Very cool! Are you planing on making a SDXL version as well?

I'm getting this error: "Error occurred when executing KSampler: mat1 and mat2 shapes cannot be multiplied (154x2048 and 768x320)"

cannot execute SAMDetectorCombined because of VRAM usage, any fix?

it would be cool to make the same config for dressing people

it would be cool to make the same config for dressing people

I'm experiencing an error running it, and I think it came from operating a Bounded Image Blend with Mask node.

Detailed error messages are as follows.

Error occurred when executing Bounded Image Blend with Mask: Too many dimensions: 3 > 2.

!!! Exception during processing !!!

torch.cuda.OutOfMemoryError: Allocation on device 0 would exceed allowed memory. (out of memory)

Currently allocated : 4.80 GiB

Requested : 768.00 MiB

Device limit : 6.00 GiB

Free (according to CUDA): 0 bytes

PyTorch limit (set by user-supplied memory fraction)

how can I solve it?

I think this is not the place to write about errors, but...

I get the error:

Can you tell me how to fix it? Thanks :3

I dont know what im doing wrong. I got everything installed, but theres a big pile of nodes in the middle that arent connected properly and the inputimage is connected to nothing. Its the same with both versions. Also on Importing the workflow I get the Error: TypeError: path.lastIndexOf is not a function. This may be due to the following script:
/extensions/ComfyUI-Impact-Pack/impact-image-util.js. Maybe some models don't download properly, I don't know. Maybe you could put a link to all required models and where to put them. By the way I installed Controllnet auxiliary preprocessor, Impact Pack and WAS nodes via the ComfyUI manager. Maybe that's the problem?

i get this Errors :
ERROR:root:Failed to validate prompt for output 931:

ERROR:root:* Bounded Image Blend with Mask 922:

ERROR:root: - Required input is missing: image

ERROR:root: - Required input is missing: mask

ERROR:root:Output will be ignored

ERROR:root:Failed to validate prompt for output 903:

ERROR:root:* Bounded Image Blend with Mask 751:

ERROR:root: - Required input is missing: image

ERROR:root: - Required input is missing: mask

ERROR:root:* Bounded Image Blend with Mask 882:

ERROR:root: - Required input is missing: image

ERROR:root: - Required input is missing: mask

ERROR:root:Output will be ignored

ERROR:root:Failed to validate prompt for output 915:

ERROR:root:* Bounded Image Blend with Mask 912:

ERROR:root: - Required input is missing: image

ERROR:root: - Required input is missing: mask

ERROR:root:Output will be ignored

ERROR:root:Failed to validate prompt for output 752:

ERROR:root:Output will be ignored

ERROR:root:Failed to validate prompt for output 883:

ERROR:root:Output will be ignored

ERROR:root:Failed to validate prompt for output 936:

ERROR:root:Output will be ignored

ERROR:root:Failed to validate prompt for output 923:

ERROR:root:Output will be ignored

and all the "Bounded Image Blend with Mask" fields are Red

what im doning wrong?

Error occurred when executing Bounded Image Blend with Mask:

images do not match

File "E:\comfyui\Blender_ComfyUI\ComfyUI\execution.py", line 153, in recursive_execute

output_data, output_ui = get_output_data(obj, input_data_all)

File "E:\comfyui\Blender_ComfyUI\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 "E:\comfyui\Blender_ComfyUI\ComfyUI\execution.py", line 76, in map_node_over_list

results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))

File "E:\comfyui\Blender_ComfyUI\ComfyUI\custom_nodes\was-node-suite-comfyui\WAS_Node_Suite.py", line 11448, in bounded_image_blend_with_mask

result = Image.composite(source_positioned, target_pil, blend_mask)

File "E:\comfyui\Blender_ComfyUI\python_embeded\lib\site-packages\PIL\Image.py", line 3341, in composite

image.paste(image1, None, mask)

File "E:\comfyui\Blender_ComfyUI\python_embeded\lib\site-packages\PIL\Image.py", line 1731, in paste

self.im.paste(im, box, mask.im)

It seems to me like the "Bitwise(Mask - Mask)" in the impact pack is not working. If I replace those nodes with the "Masks Subtract" from WAS Suite, then the masks that rely on those nodes (detect hair, detect face, etc) seem to work?

i got this error:

Error occurred when executing BboxDetectorSEGS: UltraBBoxDetector.detect() takes from 5 to 6 positional arguments but 7 were given

Can you tell me how to fix it? Thanks :3

Hey @Postpos Here are some tips(That you may already have incorporated into your "personal version").

First - The holy grail of nudification is the ability to use 2 models. The model which destroys clothes and generates the body should be an Inpainting model. These are the models that can take window context into acccount.

Use RealisticVision for everything else, but the first 2 steps should be done on RealisticVision Inpainting.

Second - Using DPMPP_SDE means you should not need more than 26 iterations. 28 is fine to be safe. I see people often putting 30. It's not much, but it's 10% computing power saved per run which really adds up!

Is there any support URL for that? I'm getting this error at some late stage:

```!!! Exception during processing !!!

Traceback (most recent call last):

File "/mnt/e/Projekty/_AI/ComfyUI/execution.py", line 151, in recursive_execute

output_data, output_ui = get_output_data(obj, input_data_all)

File "/mnt/e/Projekty/_AI/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 "/mnt/e/Projekty/_AI/ComfyUI/execution.py", line 74, in map_node_over_list

results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))

File "/mnt/e/Projekty/_AI/ComfyUI/nodes.py", line 1368, in sample

return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)

File "/mnt/e/Projekty/_AI/ComfyUI/nodes.py", line 1338, in common_ksampler

samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,

File "/mnt/e/Projekty/_AI/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/sample_error_enhancer.py", line 9, in informative_sample

return original_sample(*args, **kwargs) # This code helps interpret error messages that occur within exceptions but does not have any impact on other operations.

File "/mnt/e/Projekty/_AI/ComfyUI/comfy/sample.py", line 100, in sample

samples = sampler.sample(noise, positive_copy, negative_copy, cfg=cfg, latent_image=latent_image, start_step=start_step, last_step=last_step, force_full_denoise=force_full_denoise, denoise_mask=noise_mask, sigmas=sigmas, callback=callback, disable_pbar=disable_pbar, seed=seed)

File "/mnt/e/Projekty/_AI/ComfyUI/comfy/samplers.py", line 703, in sample

return sample(self.model, noise, positive, negative, cfg, self.device, sampler, sigmas, self.model_options, latent_image=latent_image, denoise_mask=denoise_mask, callback=callback, disable_pbar=disable_pbar, seed=seed)

File "/mnt/e/Projekty/_AI/ComfyUI/comfy/samplers.py", line 592, in sample

positive = encode_model_conds(model.extra_conds, positive, noise, device, "positive", latent_image=latent_image, denoise_mask=denoise_mask, seed=seed)

File "/mnt/e/Projekty/_AI/ComfyUI/comfy/samplers.py", line 502, in encode_model_conds

out = model_function(**params)

File "/mnt/e/Projekty/_AI/ComfyUI/comfy/model_base.py", line 128, in extra_conds

if len(denoise_mask.shape) == len(noise.shape):

AttributeError: 'NoneType' object has no attribute 'shape'

```

Hello, if the video memory is insufficient, can you adjust some parameters to avoid this problem

how can I solve the following error as soon as I execute the code: SyntaxError: Unexpected non-whitespace character after JSON at position 4 (line 1 column 5)

Hello, you have created quite a small thing here, but I have to wait quite a long time. Is there no way to speed it up?

Any edits that can be made to the workflow to make it work with XL? Get an error when running and changed a few bits but still no luck

!!! Exception during processing !!!

Traceback (most recent call last):

File "D:\comfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute

output_data, output_ui = get_output_data(obj, input_data_all)

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\comfyUI\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 "D:\comfyUI\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 "D:\comfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\was-node-suite-comfyui-main\WAS_Node_Suite.py", line 5841, in image_rembg

from rembg import remove, new_session

ImportError: cannot import name 'remove' from 'rembg' (D:\comfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\rembg\__init__.py)

Where does the output go? Haven’t played around with it much, but it seems I get lots of masks in the temp folder, but no actual output after it is done running.

All nodes should be okay (none red), used ComfyUI manager to utdate them all. Manual downloads also put in their folders. Although I had to make a sams folder, there wasn’t one.

Using windows portable version.

Hi any help im trying to repair this from 3 days and i cant
Error occurred when executing KSampler: 'NoneType' object has no attribute 'shape' File "D:\Ai\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Ai\ComfyUI\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 "D:\Ai\ComfyUI\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 "D:\Ai\ComfyUI\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1344, in sample return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Ai\ComfyUI\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1314, in common_ksampler samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Ai\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\sample_error_enhancer.py", line 9, in informative_sample return original_sample(*args, kwargs) # This code helps interpret error messages that occur within exceptions but does not have any impact on other operations. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Ai\ComfyUI\ComfyUI_windows_portable\ComfyUI\comfy\sample.py", line 37, in sample samples = sampler.sample(noise, positive, negative, cfg=cfg, latent_image=latent_image, start_step=start_step, last_step=last_step, force_full_denoise=force_full_denoise, denoise_mask=noise_mask, sigmas=sigmas, callback=callback, disable_pbar=disable_pbar, seed=seed) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Ai\ComfyUI\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 755, in sample return sample(self.model, noise, positive, negative, cfg, self.device, sampler, sigmas, self.model_options, latent_image=latent_image, denoise_mask=denoise_mask, callback=callback, disable_pbar=disable_pbar, seed=seed) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Ai\ComfyUI\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 657, in sample return cfg_guider.sample(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Ai\ComfyUI\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 644, in sample output = self.inner_sample(noise, latent_image, device, sampler, sigmas, denoise_mask, callback, disable_pbar, seed) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Ai\ComfyUI\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 623, in inner_sample samples = sampler.sample(self, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Ai\ComfyUI\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 534, in sample samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, self.extra_options) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Ai\ComfyUI\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "D:\Ai\ComfyUI\ComfyUI_windows_portable\ComfyUI\comfy\k_diffusion\sampling.py", line 137, in sample_euler denoised = model(x, sigma_hat s_in, *extra_args) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Ai\ComfyUI\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 272, in call out = self.inner_model(x, sigma, model_options=model_options, seed=seed) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Ai\ComfyUI\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 610, in call return self.predict_noise(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Ai\ComfyUI\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 613, in predict_noise return sampling_function(self.inner_model, x, timestep, self.conds.get("negative", None), self.conds.get("positive", None), self.cfg, model_options=model_options, seed=seed) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Ai\ComfyUI\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 258, in sampling_function out = calc_cond_batch(model, conds, x, timestep, model_options) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Ai\ComfyUI\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 192, in calc_cond_batch c['control'] = control.get_control(input_x, timestep_, c, len(cond_or_uncond)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Ai\ComfyUI\ComfyUI_windows_portable\ComfyUI\comfy\controlnet.py", line 184, in get_control control = self.control_model(x=x_noisy.to(dtype), hint=self.cond_hint, timesteps=timestep.float(), context=context.to(dtype), y=y) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Ai\ComfyUI\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1511, in wrappedcall_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Ai\ComfyUI\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1520, in callimpl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Ai\ComfyUI\ComfyUI_windows_portable\ComfyUI\comfy\cldm\cldm.py", line 295, in forward assert y.shape[0] == x.shape[0] ^^^^^^^

works extremely well! finding the right model and vae to stop them from becoming skinny

Impressive set-up.

Doesn't run all the way for me though, i'm getting an error during runtime on "destroy clothes and outline body" ksampler. Would you be able to check it out? https://pastebin.com/cXr82jU0

I'm a newbie and don't know where to change, can you help me, thank you very much

Error occurred when executing Bounded Image Crop with Mask:

index is out of bounds for dimension with size 0

File "E:\BaiduNetdiskDownload\ComfyUI-aki-v1.1\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "E:\BaiduNetdiskDownload\ComfyUI-aki-v1.1\execution.py", line 81, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "E:\BaiduNetdiskDownload\ComfyUI-aki-v1.1\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "E:\BaiduNetdiskDownload\ComfyUI-aki-v1.1\custom_nodes\was-node-suite-comfyui\WAS_Node_Suite.py", line 11847, in bounded_image_crop_with_mask
rmin, rmax = torch.where(rows)[0][[0, -1]]

Hello, I get an error at generate body.

Can you help me with what this is ?

Error occurred when executing Bounded Image Crop with Mask: index is out of bounds for dimension with size 0 File "X:\xxx\AI\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "X:\xxx\AI\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 "X:\xxx\AI\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 "X:\xxx\AI\ComfyUI_windows_portable\ComfyUI\custom_nodes\was-node-suite-comfyui\WAS_Node_Suite.py", line 11809, in bounded_image_crop_with_mask rmin, rmax = torch.where(rows)[0][[0, -1]] ~~~~~~~~~~~~~~~~~~~~^^^^^^^^^

I get no errors anywhere but no matter what I do it doesn't give any final image. It creates the skin tone image and then it's done.

How can i nudify an female subject with long hair covering her breasts without removing all the hair from head? I tried but no luck...

Your workflow is so good. However, it does not work when the image is "from behind" (I mean, there is no face in the image), since bbox detector can't make sufficient mask for face, which throws an exception.

I'm struggling to find any way to detect empty mask and skip "keeping old faces". However, it seems hard to resolve this problem only with custom nodes and workflows. Any idea?

Thank you anyway. it works super well usually.

Whay always stoped at Generate Body?

Extremely sophisticated workflow there.

The skin color doesn't seem to be affected at all. The "Generate Body" step seems to be completely ignoring the mask. Any Ideas?

The process crashes on CLIPSeg with this error. I have not been able to figure it out for a week.

Error occurred when executing CLIPSeg Model Loader: Failed to import transformers.models.vit.image_processing_vit because of the following error (look up to see its traceback): Unable to convert function return value to a Python type! The signature was () -> handle File "J:\AI\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "J:\AI\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 "J:\AI\ComfyUI\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) File "J:\AI\ComfyUI\custom_nodes\was-node-suite-comfyui\WAS_Node_Suite.py", line 11301, in clipseg_model inputs = CLIPSegProcessor.from_pretrained(model, cache_dir=cache) File "C:\Users\afist\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\processing_utils.py", line 465, in from_pretrained args = cls._get_arguments_from_pretrained(pretrained_model_name_or_path, **kwargs) File "C:\Users\afist\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\processing_utils.py", line 509, in getarguments_from_pretrained attribute_class = getattr(transformers_module, class_name) File "C:\Users\afist\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\utils\import_utils.py", line 1526, in getattr value = getattr(module, name) File "C:\Users\afist\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\utils\import_utils.py", line 1525, in getattr module = self._get_module(self._class_to_module[name]) File "C:\Users\afist\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\utils\import_utils.py", line 1537, in getmodule raise RuntimeError(

Works fantastically. Has anyone had any luck with modifying it to generate a different set of clothes than what's present? I'm trying to change the "nude" related text (pussy, breasts, naked, etc) to be what I'm looking for, but the end result leaves much to be desired compared to the Nude option.

I'm getting this error in my commandprompt. If I had this file, would my generations be improved/happen faster?

Falling back to ['CUDAExecutionProvider', 'CPUExecutionProvider'] and retrying.

2024-06-21 17:49:40.1490534 [E:onnxruntime:Default, provider_bridge_ort.cc:1351 onnxruntime::TryGetProviderInfo_CUDA] D:\a\_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1131 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : LoadLibrary failed with error 126 "" when trying to load "D:\p\ComfyUI\python_embeded\Lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll"

not getitng any images, only genating masks and noting else

دError occurred when executing DWPreprocessor:An error happened while trying to locate the file on the Hub and we cannot find the requested files in the local cache.

执行DWPreprocessor时发生دError:试图在Hub上定位文件时发生错误，我们无法在本地缓存中找到所请求的文件。

Please check your connection and try again or make sure your Internet connection is on.

请检查您的连接，然后再试一次，或者确保您的互联网连接是打开的。

File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_executeoutput_data, output_ui = get_output_data(obj, input_data_all)File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 81, in get_output_datareturn_values = map_node_over_list(obj, input_data_all, obj.

文件"D:\ComfyUI_windows_portable\ComfyUI\ execute .py"，第151行，在recursive_executeoutput_data, output_ui = get_output_data(obj, input_data_all)文件"D:\ComfyUI_windows_portable\ComfyUI\ execute .py"，第81行，在get_output_datareturn_values = map_node_over_list(obj, input_data_all, obj.)

FUNCTION, allow_interrupt=True)File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_ezXY\autoCastPatch.py", line 303, in map_node_over_list return mapnode_over_list(obj, input_data_all, func, allow_interrupt)File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 74, in map_node_over_listresults.

文件"D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_ezXY\autoCastPatch.py"，第303行，在map_node_over_list返回_map_node_over_list(obj, input_data_all, func, allow_interrupt)文件"D:\ComfyUI_windows_portable\ComfyUI\ execute .py"，第74行，在map_node_over_listresults. py。

append(getattr(obj, func) (**slice_dict(input_data_all, i)))File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\node_wrappers\dwpose.py", line 72, in estimate_posemodel = DwposeDetector.

append(getattr(obj, func) (**slice_dict(input_data_all, i)))文件“D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\node_wrappers\ dwposse .py”，第72行，在estimate_posemodel = DwposeDetector. py中。

from_pretrained(File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\dwpose\_init__py", line 233, infrom_pretraineddet_model_path = custom_hf_download(pretrained_det_model_or_path, det_filename)File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\util.py", line 333,

文件"D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\dwpose\ initpy "，第233行，infrom_pretraineddet_model_path = custom_hf_download(pretrained_det_model_or_path, det_filename)文件"D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\util.py"，第333行，

in lcustom_hf_downloadmodel_path = hf_hub_download(repo_id=pretrained_model_or_path,File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\huggingface_hub\utils\_validators.py", line 114, in innerfnreturn fn(*args, **kwargs)File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\huggingface_hub\file_download.py", line 1202,

在lcustom_hf_downloadmodel_path = hf_hub_download(repo_id=pretrained_model_or_path，文件"D:\ComfyUI_windows_portable\ python_embedded \Lib\site-packages\huggingface_hub\utils\_validators.py"，第114行，在_inner_fnreturn fn(*args， **kwargs)文件"D:\ComfyUI_windows_portable\ python_embedded \Lib\site-packages\huggingface_hub\file_download.py"，第1202行，

in hf_hub_download return hfhub_download_to_local_dir(File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\huggingface_hub\file_download.

在hf_hub_download返回_hf_hub_download_to_local_dir(文件"D:\ComfyUI_windows_portable\ python_embedded \Lib\site-packages\huggingface_hub\file_download。

py", line 1440, in_hf_hub_download_to_local_dirraise_on_head_call_error(head_call_error, force_download, local_files_only)File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\huggingface_hub\file_download.py", line 1826, in_raise_on_head_call_errorraise LocalEntryNotFoundError(

文件"D:\ComfyUI_windows_portable\ python_embedded \Lib\site-packages\huggingface_hub\file_download.py"，第1826行，in_raise_on_head_call_errorraise LocalEntryNotFoundError(

提示这个错误怎么解决

Error occurred when executing DWPreprocessor: File "C:\Users\Test\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "C:\Users\Test\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\Test\ComfyUI\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) File "C:\Users\Test\ComfyUI\custom_nodes\comfyui_controlnet_aux\node_wrappers\dwpose.py", line 72, in estimate_pose model = DwposeDetector.from_pretrained( File "C:\Users\Test\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\dwpose\__init__.py", line 244, in from_pretrained t = Wholebody(None, pose_model_path, torchscript_device=torchscript_device) File "C:\Users\Test\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\dwpose\wholebody.py", line 74, in init self.pose.to(torchscript_device) File "D:\AI\MiniConda\envs\comfyui\lib\site-packages\torch\nn\modules\module.py", line 1173, in to return self._apply(convert) File "D:\AI\MiniConda\envs\comfyui\lib\site-packages\torch\nn\modules\module.py", line 779, in apply module.apply(fn) File "D:\AI\MiniConda\envs\comfyui\lib\site-packages\torch\nn\modules\module.py", line 828, in _apply assert isinstance(param, Parameter)

is there a way make this simpler, it's like a giant cluster fuck maze

I'm getting this error, what should I do?

Error occurred when executing OpenposePreprocessor: OpenposeDetector.from_pretrained() missing 1 required positional argument: 'pretrained_model_or_path' File "D:\Tun\Stable\new_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Tun\Stable\new_ComfyUI_windows_portable_nvidia_cu121_or_cpu\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 "D:\Tun\Stable\new_ComfyUI_windows_portable_nvidia_cu121_or_cpu\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 "D:\Tun\Stable\new_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux-main\node_wrappers\openpose.py", line 26, in estimate_pose model = OpenposeDetector.from_pretrained().to(model_management.get_torch_device()) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

Cheers for sharing this!
Really nice results!

For some reason, my ComfyUI keeps downloading models from huggingface for each prompt I run using this workflow.
This leads to every generation taking about 30 minutes.
Just to rule out it's because of my setup, I loaded the same models into stable diffusion webui and they worked like a charm.

Any idea why this workflow might keep downloading models for every prompt even if they are in the folders?

I'm on Apple silicone M3 with 36Gigs ram, is this maybe not enough to handle the whole workflow in cache?

Cheers for any input or ideas or hints as to where the workflow is getting the idea to connect to huggingface instead of recycling my local models :D

Error occurred when executing DWPreprocessor: 'NoneType' object has no attribute 'get_providers' File "D:\comfyui\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\comfyui\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 "D:\comfyui\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 "D:\comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\node_wrappers\dwpose.py", line 72, in estimate_pose model = DwposeDetector.from_pretrained( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\dwpose\__init__.py", line 238, in from_pretrained t = Wholebody(det_model_path, None, torchscript_device=torchscript_device) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\dwpose\wholebody.py", line 41, in init print(f"Failed to load onnxruntime with {self.det.get_providers()}.\nPlease change EP_list in the config.yaml and restart ComfyUI") ^^^^^^^^^^^^^^^^^^^^^^

Error occurred when executing Image Rembg (Remove Background): No module named 'rembg' File "D:\ComfyUI-aki-v1.3\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI-aki-v1.3\execution.py", line 81, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI-aki-v1.3\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI-aki-v1.3\custom_nodes\was-node-suite-comfyui\WAS_Node_Suite.py", line 5997, in image_rembg from rembg import remove, new_session

Error occurred when executing Image Rembg (Remove Background): No module named 'rembg' File "D:\ComfyUI-aki-v1.3\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI-aki-v1.3\execution.py", line 81, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI-aki-v1.3\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI-aki-v1.3\custom_nodes\was-node-suite-comfyui\WAS_Node_Suite.py", line 5997, in image_rembg from rembg import remove, new_session

Hi, im hoping for help ;D

i got thies error:

Error occurred when executing OpenposePreprocessor: [Errno 2] No such file or directory: 'C:\\NVIDIA\\Logs\\ComfyUI_windows_portable_nvidia\\ComfyUI_windows_portable\\ComfyUI\\custom_nodes\\comfyui_controlnet_aux\\ckpts\\lllyasviel\\Annotators\\.cache\\huggingface\\download\\body_pose_model.pth.25a948c16078b0f08e236bda51a385d855ef4c153598947c28c0d47ed94bb746.incomplete' File "C:\NVIDIA\Logs\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 152, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\NVIDIA\Logs\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 82, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\NVIDIA\Logs\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 75, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\NVIDIA\Logs\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\node_wrappers\openpose.py", line 26, in estimate_pose model = OpenposeDetector.from_pretrained().to(model_management.get_torch_device()) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\NVIDIA\Logs\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\open_pose\__init__.py", line 123, in from_pretrained body_model_path = custom_hf_download(pretrained_model_or_path, filename, subfolder=subfolder) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\NVIDIA\Logs\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\util.py", line 333, in custom_hf_download model_path = hf_hub_download(repo_id=pretrained_model_or_path, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\NVIDIA\Logs\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\huggingface_hub\utils\_deprecation.py", line 101, in inner_f return f(*args, **kwargs) ^^^^^^^^^^^^^^^^^^ File "C:\NVIDIA\Logs\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\huggingface_hub\utils\_validators.py", line 114, in innerfn return fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "C:\NVIDIA\Logs\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\huggingface_hub\file_download.py", line 1220, in hf_hub_download return hfhub_download_to_local_dir( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\NVIDIA\Logs\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\huggingface_hub\file_download.py", line 1515, in hfhub_download_to_local_dir downloadto_tmp_and_move( File "C:\NVIDIA\Logs\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\huggingface_hub\file_download.py", line 1903, in downloadto_tmp_and_move with incomplete_path.open("ab") as f: ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "pathlib.py", line 1044, in open

Sorry in advance, but I can't go beyond the initial masks. I can play around with the 'exclude hair, face, hands' masks but past that there is no images.
I assume I must connect the final exclude hands mask to something, since there is also a note saying 'You should see a naked body here.' and I don't have any errors on the terminal other than the missing images (e.g Failed to validate prompt for output 645: Output will be ignored)

Im getting the following error and Im unsure of how to proceed?

Error occurred when executing DWPreprocessor: File "f:\pinokio\api\comfyui.git\app\execution.py", line 152, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "f:\pinokio\api\comfyui.git\app\execution.py", line 82, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) File "f:\pinokio\api\comfyui.git\app\execution.py", line 75, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) File "F:\pinokio\api\comfyui.git\app\custom_nodes\comfyui_controlnet_aux\node_wrappers\dwpose.py", line 72, in estimate_pose model = DwposeDetector.from_pretrained( File "F:\pinokio\api\comfyui.git\app\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\dwpose\__init__.py", line 244, in from_pretrained t = Wholebody(None, pose_model_path, torchscript_device=torchscript_device) File "F:\pinokio\api\comfyui.git\app\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\dwpose\wholebody.py", line 74, in init self.pose.to(torchscript_device) File "f:\pinokio\api\comfyui.git\app\env\lib\site-packages\torch\nn\modules\module.py", line 1173, in to return self._apply(convert) File "f:\pinokio\api\comfyui.git\app\env\lib\site-packages\torch\nn\modules\module.py", line 779, in apply module.apply(fn) File "f:\pinokio\api\comfyui.git\app\env\lib\site-packages\torch\nn\modules\module.py", line 828, in _apply assert isinstance(param, Parameter)

Hello, I am getting this error.

RuntimeError: Given groups=1, weight of size [320, 4, 3, 3], expected input[1, 16, 512, 341] to have 4 channels, but got 16 channels instead

Any ideas on how to fix this? I'm not code savvy at all so doing anything like that is not possible for me.

Getting this error. not 100% sure how to fix this.

i ofc do read but not sure why it gives an error on this image. others seem to work fine

Error occurred when executing Image Crop Location: Invalid crop dimensions. Please check the values for top, left, right, and bottom.

This workflow is No.1!

Hello, I encountered this problem:

Please tell me how to solve this problem? Or where can I download this model and install it in which folder? Thank you so much

Error occurred when executing CLIPSeg Model Loader: HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /CIDAS/clipseg-rd64-refined/resolve/main/model.safetensors (Caused by ConnectTimeoutError(, 'Connection to huggingface.co timed out. (connect timeout=10)'))

I get the below error in KSampler as part of the "Destroy Clothes and Outline Body" section. Are the restrictions on the size of the source image or is it something else.

Error occurred when executing KSampler: mat1 and mat2 shapes cannot be multiplied (154x2048 and 768x320)

any help would be appreciated

When loading the graph, the following node types were not found:

SegsToCombinedMask

ToBinaryMask

BboxDetectorSEGS

SAMLoader

SAMDetectorCombined

UltralyticsDetectorProvider

MaskToSEGS

ImpactSEGSOrderedFilter

BitwiseAndMask

FromBasicPipe

SubtractMask

ToBasicPipe

PreviewBridge

ImpactDilateMask

Nodes that have failed to load will show as red on the graph.

Hey there, thanks for your work, this really does look amazing. I get an error everytime. I have the ultralytics models in their "ComfyUI\models\ultralytics" bbox and segm folders. I don't get why this is happening. Error:

Error occurred when executing UltralyticsDetectorProvider:

PytorchStreamReader failed reading zip archive: failed finding central directory

File "E:\UserLibrary\Desktop\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 "E:\UserLibrary\Desktop\ComfyUI\execution.py", line 191, in get_output_data

return_values = mapnode_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)

File "E:\UserLibrary\Desktop\ComfyUI\execution.py", line 168, in mapnode_over_list

process_inputs(input_dict, i)

File "E:\UserLibrary\Desktop\ComfyUI\execution.py", line 157, in process_inputs

results.append(getattr(obj, func)(**inputs))

File "E:\UserLibrary\Desktop\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\impact_subpack\impact\subpack_nodes.py", line 30, in doit

model = subcore.load_yolo(model_path)

File "E:\UserLibrary\Desktop\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\impact_subpack\impact\subcore.py", line 20, in load_yolo

return YOLO(model_path)

File "C:\Users\Usuario\AppData\Local\Programs\Python\Python310\lib\site-packages\ultralytics\models\yolo\model.py", line 23, in init

super().__init__(model=model, task=task, verbose=verbose)

File "C:\Users\Usuario\AppData\Local\Programs\Python\Python310\lib\site-packages\ultralytics\engine\model.py", line 143, in init

self._load(model, task=task)

File "C:\Users\Usuario\AppData\Local\Programs\Python\Python310\lib\site-packages\ultralytics\engine\model.py", line 295, in _load

self.model, self.ckpt = attempt_load_one_weight(weights)

File "C:\Users\Usuario\AppData\Local\Programs\Python\Python310\lib\site-packages\ultralytics\nn\tasks.py", line 855, in attempt_load_one_weight

ckpt, weight = torch_safe_load(weight) # load ckpt

File "C:\Users\Usuario\AppData\Local\Programs\Python\Python310\lib\site-packages\ultralytics\nn\tasks.py", line 781, in torch_safe_load

ckpt = torch.load(file, map_location="cpu")

File "C:\Users\Usuario\AppData\Local\Programs\Python\Python310\lib\site-packages\ultralytics\utils\patches.py", line 86, in torch_load

return torchload(*args, **kwargs)

File "C:\Users\Usuario\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\serialization.py", line 1229, in load

with openzipfile_reader(opened_file) as opened_zipfile:

File "C:\Users\Usuario\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\serialization.py", line 600, in init

super().__init__(torch._C.PyTorchFileReader(name_or_buffer))

I cant proceed after exclude hands group. The console says: "Invalid output..." anyone have this same problem? I press "queue prompt" but nothing happens, and in the terminal it appears: "Failed to validate prompt [number]"

i run the workflow and nothing happens, im not getting any mask outputs and the prompt just terminates after it loads some models.

got prompt

Loads SAM model: F:\stablediffusion\otheruis\ComfyUI_windows_portable\ComfyUI\models\sams\sam_vit_h_4b8939.pth (device:AUTO)

model weight dtype torch.float16, manual cast: None

model_type EPS

Using pytorch attention in VAE

Using pytorch attention in VAE

Using pytorch attention in VAE

Using pytorch attention in VAE

Requested to load SD1ClipModel

Loading 1 new model

loaded completely 0.0 235.84423828125 True

F:\stablediffusion\otheruis\ComfyUI_windows_portable\python_embeded\Lib\site-packages\huggingface_hub\file_download.py:1150: FutureWarning: resume_download is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use force_download=True.

warnings.warn(

Loads SAM model: F:\stablediffusion\otheruis\ComfyUI_windows_portable\ComfyUI\models\sams\sam_vit_b_01ec64.pth (device:AUTO)

Prompt executed in 52.91 seconds

any help would be very useful

It stops somewhere before "choose a skin color" / "generate body" sections as they are lacking previews.
Console:
got prompt

Loads SAM model: E:\ComfyUI_windows_portable\ComfyUI\models\sams\sam_vit_b_01ec64.pth (device:AUTO)

Loads SAM model: E:\ComfyUI_windows_portable\ComfyUI\models\sams\sam_vit_h_4b8939.pth (device:AUTO)

model weight dtype torch.float16, manual cast: None

model_type EPS

Using pytorch attention in VAE

Using pytorch attention in VAE

Using pytorch attention in VAE

Using pytorch attention in VAE

Requested to load SD1ClipModel

Loading 1 new model

loaded completely 0.0 235.84423828125 True

E:\ComfyUI_windows_portable\ComfyUI\comfy\ldm\modules\attention.py:407: UserWarning: 1Torch was not compiled with flash attention. (Triggered internally at ..\aten\src\ATen\native\transformers\cuda\sdp_utils.cpp:455.)

out = torch.nn.functional.scaled_dot_product_attention(q, k, v, attn_mask=mask, dropout_p=0.0, is_causal=False)

Prompt executed in 8.43 seconds

[INFO] ComfyUI-Impact-Pack: Loading SAM model 'E:\ComfyUI_windows_portable\ComfyUI\models'

[INFO] ComfyUI-Impact-Pack: SAM model loaded.

got prompt

model_path is E:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\ckpts\yzd-v/DWPose\yolox_l.onnx

model_path is E:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\ckpts\hr16/DWPose-TorchScript-BatchSize5\dw-ll_ucoco_384_bs5.torchscript.pt

DWPose: Using yolox_l.onnx for bbox detection and dw-ll_ucoco_384_bs5.torchscript.pt for pose estimation

DWPose: Caching OpenCV DNN module yolox_l.onnx on cv2.DNN...

DWPose: Caching TorchScript module dw-ll_ucoco_384_bs5.torchscript.pt on ...

DWPose: Bbox 2508.40ms

DWPose: Pose 219.08ms on 1 people

0: 640x512 1 person, 51.9ms

Speed: 4.0ms preprocess, 51.9ms inference, 17.0ms postprocess per image at shape (1, 3, 640, 512)

0: 640x512 1 face, 12.0ms

Speed: 2.0ms preprocess, 12.0ms inference, 1.0ms postprocess per image at shape (1, 3, 640, 512)

Unused or unrecognized kwargs: padding.

# of Detected SEGS: 1

Unused or unrecognized kwargs: padding.

0: 640x512 (no detections), 35.3ms

Speed: 2.5ms preprocess, 35.3ms inference, 0.0ms postprocess per image at shape (1, 3, 640, 512)

Requested to load AutoencoderKL

Loading 1 new model

loaded completely 0.0 319.11416244506836 True

Requested to load BaseModel

Requested to load ControlNet

Loading 2 new models

loaded completely 0.0 1639.406135559082 True

loaded completely 0.0 689.0852355957031 True

100%|██████████████████████████████████████████████████████████████████████████████████| 16/16 [00:03<00:00, 4.32it/s]

0: 640x512 1 person, 21.0ms

Speed: 2.0ms preprocess, 21.0ms inference, 2.0ms postprocess per image at shape (1, 3, 640, 512)

Unused or unrecognized kwargs: padding.

# of Detected SEGS: 1

# of Detected SEGS: 1

Unused or unrecognized kwargs: padding.

Unused or unrecognized kwargs: padding.

Unused or unrecognized kwargs: padding.

Unused or unrecognized kwargs: padding.

# of Detected SEGS: 1

Unused or unrecognized kwargs: padding.

# of Detected SEGS: 1

Prompt executed in 29.56 seconds

This custom node is truly amazing, effective, and powerful. I deeply respect the creator for such a remarkable achievement. I would even like to offer my personal support.

It would be greatly appreciated if you could develop an XL version or a Flux version as well

give me a way to get rid of the interference ...

No output in preview bridge. pls help

I followed installation steps and added resources aftwards aswell but there are still a lot of nodes missing. How should i proceed?

CLIPSeg Masking

Input image size (352*352) doesn't match model (224*224).

What does this mean?

[ONNXRuntimeError] : 1 : FAIL : TensorRT EP failed to create engine from network for fused node: TensorrtExecutionProvider_TRTKernel_graph_torch-jit-export_1210855768532638510_0_0

this is best, but can someone help me? I`m not mask a face but why the face its change, how to fix this

Many models have to be installed on top of it, namely stuff from adetailer

Also after many hours of debugging I have this error

RuntimeError: mat1 and mat2 shapes cannot be multiplied (154x2048 and 768x320)

Really i dont know how it work, preview image is always empty. only mask mask mask and nothing

12gb vram, but yet the workflow crashes at the ksampler at 'destroy clothes and outline body' section with the following error:
Warning: Ran out of memory when regular VAE encoding, retrying with tiled VAE encoding.

Requested to load BaseModel

Requested to load ControlNet

Loading 2 new models

loaded completely 0.0 1639.406135559082 True

loaded completely 0.0 689.0852355957031 True

0%| | 0/16 [00:00<?, ?it/s]

It gets stuck and won't progress. Can anybody help please? Thanks in advance.