After the latest upgrade, there was an error when using the Voronoi Noise node.

[sober54]

Error occurred when executing Image Voronoi Noise Filter:

setting an array element with a sequence.

File "C:\Users\sober\compyui\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "C:\Users\sober\compyui\ComfyUI_windows_portable\ComfyUI\execution.py", line 81, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) File "C:\Users\sober\compyui\ComfyUI_windows_portable\ComfyUI\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) File "C:\Users\sober\compyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\was-node-suite-comfyui\WAS_Node_Suite.py", line 4221, in voronoi_noise_filter image = WTools.worley_noise(height=width, width=height, density=density, option=modulator, use_broadcast_ops=True, flat=(flat == "True")).image File "C:\Users\sober\compyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\was-node-suite-comfyui\WAS_Node_Suite.py", line 2082, in init self.image = self.generateImage(option, flat_mode=flat) File "C:\Users\sober\compyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\was-node-suite-comfyui\WAS_Node_Suite.py", line 2116, in generateImage non_flat_black_adjusted[h, w] = self.data[h, w] + self.data[closest_point_idx]

[sober54]

It is now in the bag,I am going to test the ultimate challenge- underwater

[sober54]

Incredibly good

[sober54]

赛博菩萨

[sober54]

[WASasquatch]

It's definitely subjective in some gens, I've noticed from my experimenting, but overall it does seam to lean towards better gens, and even prompt interpretation. Like when I do a product or character concept, I often get just the subject on plain background, where regular noise will put in random backgrounds.

I'm going to close this topic, but we can continue to discuss. Since the original problem is solved.

[sober54]

Certainly, sir. This issue is like for solving an input error, you are improving this world .

[sober54]

The node has a bug. When using image as output, it generates the set size(7681024) img, but the ksampler calculates a 96128 image

[sober54]

I think you need to enter a complete and user-friendly node description in the readme. Move those comparison images to another place so that I have a space to put more images

[WASasquatch]

I think you need to enter a complete and user-friendly node description in the readme. Move those comparison images to another place so that I have a space to put more images

Could probably activate and use the wiki thing.

[sober54]

Okay,let me know if you need anything

[WASasquatch]

Added a wiki: https://github.com/WASasquatch/PPF_Noise_ComfyUI/wiki

And I redid the readme, moving old stuff to old_readme.md so it looks more tidy.

Feel free to add more comparisons, or new sections for study or image/workflow share.

[sober54]

it's done sir

[WASasquatch]

Nice, though maybe name it something like "Walkthrough". Also to note, you do not need to input a VAE. That is optional.

[sober54]

CUDA latent is absolutely genius, as it seems to solve the problem with VAE