kernel image is available for execution on the device
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.

### Actual Behavior

CUDA error: no kernel image is available for execution on the device
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.

### Steps to Reproduce

CUDA error: no kernel image is available for execution on the device
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.

### Debug Logs

```powershell
# ComfyUI Error Report
## Error Details
- **Node ID:** 542
- **Node Type:** WanMoeKSampler
- **Exception Type:** torch.AcceleratorError
- **Exception Message:** CUDA error: no kernel image is available for execution on the device
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.

## Stack Trace

File "/root/autodl-tmp/ComfyUI/execution.py", line 498, 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, hidden_inputs=hidden_inputs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/execution.py", line 316, 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, hidden_inputs=hidden_inputs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/execution.py", line 290, in _async_map_node_over_list
await process_inputs(input_dict, i)

File "/root/autodl-tmp/ComfyUI/execution.py", line 278, in process_inputs
result = f(**inputs)
^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI-WanMoeKSampler/nodes.py", line 116, in sample
return wan_ksampler(model_high_noise, model_low_noise, seed, steps, (cfg_high_noise, cfg_low_noise), sampler_name, scheduler, positive, negative, latent_image,boundary=boundary, denoise=denoise)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI-WanMoeKSampler/nodes.py", line 52, in wan_ksampler
latent_image = comfy.sample.sample(model_high_noise, noise, steps, cfgs[0], sampler_name, scheduler, positive, negative, latent_image,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/comfy/sample.py", line 60, in sample
samples = sampler.sample(noise, positive, negative, cfg=cfg, latent_image=latent_image, start_step=start_step, last_step=last_step, force_full_denoise=force_full_denoise, denoise_mask=noise_mask, sigmas=sigmas, callback=callback, disable_pbar=disable_pbar, seed=seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI_smZNodes/smZNodes.py", line 131, in KSampler_sample
return orig_fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/comfy/samplers.py", line 1163, in sample
return sample(self.model, noise, positive, negative, cfg, self.device, sampler, sigmas, self.model_options, latent_image=latent_image, denoise_mask=denoise_mask, callback=callback, disable_pbar=disable_pbar, seed=seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI_smZNodes/smZNodes.py", line 149, in sample
return orig_fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/comfy/samplers.py", line 1053, in sample
return cfg_guider.sample(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/comfy/samplers.py", line 1035, in sample
output = executor.execute(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed, latent_shapes=latent_shapes)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/comfy/patcher_extension.py", line 112, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/comfy/samplers.py", line 997, in outer_sample
output = self.inner_sample(noise, latent_image, device, sampler, sigmas, denoise_mask, callback, disable_pbar, seed, latent_shapes=latent_shapes)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/comfy/samplers.py", line 980, in inner_sample
samples = executor.execute(self, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/comfy/patcher_extension.py", line 112, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI_smZNodes/smZNodes.py", line 114, in KSAMPLER_sample
return orig_fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/comfy/samplers.py", line 752, in sample
samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **self.extra_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/miniconda3/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 120, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/comfy/k_diffusion/sampling.py", line 212, in sample_euler_ancestral
return sample_euler_ancestral_RF(model, x, sigmas, extra_args, callback, disable, eta, s_noise, noise_sampler)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/miniconda3/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 120, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/comfy/k_diffusion/sampling.py", line 241, in sample_euler_ancestral_RF
denoised = model(x, sigmas[i] * s_in, **extra_args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/comfy/samplers.py", line 401, in __call__
out = self.inner_model(x, sigma, model_options=model_options, seed=seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/comfy/samplers.py", line 953, in __call__
return self.outer_predict_noise(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/comfy/samplers.py", line 960, in outer_predict_noise
).execute(x, timestep, model_options, seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/comfy/patcher_extension.py", line 112, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/comfy/samplers.py", line 963, in predict_noise
return sampling_function(self.inner_model, x, timestep, self.conds.get("negative", None), self.conds.get("positive", None), self.cfg, model_options=model_options, seed=seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI_smZNodes/smZNodes.py", line 189, in sampling_function
out = orig_fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/comfy/samplers.py", line 381, in sampling_function
out = calc_cond_batch(model, conds, x, timestep, model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/comfy/samplers.py", line 206, in calc_cond_batch
return _calc_cond_batch_outer(model, conds, x_in, timestep, model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/comfy/samplers.py", line 214, in _calc_cond_batch_outer
return executor.execute(model, conds, x_in, timestep, model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/comfy/patcher_extension.py", line 112, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/comfy/samplers.py", line 326, in _calc_cond_batch
output = model.apply_model(input_x, timestep_, **c).chunk(batch_chunks)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/comfy/model_base.py", line 161, in apply_model
return comfy.patcher_extension.WrapperExecutor.new_class_executor(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/comfy/patcher_extension.py", line 112, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/comfy/model_base.py", line 203, in _apply_model
model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/miniconda3/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1773, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/miniconda3/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1784, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/comfy/ldm/wan/model.py", line 614, in forward
return comfy.patcher_extension.WrapperExecutor.new_class_executor(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/comfy/patcher_extension.py", line 112, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/comfy/ldm/wan/model.py", line 634, in _forward
return self.forward_orig(x, timestep, context, clip_fea=clip_fea, freqs=freqs, transformer_options=transformer_options, **kwargs)[:, :, :t, :h, :w]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/comfy/ldm/wan/model.py", line 579, in forward_orig
x = block(x, e=e0, freqs=freqs, context=context, context_img_len=context_img_len, transformer_options=transformer_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/miniconda3/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1773, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/miniconda3/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1784, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/comfy/ldm/wan/model.py", line 235, in forward
y = self.self_attn(
^^^^^^^^^^^^^^^

File "/root/miniconda3/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1773, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/miniconda3/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1784, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/comfy/ldm/wan/model.py", line 81, in forward
x = optimized_attention(
^^^^^^^^^^^^^^^^^^^^

File "/root/miniconda3/lib/python3.12/site-packages/torch/_dynamo/eval_frame.py", line 929, in _fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI-KJNodes/nodes/model_optimization_nodes.py", line 153, in attention_sage
out = sage_func(q, k, v, attn_mask=mask, is_causal=False, tensor_layout=tensor_layout)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI-KJNodes/nodes/model_optimization_nodes.py", line 99, in func
return sageattn(q, k, v, is_causal=is_causal, attn_mask=attn_mask, tensor_layout=tensor_layout)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/miniconda3/lib/python3.12/site-packages/sageattention-2.2.0-py3.12-linux-x86_64.egg/sageattention/core.py", line 146, in sageattn
return sageattn_qk_int8_pv_fp8_cuda(q, k, v, tensor_layout=tensor_layout, is_causal=is_causal, sm_scale=sm_scale, return_lse=return_lse, pv_accum_dtype="fp32+fp16")
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/miniconda3/lib/python3.12/site-packages/torch/_dynamo/eval_frame.py", line 929, in _fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^

File "/root/miniconda3/lib/python3.12/site-packages/sageattention-2.2.0-py3.12-linux-x86_64.egg/sageattention/core.py", line 804, in sageattn_qk_int8_pv_fp8_cuda
v_fp8, v_scale, vm = per_channel_fp8(v, tensor_layout=tensor_layout, scale_max=quant_v_scale_max, smooth_v=smooth_v)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/root/miniconda3/lib/python3.12/site-packages/sageattention-2.2.0-py3.12-linux-x86_64.egg/sageattention/quant.py", line 283, in per_channel_fp8
v_fp8 = torch.empty(v_transposed_permutted.shape, dtype=torch.float8_e4m3fn, device=v.device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

## System Information
- **ComfyUI Version:** 0.3.67
- **Arguments:** main.py --port 6006 --listen 0.0.0.0
- **OS:** posix
- **Python Version:** 3.12.3 | packaged by Anaconda, Inc. | (main, May 6 2024, 19:46:43) [GCC 11.2.0]
- **Embedded Python:** false
- **PyTorch Version:** 2.8.0+cu128
## Devices

- **Name:** cuda:0 NVIDIA vGPU-48GB : cudaMallocAsync
- **Type:** cuda
- **VRAM Total:** 50875924480
- **VRAM Free:** 48582588398
- **Torch VRAM Total:** 1912602624
- **Torch VRAM Free:** 148142062

## Logs

2025-11-02T09:47:41.891627 - ======================================== ComfyUI-nunchaku Initialization ========================================
2025-11-02T09:47:41.892303 - Nunchaku version: 1.0.0
2025-11-02T09:47:41.892616 - ComfyUI-nunchaku version: 1.0.1
2025-11-02T09:47:42.543892 - 'nunchaku_versions.json' not found. Node will start in minimal mode.2025-11-02T09:47:42.543946 -
2025-11-02T09:47:42.544056 - =================================================================================================================
2025-11-02T09:47:42.555539 - ------------------------------------------2025-11-02T09:47:42.555581 -
2025-11-02T09:47:42.555604 - Comfyroll Studio v1.76 :  175 Nodes Loaded2025-11-02T09:47:42.555621 -
2025-11-02T09:47:42.555637 - ------------------------------------------2025-11-02T09:47:42.555650 -
2025-11-02T09:47:42.555665 - ** For changes, please see patch notes at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/blob/main/Patch_Notes.md2025-11-02T09:47:42.555680 -
2025-11-02T09:47:42.555695 - ** For help, please see the wiki at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/wiki2025-11-02T09:47:42.555708 -
2025-11-02T09:47:42.555723 - ------------------------------------------2025-11-02T09:47:42.555736 -
2025-11-02T09:47:42.561676 - Web extensions folder found at /root/autodl-tmp/ComfyUI/web/extensions/ComfyLiterals2025-11-02T09:47:42.561715 -
2025-11-02T09:47:42.575755 - Traceback (most recent call last):
File "/root/autodl-tmp/ComfyUI/nodes.py", line 2131, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 991, in exec_module
File "", line 1128, in get_code
File "", line 1186, in get_data
FileNotFoundError: [Errno 2] No such file or directory: '/root/autodl-tmp/ComfyUI/custom_nodes/.ipynb_checkpoints/__init__.py'

2025-11-02T09:47:42.575960 - Cannot import /root/autodl-tmp/ComfyUI/custom_nodes/.ipynb_checkpoints module for custom nodes: [Errno 2] No such file or directory: '/root/autodl-tmp/ComfyUI/custom_nodes/.ipynb_checkpoints/__init__.py'
2025-11-02T09:47:42.578670 - # 😺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/52025-11-02T09:47:42.578716 -
2025-11-02T09:47:42.656227 -
Import times for custom nodes:
2025-11-02T09:47:42.656373 - 0.0 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/websocket_image_save.py
2025-11-02T09:47:42.656414 - 0.0 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI_ADV_CLIP_emb
2025-11-02T09:47:42.656447 - 0.0 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/ComfyLiterals
2025-11-02T09:47:42.656476 - 0.0 seconds (IMPORT FAILED): /root/autodl-tmp/ComfyUI/custom_nodes/.ipynb_checkpoints
2025-11-02T09:47:42.656511 - 0.0 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/masquerade-nodes-comfyui
2025-11-02T09:47:42.656537 - 0.0 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI-WanMoeKSampler
2025-11-02T09:47:42.656561 - 0.0 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI-WD14-Tagger
2025-11-02T09:47:42.656583 - 0.0 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/wanblockswap
2025-11-02T09:47:42.656607 - 0.0 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI-moondream
2025-11-02T09:47:42.656629 - 0.0 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/comfyui-various
2025-11-02T09:47:42.656652 - 0.0 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/wavespeed
2025-11-02T09:47:42.656675 - 0.0 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI-Custom-Scripts
2025-11-02T09:47:42.656698 - 0.0 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI_essentials
2025-11-02T09:47:42.656721 - 0.0 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI-Dev-Utils
2025-11-02T09:47:42.656741 - 0.0 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/PowerNoiseSuite
2025-11-02T09:47:42.656763 - 0.0 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI-Frame-Interpolation
2025-11-02T09:47:42.656784 - 0.0 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/Derfuu_ComfyUI_ModdedNodes
2025-11-02T09:47:42.656805 - 0.0 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/comfyui-browser
2025-11-02T09:47:42.656825 - 0.0 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI-Advanced-ControlNet
2025-11-02T09:47:42.656852 - 0.0 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/rgthree-comfy
2025-11-02T09:47:42.656878 - 0.0 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI-KJNodes
2025-11-02T09:47:42.656902 - 0.0 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI_Qwen3-VL-Instruct
2025-11-02T09:47:42.656925 - 0.0 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI_IPAdapter_plus
2025-11-02T09:47:42.656947 - 0.0 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI_Comfyroll_CustomNodes
2025-11-02T09:47:42.656972 - 0.0 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/efficiency-nodes-comfyui
2025-11-02T09:47:42.656997 - 0.0 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI_tinyterraNodes
2025-11-02T09:47:42.657020 - 0.0 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI-Inspire-Pack
2025-11-02T09:47:42.657042 - 0.0 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI_smZNodes
2025-11-02T09:47:42.657064 - 0.0 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI-VideoHelperSuite
2025-11-02T09:47:42.657088 - 0.1 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI-Manager
2025-11-02T09:47:42.657110 - 0.1 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/comfyui_layerstyle
2025-11-02T09:47:42.657130 - 0.1 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI-Impact-Pack
2025-11-02T09:47:42.657150 - 0.1 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI_FizzNodes
2025-11-02T09:47:42.657173 - 0.2 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI-Easy-Use
2025-11-02T09:47:42.657194 - 0.6 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/comfyui_controlnet_aux
2025-11-02T09:47:42.657214 - 0.7 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI-nunchaku
2025-11-02T09:47:42.657236 - 0.9 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/was-node-suite-comfyui
2025-11-02T09:47:42.657256 - 1.0 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI-WanVideoWrapper
2025-11-02T09:47:42.657276 - 1.7 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI-TeaCache
2025-11-02T09:47:42.657305 - 12.6 seconds: /root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI_BiRefNet_ll
2025-11-02T09:47:42.657331 -
2025-11-02T09:47:43.216508 - Context impl SQLiteImpl.
2025-11-02T09:47:43.216630 - Will assume non-transactional DDL.
2025-11-02T09:47:43.217402 - No target revision found.
2025-11-02T09:47:43.235567 - Starting server

2025-11-02T09:47:43.235819 - To see the GUI go to: http://0.0.0.0:6006
2025-11-02T09:48:01.574659 - FETCH ComfyRegistry Data: 5/1032025-11-02T09:48:01.574839 -
2025-11-02T09:48:10.516683 - FETCH ComfyRegistry Data: 10/1032025-11-02T09:48:10.516828 -
2025-11-02T09:48:18.531822 - FETCH ComfyRegistry Data: 15/1032025-11-02T09:48:18.532177 -
2025-11-02T09:48:26.832712 - FETCH ComfyRegistry Data: 20/1032025-11-02T09:48:26.832862 -
2025-11-02T09:48:46.213101 - FETCH ComfyRegistry Data: 25/1032025-11-02T09:48:46.213351 -
2025-11-02T09:48:56.448185 - FETCH ComfyRegistry Data: 30/1032025-11-02T09:48:56.448323 -
2025-11-02T09:49:05.034500 - FETCH ComfyRegistry Data: 35/1032025-11-02T09:49:05.034661 -
2025-11-02T09:49:14.156118 - FETCH ComfyRegistry Data: 40/1032025-11-02T09:49:14.156264 -
2025-11-02T09:49:17.338448 - [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.
2025-11-02T09:49:17.411208 - [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.
2025-11-02T09:49:17.427246 - [DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/popup.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.
2025-11-02T09:49:17.428180 - [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.
2025-11-02T09:49:17.478055 - [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.
2025-11-02T09:49:17.485640 - [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.
2025-11-02T09:49:17.523604 - [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.
2025-11-02T09:49:20.421683 - Disable Log Console. client id: 68956cc80f9341b9bc444b0fb28a1f02, console id: 4f3b6941-46cf-4f53-a4d2-e9b76892b7ee2025-11-02T09:49:20.421820 -
2025-11-02T09:49:33.509792 - FETCH ComfyRegistry Data: 45/1032025-11-02T09:49:33.509938 -
2025-11-02T09:49:43.976053 - FETCH ComfyRegistry Data: 50/1032025-11-02T09:49:43.976221 -
2025-11-02T09:49:46.233174 - got prompt
2025-11-02T09:49:46.641647 - Failed to validate prompt for output 545:
2025-11-02T09:49:46.641978 - * ImageLoader 386:
2025-11-02T09:49:46.642152 - - Custom validation failed for node: image - Invalid image file: 27d223b9fa17b3949fe76ec74418bd26.jpg
2025-11-02T09:49:46.642271 - Output will be ignored
2025-11-02T09:49:46.643323 - Failed to validate prompt for output 544:
2025-11-02T09:49:46.643521 - * VAELoader 360:
2025-11-02T09:49:46.643655 - - Value not in list: vae_name: 'Qwen\qwen_image_vae.safetensors' not in ['qwen_image_vae.safetensors', 'sdxl_vae_fp16_fix.safetensors', 'wan_2.1_vae.safetensors', 'pixel_space']
2025-11-02T09:49:46.643761 - * UNETLoader 358:
2025-11-02T09:49:46.643850 - - Value not in list: unet_name: 'Rebalance_v1.safetensors' not in ['smoothMixWan22I2V14B_i2vHigh.safetensors', 'smoothMixWan22I2V14B_i2vLow.safetensors', 'svdq-fp4_r128-qwen-image-edit-2509-lightningv2.0-4steps.safetensors', 'svdq-fp4_r128-qwen-image-lightningv1.1-8steps.safetensors']
2025-11-02T09:49:46.643958 - * LoraLoaderModelOnly 367:
2025-11-02T09:49:46.644040 - - Value not in list: lora_name: 'Qwen\Qwen-Image-Edit-2509-Lightning-8steps-V1.0-bf16.safetensors' not in []
2025-11-02T09:49:46.644123 - Output will be ignored
2025-11-02T09:49:46.644261 - Failed to validate prompt for output 373:
2025-11-02T09:49:46.644366 - Output will be ignored
2025-11-02T09:49:46.644448 - Failed to validate prompt for output 388:
2025-11-02T09:49:46.644539 - Output will be ignored
2025-11-02T09:49:46.644657 - Failed to validate prompt for output 283:
2025-11-02T09:49:46.644753 - Output will be ignored
2025-11-02T09:49:46.652531 - WARNING: [Errno 2] No such file or directory: '/root/autodl-tmp/ComfyUI/input/27d223b9fa17b3949fe76ec74418bd26.jpg'
2025-11-02T09:49:46.680795 - /root/miniconda3/lib/python3.12/site-packages/torch/cuda/memory.py:491: FutureWarning: torch.cuda.reset_max_memory_allocated now calls torch.cuda.reset_peak_memory_stats, which resets /all/ peak memory stats.
warnings.warn(
2025-11-02T09:49:46.688391 - Using pytorch attention in VAE
2025-11-02T09:49:46.689202 - Using pytorch attention in VAE
2025-11-02T09:49:46.766975 - VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
2025-11-02T09:49:46.778243 - end_vram - start_vram: 0 - 0 = 02025-11-02T09:49:46.778495 -
2025-11-02T09:49:46.778541 - #454 [VAELoader]: 0.10s - vram 0b2025-11-02T09:49:46.778562 -
2025-11-02T09:49:47.212017 - end_vram - start_vram: 0 - 0 = 02025-11-02T09:49:47.212318 -
2025-11-02T09:49:47.212368 - #518 [ImageLoader]: 0.43s - vram 0b2025-11-02T09:49:47.212389 -
2025-11-02T09:49:47.212853 - end_vram - start_vram: 0 - 0 = 02025-11-02T09:49:47.212884 -
2025-11-02T09:49:47.212948 - #497 [Int]: 0.00s - vram 0b2025-11-02T09:49:47.213066 -
2025-11-02T09:49:47.608362 - # 😺dzNodes: LayerStyle -> ImageScaleByAspectRatio V2 Processed 1 image(s).2025-11-02T09:49:47.608429 -
2025-11-02T09:49:47.609515 - end_vram - start_vram: 0 - 0 = 02025-11-02T09:49:47.609548 -
2025-11-02T09:49:47.609619 - #438 [LayerUtility: ImageScaleByAspectRatio V2]: 0.40s - vram 0b2025-11-02T09:49:47.609703 -
2025-11-02T09:49:47.643093 - end_vram - start_vram: 0 - 0 = 02025-11-02T09:49:47.643190 -
2025-11-02T09:49:47.643276 - #439 [PreviewImage]: 0.03s - vram 0b2025-11-02T09:49:47.643305 -
2025-11-02T09:49:47.643706 - {'type': 'image', 'image': '/root/autodl-tmp/ComfyUI/input/η•Œε›Ύ1761989255007.png'}2025-11-02T09:49:47.643750 -
2025-11-02T09:49:47.643824 - [{'type': 'image', 'image': '/root/autodl-tmp/ComfyUI/input/η•Œε›Ύ1761989255007.png'}]2025-11-02T09:49:47.643852 -
2025-11-02T09:49:47.644027 - end_vram - start_vram: 0 - 0 = 02025-11-02T09:49:47.644076 -
2025-11-02T09:49:47.644142 - #516 [MultiplePathsInput]: 0.00s - vram 0b2025-11-02T09:49:47.644169 -
2025-11-02T09:49:47.798445 - end_vram - start_vram: 0 - 0 = 02025-11-02T09:49:47.798584 -
2025-11-02T09:49:47.798649 - #534 [CLIPVisionLoader]: 0.15s - vram 0b2025-11-02T09:49:47.798714 -
2025-11-02T09:49:47.799146 - Requested to load CLIPVisionModelProjection
2025-11-02T09:49:47.994506 - loaded completely 46907.4875 1208.09814453125 True
2025-11-02T09:49:48.166608 - end_vram - start_vram: 1487459352 - 0 = 14874593522025-11-02T09:49:48.166726 -
2025-11-02T09:49:48.166775 - #537 [CLIPVisionEncode]: 0.37s - vram 1487459352b2025-11-02T09:49:48.166797 -
2025-11-02T09:49:48.656429 - Requested to load WanTEModel
2025-11-02T09:49:48.662250 - loaded completely 9.5367431640625e+25 10835.4765625 True
2025-11-02T09:49:48.663758 - CLIP/text encoder model load device: cpu, offload device: cpu, current: cpu, dtype: torch.float16
2025-11-02T09:49:49.748208 - end_vram - start_vram: 1275304960 - 1275304960 = 02025-11-02T09:49:49.748521 -
2025-11-02T09:49:49.748617 - #506 [CLIPLoader]: 1.58s - vram 0b2025-11-02T09:49:49.748642 -
2025-11-02T09:49:52.940627 - FETCH ComfyRegistry Data: 55/1032025-11-02T09:49:52.940713 -
2025-11-02T09:49:56.156929 - end_vram - start_vram: 1275304960 - 1275304960 = 02025-11-02T09:49:56.157404 -
2025-11-02T09:49:56.157466 - #442 [CLIPTextEncode]: 6.41s - vram 0b2025-11-02T09:49:56.157497 -
2025-11-02T09:49:56.158139 - end_vram - start_vram: 1275304960 - 1275304960 = 02025-11-02T09:49:56.158212 -
2025-11-02T09:49:56.158263 - #540 [CR Prompt Text]: 0.00s - vram 0b2025-11-02T09:49:56.158293 -
2025-11-02T09:49:56.158743 - end_vram - start_vram: 1275304960 - 1275304960 = 02025-11-02T09:49:56.158779 -
2025-11-02T09:49:56.158854 - #523 [CR Prompt Text]: 0.00s - vram 0b2025-11-02T09:49:56.158877 -
2025-11-02T09:49:56.159326 - end_vram - start_vram: 1275304960 - 1275304960 = 02025-11-02T09:49:56.159362 -
2025-11-02T09:49:56.159714 - #524 [JWStringConcat]: 0.00s - vram 0b2025-11-02T09:49:56.159743 -
2025-11-02T09:49:56.886140 - We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk).
2025-11-02T09:50:00.884952 -
Loading checkpoint shards: 50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 1/2 [00:03<00:03, 3.94s/it]2025-11-02T09:50:02.559757 - FETCH ComfyRegistry Data: 60/1032025-11-02T09:50:02.559902 -
2025-11-02T09:50:04.878695 -
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2/2 [00:07<00:00, 3.97s/it]2025-11-02T09:50:04.878915 -
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2/2 [00:07<00:00, 3.96s/it]2025-11-02T09:50:04.878944 -
2025-11-02T09:50:05.265501 - /root/miniconda3/lib/python3.12/site-packages/bitsandbytes/autograd/_functions.py:181: UserWarning: MatMul8bitLt: inputs will be cast from torch.bfloat16 to float16 during quantization
warnings.warn(f"MatMul8bitLt: inputs will be cast from {A.dtype} to float16 during quantization")
2025-11-02T09:50:11.286493 - FETCH ComfyRegistry Data: 65/1032025-11-02T09:50:11.286690 -
2025-11-02T09:50:23.885886 - FETCH ComfyRegistry Data: 70/1032025-11-02T09:50:23.886307 -
2025-11-02T09:50:35.809936 - FETCH ComfyRegistry Data: 75/1032025-11-02T09:50:35.810160 -
2025-11-02T09:50:40.832631 - end_vram - start_vram: 6401180820 - 1275304960 = 51258758602025-11-02T09:50:40.833001 -
2025-11-02T09:50:40.833058 - #521 [Qwen3_VQA]: 44.67s - vram 5125875860b2025-11-02T09:50:40.833090 -
2025-11-02T09:50:40.833558 - end_vram - start_vram: 1275304960 - 1275304960 = 02025-11-02T09:50:40.833588 -
2025-11-02T09:50:40.833639 - #546 [easy clearCacheAll]: 0.00s - vram 0b2025-11-02T09:50:40.833663 -
2025-11-02T09:50:40.834046 - end_vram - start_vram: 1275304960 - 1275304960 = 02025-11-02T09:50:40.834074 -
2025-11-02T09:50:40.834130 - #520 [easy showAnything]: 0.00s - vram 0b2025-11-02T09:50:40.834147 -
2025-11-02T09:50:47.930071 - FETCH ComfyRegistry Data: 80/1032025-11-02T09:50:47.930318 -
2025-11-02T09:50:49.401229 - end_vram - start_vram: 1275304960 - 1275304960 = 02025-11-02T09:50:49.401293 -
2025-11-02T09:50:49.401592 - #501 [CLIPTextEncode]: 8.57s - vram 0b2025-11-02T09:50:49.401642 -
2025-11-02T09:50:49.402295 - end_vram - start_vram: 1275304960 - 1275304960 = 02025-11-02T09:50:49.402372 -
2025-11-02T09:50:49.402465 - #489 [Int]: 0.00s - vram 0b2025-11-02T09:50:49.402486 -
2025-11-02T09:50:49.446868 - Requested to load WanVAE
2025-11-02T09:50:49.549514 - loaded completely 42970.7275390625 242.02829551696777 True
2025-11-02T09:50:51.639052 - end_vram - start_vram: 4137959926 - 1275304960 = 28626549662025-11-02T09:50:51.639242 -
2025-11-02T09:50:51.639387 - #472 [WanImageToVideo]: 2.24s - vram 2862654966b2025-11-02T09:50:51.639422 -
2025-11-02T09:50:51.681293 - Using scaled fp8: fp8 matrix mult: True, scale input: True
2025-11-02T09:50:51.708352 - model weight dtype torch.float16, manual cast: None
2025-11-02T09:50:51.708714 - model_type FLOW
2025-11-02T09:50:53.260076 - end_vram - start_vram: 1529090022 - 1529090022 = 02025-11-02T09:50:53.260444 -
2025-11-02T09:50:53.260490 - #458 [UNETLoader]: 1.62s - vram 0b2025-11-02T09:50:53.260530 -
2025-11-02T09:50:53.261134 - end_vram - start_vram: 1529090022 - 1529090022 = 02025-11-02T09:50:53.261162 -
2025-11-02T09:50:53.261225 - #459 [wanBlockSwap]: 0.00s - vram 0b2025-11-02T09:50:53.261243 -
2025-11-02T09:50:53.261798 - end_vram - start_vram: 1529090022 - 1529090022 = 02025-11-02T09:50:53.261829 -
2025-11-02T09:50:53.261983 - #440 [PathchSageAttentionKJ]: 0.00s - vram 0b2025-11-02T09:50:53.262015 -
2025-11-02T09:50:53.262390 - end_vram - start_vram: 1529090022 - 1529090022 = 02025-11-02T09:50:53.262426 -
2025-11-02T09:50:53.262467 - #448 [ModelPatchTorchSettings]: 0.00s - vram 0b2025-11-02T09:50:53.262493 -
2025-11-02T09:50:53.311129 - Using scaled fp8: fp8 matrix mult: True, scale input: True
2025-11-02T09:50:53.337361 - model weight dtype torch.float16, manual cast: None
2025-11-02T09:50:53.337698 - model_type FLOW
2025-11-02T09:50:54.726068 - end_vram - start_vram: 1529090022 - 1529090022 = 02025-11-02T09:50:54.726479 -
2025-11-02T09:50:54.726523 - #505 [UNETLoader]: 1.46s - vram 0b2025-11-02T09:50:54.726550 -
2025-11-02T09:50:54.727093 - end_vram - start_vram: 1529090022 - 1529090022 = 02025-11-02T09:50:54.727130 -
2025-11-02T09:50:54.727169 - #461 [wanBlockSwap]: 0.00s - vram 0b2025-11-02T09:50:54.727192 -
2025-11-02T09:50:54.727690 - end_vram - start_vram: 1529090022 - 1529090022 = 02025-11-02T09:50:54.727724 -
2025-11-02T09:50:54.727758 - #441 [PathchSageAttentionKJ]: 0.00s - vram 0b2025-11-02T09:50:54.727780 -
2025-11-02T09:50:54.728284 - end_vram - start_vram: 1529090022 - 1529090022 = 02025-11-02T09:50:54.728318 -
2025-11-02T09:50:54.728357 - #447 [ModelPatchTorchSettings]: 0.00s - vram 0b2025-11-02T09:50:54.728378 -
2025-11-02T09:50:54.728713 - end_vram - start_vram: 1529090022 - 1529090022 = 02025-11-02T09:50:54.728740 -
2025-11-02T09:50:54.728772 - #487 [INTConstant]: 0.00s - vram 0b2025-11-02T09:50:54.728803 -
2025-11-02T09:50:54.737964 - switching model at step 22025-11-02T09:50:54.738012 -
2025-11-02T09:50:54.738039 - Running high noise model...2025-11-02T09:50:54.738057 -
2025-11-02T09:50:54.738872 - Requested to load WAN21
2025-11-02T09:50:56.455513 - loaded completely 41627.2382723107 13629.075424194336 True
2025-11-02T09:51:00.691097 -
Initializing block swap: 98%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ| 39/40 [00:04<00:00, 7.82it/s]2025-11-02T09:51:00.778706 -
Initializing block swap: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 40/40 [00:04<00:00, 9.28it/s]2025-11-02T09:51:00.778745 -
2025-11-02T09:51:01.516221 - Patching comfy attention to use sageattn2025-11-02T09:51:01.516477 -
2025-11-02T09:51:01.516570 - Patching torch settings: torch.backends.cuda.matmul.allow_fp16_accumulation = True2025-11-02T09:51:01.516598 -
2025-11-02T09:51:01.520958 -
0%| | 0/2 [00:00

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.