wanvideo_2_1_14B_MoCha_replace_subject_KJ_02.json

Open
#2,006 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
3/5
Estimated time
1-2 days
Newbie friendliness
43/100
Issue type
Bug
Clarity
Mostly clear
Activity status
Quiet
Tech stack
python, pytorch

Research direction

Start with nodes_sampler.py at the compile_model call and utils.py where torch.compile is configured; the traceback shows an ImportError inside PyTorch Inductor for get_free_symbols. Check the project’s documented PyTorch and ComfyUI version requirements, then reproduce with the reported workflow and compilation settings. Done means compilation no longer raises this import error under the supported setup.

Written by the indexing model from the issue text.

Description

File "N:\ComfyUI-master\ComfyUI\execution.py", line 534, 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 "N:\ComfyUI-master\ComfyUI\execution.py", line 334, 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 "N:\ComfyUI-master\ComfyUI\execution.py", line 308, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "N:\ComfyUI-master\ComfyUI\execution.py", line 296, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "N:\ComfyUI-master\ComfyUI\custom_nodes\ComfyUI-WanVideoWrapper\nodes_sampler.py", line 147, in process
transformer = compile_model(transformer, model["compile_args"])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "N:\ComfyUI-master\ComfyUI\custom_nodes\ComfyUI-WanVideoWrapper\utils.py", line 636, in compile_model
transformer.blocks[i] = torch.compile(block, fullgraph=compile_args["fullgraph"], dynamic=compile_args["dynamic"], backend=compile_args["backend"], mode=compile_args["mode"])

File "N:\ComfyUI-master\python_embeded\Lib\site-packages\torch_init_.py", line 2572, in compile
return torch._dynamo.optimize(
^^^^^^^^^^^^^^^^^^^^^^^
File "N:\ComfyUI-master\python_embeded\Lib\site-packages\torch_dynamo\eval_frame.py", line 944, in optimize
return _optimize(rebuild_ctx, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "N:\ComfyUI-master\python_embeded\Lib\site-packages\torch_dynamo\eval_frame.py", line 1019, in optimize
backend.get_compiler_config()
File "N:\ComfyUI-master\python_embeded\Lib\site-packages\torch_init.py", line 2350, in get_compiler_config
from torch.inductor.compile_fx import get_patched_config_dict
File "N:\ComfyUI-master\python_embeded\Lib\site-packages\torch_inductor\compile_fx.py", line 101, in
from .fx_passes.joint_graph import joint_graph_passes
File "N:\ComfyUI-master\python_embeded\Lib\site-packages\torch_inductor\fx_passes\joint_graph.py", line 23, in
from ..pattern_matcher import (
File "N:\ComfyUI-master\python_embeded\Lib\site-packages\torch_inductor\pattern_matcher.py", line 79, in
from .lowering import fallback_node_due_to_unsupported_type
File "N:\ComfyUI-master\python_embeded\Lib\site-packages\torch_inductor\lowering.py", line 7027, in
import_submodule(kernel)
File "N:\ComfyUI-master\python_embeded\Lib\site-packages\torch_dynamo\utils.py", line 3412, in import_submodule
importlib.import_module(f"{mod.name}.{filename[:-3]}")
File "importlib_init.py", line 90, in import_module
File "N:\ComfyUI-master\python_embeded\Lib\site-packages\torch_inductor\kernel\custom_op.py", line 10, in
from torch._inductor.codegen.subgraph import SubgraphTemplate
File "N:\ComfyUI-master\python_embeded\Lib\site-packages\torch_inductor\codegen\subgraph.py", line 12, in
from torch._inductor.ir import (
ImportError: cannot import name 'get_free_symbols' from 'torch._inductor.ir' (N:\ComfyUI-master\python_embeded\Lib\site-packages\torch_inductor\ir.py)

Dominant language
Python
Stars
6.8k
Forks
712
PR merge metrics
No merged PRs in 30d

Getting set up

This project ships no dev container, Dockerfile or contributing guide, so setting up is up to you: start from its README, and see our first-contribution guide for the general steps.

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from kijai/ComfyUI-WanVideoWrapper

All issues in kijai/ComfyUI-WanVideoWrapper

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.