Starting from ComfyUI v0.16.0 and continuing in all newer versions I tested, enabling the merge_lora option in the WanVideo Lora Select Multi node causes an error and prevents the workflow from running correctly.
[INFO] got prompt
[WARNING] WARNING: type object 'LoadText' has no attribute 'file'
[INFO] CUDA Compute Capability: 8.6
[INFO] Detected model in_channels: 36
[INFO] Model cross attention type: i2v, num_heads: 40, num_layers: 40
[INFO] Model variant detected: 14B
[INFO] Loading LoRA: wan\lightx2v_I2V_14B_480p_cfg_step_distill_rank256_bf16 with strength: 0.6
[INFO] Loading LoRA: wan\Wan21_CausVid_14B_T2V_lora_rank32_v2 with strength: 1.0
[INFO] Loading LoRA: wan\Wan2.1-Fun-14B-InP-MPS with strength: 1.0
[INFO] Merging LoRA to the model...
Loading model and applying LoRA weights:: 0%| | 0/731 [00:00<?, ?it/s][WARNING] WARNING: string_to_seed has moved from comfy.model_patcher to comfy.utils
[WARNING] WARNING: string_to_seed has moved from comfy.model_patcher to comfy.utils
Loading model and applying LoRA weights:: 0%| | 1/731 [00:00<04:18, 2.82it/s][WARNING] WARNING: string_to_seed has moved from comfy.model_patcher to comfy.utils
[WARNING] WARNING: string_to_seed has moved from comfy.model_patcher to comfy.utils
[WARNING] WARNING: string_to_seed has moved from comfy.model_patcher to comfy.utils
[WARNING] WARNING: string_to_seed has moved from comfy.model_patcher to comfy.utils
[WARNING] WARNING: string_to_seed has moved from comfy.model_patcher to comfy.utils
[WARNING] WARNING: string_to_seed has moved from comfy.model_patcher to comfy.utils
Loading model and applying LoRA weights:: 1%|▏ | 4/731 [00:00<01:09, 10.43it/s][WARNING] WARNING: string_to_seed has moved from comfy.model_patcher to comfy.utils
[WARNING] WARNING: string_to_seed has moved from comfy.model_patcher to comfy.utils
[WARNING] WARNING: string_to_seed has moved from comfy.model_patcher to comfy.utils
Windows fatal exception: access violation
Stack (most recent call first):
File "C:\Portable\ComfyUI\ComfyUI_windows_portable\ComfyUI\comfy\utils.py", line 919 in copy_to_param
File "C:\Portable\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-WanVideoWrapper\utils.py", line 266 in patch_weight_to_device
File "C:\Portable\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-WanVideoWrapper\utils.py", line 313 in apply_lora
File "C:\Portable\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-WanVideoWrapper\nodes_model_loading.py", line 1736 in loadmodel
File "C:\Portable\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 298 in process_inputs
File "C:\Portable\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 310 in _async_map_node_over_list
File "C:\Portable\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 336 in get_output_data
File "C:\Portable\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 536 in execute
File "C:\Portable\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 774 in execute_async
File "asyncio\events.py", line 89 in _run
File "asyncio\base_events.py", line 2050 in _run_once
File "asyncio\base_events.py", line 683 in run_forever
File "asyncio\base_events.py", line 712 in run_until_complete
File "asyncio\runners.py", line 118 in run
File "asyncio\runners.py", line 195 in run
File "C:\Portable\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 714 in execute
File "C:\Portable\ComfyUI\ComfyUI_windows_portable\ComfyUI\main.py", line 327 in prompt_worker
File "threading.py", line 995 in run
File "threading.py", line 1044 in _bootstrap_inner
File "threading.py", line 1015 in _bootstrap
The issue does not occur in ComfyUI versions prior to v0.15.1
Starting from ComfyUI v0.16.0 and continuing in all newer versions I tested, enabling the merge_lora option in the WanVideo Lora Select Multi node causes an error and prevents the workflow from running correctly.