AttributeError: 'NoneType' object has no attribute 'cpu'
Closed this issue · 1 comments
halr9000 commented
Getting the below error when trying to use the simplest workflow. I've used the efficiency nodes successfully a million times before. I'm sure it's something in my Python environment which I've been debugging over the past couple of days, but would appreciate help debugging.
Efficient Loader Models Cache:
Ckpt:
[1] visiongenRealism_visiongenRealism
ERROR:root:!!! Exception during processing !!!
ERROR:root:Traceback (most recent call last):
File "D:\hal\stable-diffusion\ComfyUI\execution.py", line 153, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "D:\hal\stable-diffusion\ComfyUI\execution.py", line 83, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "D:\hal\stable-diffusion\ComfyUI\execution.py", line 76, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "D:\hal\stable-diffusion\ComfyUI\custom_nodes\efficiency-nodes-comfyui\efficiency_nodes.py", line 700, in sample
samples, images, gifs, preview = process_latent_image(model, seed, steps, cfg, sampler_name, scheduler,
File "D:\hal\stable-diffusion\ComfyUI\custom_nodes\efficiency-nodes-comfyui\efficiency_nodes.py", line 503, in process_latent_image
positive_hash = tensor_to_hash(positive[0][0])
File "D:\hal\stable-diffusion\ComfyUI\custom_nodes\efficiency-nodes-comfyui\tsc_utils.py", line 96, in tensor_to_hash
byte_repr = tensor.cpu().numpy().tobytes() # Convert tensor to bytes
AttributeError: 'NoneType' object has no attribute 'cpu'
Workflow image:
Repro steps
- Load default workflow, click Queue
- Observe successful generation
- Clear canvas
- Add efficiency loader, efficiency sampler, preview image nodes, wire them together, click queue
- Observe error