-
-
Notifications
You must be signed in to change notification settings - Fork 97
Open
Description
'🔥 - 11 Nodes not included in prompt but is activated'
CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
Requested to load SD3ClipModel_
loaded partially 1979.9816368103027 1965.693359375 0
loaded partially 3853.674996185303 3853.673828125 0
!!! Exception during processing !!! local variable 'H' referenced before assignment
Traceback (most recent call last):
File "/home/garrett/AI/ComfyUI/execution.py", line 427, 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)
File "/home/garrett/AI/ComfyUI/execution.py", line 270, 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)
File "/home/garrett/AI/ComfyUI/execution.py", line 244, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "/home/garrett/AI/ComfyUI/execution.py", line 232, in process_inputs
result = f(**inputs)
File "/home/garrett/AI/ComfyUI/custom_nodes/comfyui-cogvideoxwrapper/nodes.py", line 662, in process
height = H * 8
UnboundLocalError: local variable 'H' referenced before assignment
This issue is in "ComfyUI/custom_nodes/comfyui-cogvideoxwrapper/nodes.py". Changing:
if samples is not None:
if len(samples["samples"].shape) == 5:
B, T, C, H, W = samples["samples"].shape
latents = samples["samples"]
if len(samples["samples"].shape) == 4:
B, C, H, W = samples["samples"].shape
latents = None
if image_cond_latents is not None:
B, T, C, H, W = image_cond_latents["samples"].shape
height = H * 8
width = W * 8
to:
if samples is not None:
if len(samples["samples"].shape) == 5:
B, T, C, H, W = samples["samples"].shape
latents = samples["samples"]
elif len(samples["samples"].shape) == 4: # change if to elif
B, C, H, W = samples["samples"].shape
latents = None
elif image_cond_latents is not None: # change if to elif
B, T, C, H, W = image_cond_latents["samples"].shape
else: # add this else statement
raise ValueError("Either 'samples' or 'image_cond_latents' must be provided to determine dimensions.")
height = H * 8
width = W * 8
resolves the issue.
Metadata
Metadata
Assignees
Labels
No labels