haoming02 / comfyui-resharpen Goto Github PK

Hey, thank you for your custom node, I'm currently using on it with Flux and works very well, but once I try to generate another image with the same reshapen node value , it gives me this error, If I change the value to another one and I queue the prompt, it works without issues, and then I can change to the original value, but as as soon as I try to repeat the workflow, it gives me this error:

`Error occurred when executing SamplerCustomAdvanced:

The size of tensor a (136) must match the size of tensor b (170) at non-singleton dimension 3

File "G:\ComfyUI\execution.py", line 316, 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 "G:\ComfyUI\execution.py", line 191, 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 "G:\ComfyUI\execution.py", line 168, in _map_node_over_list
process_inputs(input_dict, i)
File "G:\ComfyUI\execution.py", line 157, in process_inputs
results.append(getattr(obj, func)(**inputs))
File "G:\ComfyUI\comfy_extras\nodes_custom_sampler.py", line 612, in sample
samples = guider.sample(noise.generate_noise(latent), latent_image, sampler, sigmas, denoise_mask=noise_mask, callback=callback, disable_pbar=disable_pbar, seed=noise.seed)
File "G:\ComfyUI\comfy\samplers.py", line 716, in sample
output = self.inner_sample(noise, latent_image, device, sampler, sigmas, denoise_mask, callback, disable_pbar, seed)
File "G:\ComfyUI\comfy\samplers.py", line 695, in inner_sample
samples = sampler.sample(self, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
File "G:\ComfyUI\comfy\samplers.py", line 600, in sample
samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **self.extra_options)
File "G:\ComfyUI\venv\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "G:\ComfyUI\comfy\k_diffusion\sampling.py", line 655, in sample_dpmpp_2m
callback({'x': x, 'i': i, 'sigma': sigmas[i], 'sigma_hat': sigmas[i], 'denoised': denoised})
File "G:\ComfyUI\comfy\samplers.py", line 598, in
k_callback = lambda x: callback(x["i"], x["denoised"], x["x"], total_steps)
File "G:\ComfyUI\venv\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "G:\ComfyUI\custom_nodes\comfyui-resharpen\resharpen.py", line 37, in hijack_callback
delta = x.detach().clone() - LATENT_CACHE`

I have it connected like this

Thanks for everything

Intermittently blurry images when using this with Flux. I think it may be related to some recent comfyui update as the issue wasn't here a week ago but I'm unable to debug it.

Please give info in description

1. What sd its used? 1.5, xl, 3 etc?
2. what samplers you recomend.

I have 2 controlNet before the prompt (one tile, one Hed), when I add the hook between prompt (which is null, I don't use any to test) and 1st controlnet (positive) it gives me 0 differente or even an error message. Did you try to use with a loaded image on img2img to see the effect?

Hi I'm getting following error if try to install via manager

ComfyUI ReSharpen install failed: With the current security level configuration, only custom nodes from the "default channel" can be installed.

Updated and restarted comfy, but didn't help.. Probably it's not addon issue but dont know what to do with it