Getting thiis error! in my comfy UI while running it on RunPod. Can you please guide Warning: Missing Node Types When loading the graph, the following node types were not found: easy imageRemBg ImageResize+ UltimateSDUpscale UpscaleModelLoader easy ipadapterApply No selected item Nodes that have failed to load will show as red on the graph.
Excellent video Kazi A few quick questions: 1. How would you size/scale the image to be in proportion to the background scene? I tried a simple positive prompt: dark city street of london, street lamps The outcome was my model being the same size as the street lights. 2. How can you incorporate your image so it seamlessly blends into your background without it looking like a cut out? Have you managed to incorporate depth, xyz positioning, shadows and or dimensions (e.g 3D)? I'd be keen to see your workflow. Thank you and keep up the good work!
I have experienced the scale and proportion issue. I haven't figured out a way to tackle that yet. I will do some more experiments this week, and try to improve on the workflow. As for blending the background, you gotta tweak the settings a bit, use mask blur, adjust sigma values etc. The workflow isn't perfect yet for production level work, it's very basic right now, for experimenting with ideas and brainstorming. You brought some valid points in the conversation, thank you for that! 🙌🏽
@kaziahmed excellent answers. I appreciate your cadidness. Yes please look into it. I'm not designing anything for production - I'm just a bit of a perfectionist :)
How would i do if i want the foreground object to have some changes too? i.e in your shoe example, i might want to add a bit of dirt and dust to them, and change their color. How would that be done in this workflow? Right now i can't do any changes to foreground object
The portable Comfyui which you installed has already a python in it's package. So is there a special reason you also installing python again seperately?
Hi buddy. thanks for your effort. But I couldn't see the workflow json file anywhere. There is only a png image in the link you gave. Didn't I see this json?
You need to install the extra nodes like KJNodes and LayerDiffuse. The links are in the video description. Also make sure you download the correct model files for IC Light.
@@Adi3DPro You need to install the extra nodes like KJNodes and LayerDiffuse. The links are in the video description. Also make sure you download the correct model files for IC Light.
My implementation of your workflow keeps dying on the KSampler node - "Error occurred when executing KSampler:vGiven groups=1, weight of size [320, 12, 3, 3], expected input[2, 8, 128, 128] to have 12 channels, but got 8 channels instead" Any ideas? I'd love to give this one a try, thanks for making the video for us!
@alexisnik135 please check the video description. The IC light node installation is a bit tricky… you need to install layer diffuse and kjnodes. And for the ic light models don’t download them from comfyui manager, use the huggingface files link that I provided. It will work. Also, the workflow is for SD1.5
Very good video. Thank you. I tried to install everything by you explanation. My workflow stops at background replacement. It is empty. Do you know why?
You might be missing one of the custom nodes that's required for IC-Light. Make sure you have KJNodes and Layerdiffuse installed. Also, check the file names and locations from my video, it's a bit tricky. A few others on my fb had a similar issue, it was resolved by installing this node: github.com/huchenlei/ComfyUI-layerdiffuse
Ok I got Solution the problem I was facing is related to (ComfyUI-layerdiffuse), I was trying to install by cmd, but it was not working same error so Solution for me is I have install (ComfyUI-layerdiffuse) Manually by download zip file then extract then restart and yes its working great thanks bro for ur help its so amazing ❤❤❤❤❤❤❤❤❤❤❤❤🩹❤🩹❤🩹❤🩹❤🩹❤🩹
Try doing a fresh install of comfyUI in a seperate folder. Then make sure you install all the missing nodes plus KJNodes and LayerDiffuse Node. The others who had this issue were able to simply solve it by doing this. Also for the IC Light models use the Huggingface link I provided.
Great video!! please make more videos about product photography.
Definitely, will do! 🙌
I really like your videos!!!!!
Thank you 🙌🏽🙌🏽
Superb strategies ❤
Thank you :)
Getting thiis error! in my comfy UI while running it on RunPod. Can you please guide
Warning: Missing Node Types
When loading the graph, the following node types were not found:
easy imageRemBg
ImageResize+
UltimateSDUpscale
UpscaleModelLoader
easy ipadapterApply
No selected item
Nodes that have failed to load will show as red on the graph.
Excellent video Kazi
A few quick questions:
1. How would you size/scale the image to be in proportion to the background scene?
I tried a simple positive prompt: dark city street of london, street lamps
The outcome was my model being the same size as the street lights.
2. How can you incorporate your image so it seamlessly blends into your background without it looking like a cut out?
Have you managed to incorporate depth, xyz positioning, shadows and or dimensions (e.g 3D)?
I'd be keen to see your workflow.
Thank you and keep up the good work!
I have experienced the scale and proportion issue. I haven't figured out a way to tackle that yet. I will do some more experiments this week, and try to improve on the workflow.
As for blending the background, you gotta tweak the settings a bit, use mask blur, adjust sigma values etc. The workflow isn't perfect yet for production level work, it's very basic right now, for experimenting with ideas and brainstorming. You brought some valid points in the conversation, thank you for that! 🙌🏽
@kaziahmed excellent answers. I appreciate your cadidness.
Yes please look into it. I'm not designing anything for production - I'm just a bit of a perfectionist :)
Thanks ❤
You're wecome :)
How would i do if i want the foreground object to have some changes too? i.e in your shoe example, i might want to add a bit of dirt and dust to them, and change their color. How would that be done in this workflow? Right now i can't do any changes to foreground object
That can be achieved by adding a custom mask to the input image.
thx sir!
you're welcome 🙌🏽🙌🏽
How to do it if i have background already
how to save your workflow on github , create it, and also upload to huggingface ? thanks
Workflow's link has just the screenshoot picture of workflow. But not the download option for the workflow. Can you please check?
As I mentioned in the video, the png file has the json embedded in it. Simply drag and drop the image into your ComfyUI and it will work. 🙌🏽🙌🏽
The portable Comfyui which you installed has already a python in it's package. So is there a special reason you also installing python again seperately?
Some users had a issue with the python not being added to the environment variable path, that's why I showed that.
Hi buddy. thanks for your effort. But I couldn't see the workflow json file anywhere. There is only a png image in the link you gave. Didn't I see this json?
The png file has the json embedded in it. Just drag and drop it in comfyUI.
@@kaziahmed oh okeyyy i understand. Thank you bro :)
@@skozaa1 You're welcome bro!
Thanks for the workflow Kazi. I'm getting a black halo around my image after the detailer is applied. Anyway to get rid of this black halo?
You have to adjust the mask and blur. Also try adjusting the sigma value.
@@kaziahmedThanks! I’ll try that!
Error occurred when executing KSampler:
Given groups=1, weight of size [320, 4, 3, 3], expected input[2, 8, 128, 128] to have 4 channels, but got 8 channels instead
File "L:\-work\-ai\ComfyUI\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\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 "L:\-work\-ai\ComfyUI\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI
odes.py", line 1371, in sample
return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI
odes.py", line 1341, in common_ksampler
samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI\comfy\sample.py", line 43, 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 "L:\-work\-ai\ComfyUI\ComfyUI\comfy\samplers.py", line 795, 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 "L:\-work\-ai\ComfyUI\ComfyUI\comfy\samplers.py", line 697, in sample
return cfg_guider.sample(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI\comfy\samplers.py", line 684, in sample
output = self.inner_sample(noise, latent_image, device, sampler, sigmas, denoise_mask, callback, disable_pbar, seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI\comfy\samplers.py", line 663, in inner_sample
samples = sampler.sample(self, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI\comfy\samplers.py", line 568, in sample
samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **self.extra_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\python_embeded\Lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI\comfy\k_diffusion\sampling.py", line 635, in sample_dpmpp_2m_sde
denoised = model(x, sigmas[i] * s_in, **extra_args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI\comfy\samplers.py", line 291, in __call__
out = self.inner_model(x, sigma, model_options=model_options, seed=seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI\comfy\samplers.py", line 650, in __call__
return self.predict_noise(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI\comfy\samplers.py", line 653, 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 "L:\-work\-ai\ComfyUI\ComfyUI\comfy\samplers.py", line 277, in sampling_function
out = calc_cond_batch(model, conds, x, timestep, model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI\comfy\samplers.py", line 224, in calc_cond_batch
output = model_options['model_function_wrapper'](model.apply_model, {"input": input_x, "timestep": timestep_, "c": c, "cond_or_uncond": cond_or_uncond}).chunk(batch_chunks)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI\custom_nodes\ComfyUI-IC-Light-Native\ic_light_nodes.py", line 116, in wrapper_func
return existing_wrapper(unet_apply, params=apply_c_concat(params))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI\custom_nodes\ComfyUI-IC-Light-Native\ic_light_nodes.py", line 108, in unet_dummy_apply
return unet_apply(x=params["input"], t=params["timestep"], **params["c"])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI\comfy\model_base.py", line 113, in apply_model
model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds).float()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\python_embeded\Lib\site-packages\torch
n\modules\module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\python_embeded\Lib\site-packages\torch
n\modules\module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 852, in forward
h = forward_timestep_embed(module, h, emb, context, transformer_options, time_context=time_context, num_video_frames=num_video_frames, image_only_indicator=image_only_indicator)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 50, in forward_timestep_embed
x = layer(x)
^^^^^^^^
File "L:\-work\-ai\ComfyUI\python_embeded\Lib\site-packages\torch
n\modules\module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\python_embeded\Lib\site-packages\torch
n\modules\module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI\comfy\ops.py", line 80, in forward
return super().forward(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\python_embeded\Lib\site-packages\torch
n\modules\conv.py", line 460, in forward
return self._conv_forward(input, self.weight, self.bias)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\python_embeded\Lib\site-packages\torch
n\modules\conv.py", line 456, in _conv_forward
return F.conv2d(input, weight, bias, self.stride,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
I am getting this error any help bro?
You need to install the extra nodes like KJNodes and LayerDiffuse. The links are in the video description. Also make sure you download the correct model files for IC Light.
@@Adi3DPro You need to install the extra nodes like KJNodes and LayerDiffuse. The links are in the video description. Also make sure you download the correct model files for IC Light.
My implementation of your workflow keeps dying on the KSampler node - "Error occurred when executing KSampler:vGiven groups=1, weight of size [320, 12, 3, 3], expected input[2, 8, 128, 128] to have 12 channels, but got 8 channels instead" Any ideas? I'd love to give this one a try, thanks for making the video for us!
Nevermind! After a bunch of random refreshes it works now - thank you!
@@Coalbanksco Glad it worked out! I know the setup can be a bit painful, but once all the pieces fall into places it works perfectly :)
@@kaziahmed having this exact same issue as well at first i though it was the sdxl model but it doesn'r work on sd 1.5 either
@alexisnik135 please check the video description. The IC light node installation is a bit tricky… you need to install layer diffuse and kjnodes. And for the ic light models don’t download them from comfyui manager, use the huggingface files link that I provided. It will work.
Also, the workflow is for SD1.5
Very good video. Thank you. I tried to install everything by you explanation. My workflow stops at background replacement. It is empty. Do you know why?
You might be missing one of the custom nodes that's required for IC-Light. Make sure you have KJNodes and Layerdiffuse installed.
Also, check the file names and locations from my video, it's a bit tricky. A few others on my fb had a similar issue, it was resolved by installing this node: github.com/huchenlei/ComfyUI-layerdiffuse
@@kaziahmed I had the same problem, in others workflows, but this helped me a lot. Thanks a lot bro.
@@ImagindeDash You're welcome bro 🙌🏽🙌🏽
How can I export my comfyui workflow as png, so I can load from png image as you make your file
I used a custom node, here's the link: github.com/pythongosssss/ComfyUI-Custom-Scripts?tab=readme-ov-file#workflow-images
Still Getting this
I tried again from start to end
---------
Error occurred when executing KSampler:
Given groups=1, weight of size [320, 4, 3, 3], expected input[2, 8, 128, 128] to have 4 channels, but got 8 channels instead
File "L:\-work\-ai\ComfyUI\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\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 "L:\-work\-ai\ComfyUI\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI
odes.py", line 1371, in sample
return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI
odes.py", line 1341, in common_ksampler
samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI\comfy\sample.py", line 43, 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 "L:\-work\-ai\ComfyUI\ComfyUI\comfy\samplers.py", line 795, 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 "L:\-work\-ai\ComfyUI\ComfyUI\comfy\samplers.py", line 697, in sample
return cfg_guider.sample(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI\comfy\samplers.py", line 684, in sample
output = self.inner_sample(noise, latent_image, device, sampler, sigmas, denoise_mask, callback, disable_pbar, seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI\comfy\samplers.py", line 663, in inner_sample
samples = sampler.sample(self, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI\comfy\samplers.py", line 568, in sample
samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **self.extra_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\python_embeded\Lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI\comfy\k_diffusion\sampling.py", line 635, in sample_dpmpp_2m_sde
denoised = model(x, sigmas[i] * s_in, **extra_args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI\comfy\samplers.py", line 291, in __call__
out = self.inner_model(x, sigma, model_options=model_options, seed=seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI\comfy\samplers.py", line 650, in __call__
return self.predict_noise(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI\comfy\samplers.py", line 653, 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 "L:\-work\-ai\ComfyUI\ComfyUI\comfy\samplers.py", line 277, in sampling_function
out = calc_cond_batch(model, conds, x, timestep, model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI\comfy\samplers.py", line 224, in calc_cond_batch
output = model_options['model_function_wrapper'](model.apply_model, {"input": input_x, "timestep": timestep_, "c": c, "cond_or_uncond": cond_or_uncond}).chunk(batch_chunks)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI\custom_nodes\ComfyUI-IC-Light-Native\ic_light_nodes.py", line 116, in wrapper_func
return existing_wrapper(unet_apply, params=apply_c_concat(params))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI\custom_nodes\ComfyUI-IC-Light-Native\ic_light_nodes.py", line 108, in unet_dummy_apply
return unet_apply(x=params["input"], t=params["timestep"], **params["c"])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI\comfy\model_base.py", line 113, in apply_model
model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds).float()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\python_embeded\Lib\site-packages\torch
n\modules\module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\python_embeded\Lib\site-packages\torch
n\modules\module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 852, in forward
h = forward_timestep_embed(module, h, emb, context, transformer_options, time_context=time_context, num_video_frames=num_video_frames, image_only_indicator=image_only_indicator)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 50, in forward_timestep_embed
x = layer(x)
^^^^^^^^
File "L:\-work\-ai\ComfyUI\python_embeded\Lib\site-packages\torch
n\modules\module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\python_embeded\Lib\site-packages\torch
n\modules\module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\ComfyUI\comfy\ops.py", line 80, in forward
return super().forward(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\python_embeded\Lib\site-packages\torch
n\modules\conv.py", line 460, in forward
return self._conv_forward(input, self.weight, self.bias)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "L:\-work\-ai\ComfyUI\python_embeded\Lib\site-packages\torch
n\modules\conv.py", line 456, in _conv_forward
return F.conv2d(input, weight, bias, self.stride,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Ok I got Solution the problem I was facing is related to (ComfyUI-layerdiffuse), I was trying to install by cmd, but it was not working same error
so Solution for me is I have install (ComfyUI-layerdiffuse) Manually by download zip file then extract then restart and yes its working great
thanks bro for ur help its so amazing
❤❤❤❤❤❤❤❤❤❤❤❤🩹❤🩹❤🩹❤🩹❤🩹❤🩹
Try doing a fresh install of comfyUI in a seperate folder. Then make sure you install all the missing nodes plus KJNodes and LayerDiffuse Node. The others who had this issue were able to simply solve it by doing this.
Also for the IC Light models use the Huggingface link I provided.
@@kaziahmed Thanks Working Great
how you fix this issue? i have same problem with you
@@panonesia you have to install the extra nodes. specially KJNodes in comfyUI.