kijai / ComfyUI-CogVideoXWrapper

981 stars 59 forks source link

Getting the Sizes of tensors must match error on the 1.5 test branch for image to video on new 1.5 model #250

Closed tcla75 closed 2 days ago

tcla75 commented 2 days ago

got prompt Only one image conditioning frame received, img2vid !!! Exception during processing !!! Sizes of tensors must match except in dimension 1. Expected size 60 but got size 170 for tensor number 1 in the list. Traceback (most recent call last): File "C:\SD\ComfyUI2\New\ComfyUI_windows_portable\ComfyUI\execution.py", line 323, 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 "C:\SD\ComfyUI2\New\ComfyUI_windows_portable\ComfyUI\execution.py", line 198, 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 "C:\SD\ComfyUI2\New\ComfyUI_windows_portable\ComfyUI\execution.py", line 169, in _map_node_over_list process_inputs(input_dict, i) File "C:\SD\ComfyUI2\New\ComfyUI_windows_portable\ComfyUI\execution.py", line 158, in process_inputs results.append(getattr(obj, func)(*inputs)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\SD\ComfyUI2\New\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-CogVideoXWrapper\nodes.py", line 875, in process latents = pipeline["pipe"]( ^^^^^^^^^^^^^^^^^ File "C:\SD\ComfyUI2\New\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\utils_contextlib.py", line 116, in decorate_context return func(args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "C:\SD\ComfyUI2\New\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-CogVideoXWrapper\pipeline_cogvideox.py", line 525, in call image_cond_latents = torch.cat([image_cond_latents, latent_padding], dim=1) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 60 but got size 170 for tensor number 1 in the list.

kijai commented 2 days ago

This was probably due to me changing the nodes, lots of stuff has changed so this issue as it is becomes redundant.