bytedance / bytedance/ComfyUI-HyperLoRA

HyperLoRA ID Cond torch.cat(): expected a non-empty list of Tensors

Open
#39 3 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
499
Forks
29
PR merge metrics
No merged PRs in 30d

Description

Traceback (most recent call last):
File "/home/aigc_worker/aigc/ComfyUI/execution.py", line 327, in execute
output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
File "/home/aigc_worker/aigc/ComfyUI/custom_nodes/Comfy-WaveSpeed/first_block_cache.py", line 90, in new_get_output_data
out = get_output_data(*args, **kwargs)
File "/home/aigc_worker/aigc/ComfyUI/execution.py", line 202, in get_output_data
return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
File "/home/aigc_worker/aigc/ComfyUI/execution.py", line 174, in _map_node_over_list
process_inputs(input_dict, i)
File "/home/aigc_worker/aigc/ComfyUI/execution.py", line 163, in process_inputs
results.append(getattr(obj, func)(**inputs))
File "/home/aigc_worker/aigc/ComfyUI/custom_nodes/ComfyUI-HyperLoRA/hyperlora/nodes.py", line 321, in execute
return [ id_images, id_embeds ], images2tensor(faces)
File "/home/aigc_worker/aigc/ComfyUI/custom_nodes/ComfyUI-HyperLoRA/hyperlora/common.py", line 90, in images2tensor
return torch.cat(tensor_list, dim=0)
RuntimeError: torch.cat(): expected a non-empty list of Tensors

Contributor guide

No contributing guide indexed for this repository

Research direction

Start in hyperlora/common.py at images2tensor, then trace its caller in hyperlora/nodes.py around execute line 321. Reproduce the HyperLoRA ID Cond failure and determine why faces produces an empty tensor list; done means the node no longer reaches torch.cat with no tensors and the intended output behavior is verified.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.