Comments (31)
The fix was luckily very simple and is now merged into AnimateDiff-Evolved. Update AnimateDiff-Evolved, and the issue should be fixed. Let me know if it works now!
Kosinkadink/ComfyUI-AnimateDiff-Evolved#319
from comfyui.
A few seconds ago I pushed an update that should fix it - see if it works now. The change in ComfyUI code meant that any time a model containing AD would get unloaded, it didn't have the code to accept a new keyword parameter that ComfyUI does now when it unpatches and it would throw that error.
Kosinkadink/ComfyUI-AnimateDiff-Evolved#321
from comfyui.
I got the same issue. patch_model()
definitely accepts patch_weights
so I'm very confused what causes this. Waiting for a solution.
from comfyui.
File "D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\comfy\model_patcher.py", line 225, in patch_model_lowvram
self.patch_model(device_to, patch_weights=False)
TypeError: ModelPatcherAndInjector.patch_model() got an unexpected keyword argument 'patch_weights'
I am getting this too, when I use animatediff with controlnets
from comfyui.
I dunno I am still getting this error after I updated everything. First updated using comfy manager and then manually downloaded the model_injection.py and replaced it in my comfyUI folder.
The prompt will run to 100% done then error out. It definitely goes further than what I got as of yesterday though, which is it errors out before it even gets me to 0%. I'm almost thinking I should do a clean reinstall of comfy and see if it helps.
Error occurred when executing VAEDecode:
ModelPatcherAndInjector.unpatch_model() got an unexpected keyword argument 'unpatch_weights'
File "F:\comfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\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 "F:\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 "F:\comfyUI\ComfyUI_windows_portable\ComfyUI\nodes.py", line 288, in decode
return (vae.decode(samples["samples"]), )
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\comfyUI\ComfyUI_windows_portable\ComfyUI\comfy\sd.py", line 285, in decode
model_management.load_models_gpu([self.patcher], memory_required=memory_used)
File "F:\comfyUI\ComfyUI_windows_portable\ComfyUI\comfy\model_management.py", line 409, in load_models_gpu
free_memory(total_memory_required[device] * 1.3 + extra_mem, device, models_already_loaded)
File "F:\comfyUI\ComfyUI_windows_portable\ComfyUI\comfy\model_management.py", line 361, in free_memory
m.model_unload()
File "F:\comfyUI\ComfyUI_windows_portable\ComfyUI\comfy\model_management.py", line 312, in model_unload
self.model.unpatch_model(self.model.offload_device, unpatch_weights=unpatch_weights)
from comfyui.
Can confirm, I just updated everything after not doing so for a while and while the first gen works correctly, trying to start another results in the unpatch_weights error. To the best of my knowledge I am not using lowvram mode though oO
from comfyui.
@Kosinkadink, I do like @molkemon, the same problem also occurs. What is strange is that it only happens at the first queue prompt. Each time not works, I have to restart it.
cmd: clear && python main.py --use-split-cross-attention --force-fp16
error:
Exception in thread Thread-3 (prompt_worker):
Traceback (most recent call last):
File "/root/miniconda3/lib/python3.10/threading.py", line 1016, in _bootstrap_inner
self.run()
File "/root/miniconda3/lib/python3.10/threading.py", line 953, in run
self._target(*self._args, **self._kwargs)
File "/root/autodl-tmp/ComfyUI/main.py", line 111, in prompt_worker
e.execute(item[2], prompt_id, item[3], item[4])
File "/root/autodl-tmp/ComfyUI/custom_nodes/rgthree-comfy/init.py", line 209, in rgthree_execute
return self.rgthree_old_execute(*args, **kwargs)
File "/root/autodl-tmp/ComfyUI/execution.py", line 371, in execute
comfy.model_management.cleanup_models()
File "/root/autodl-tmp/ComfyUI/comfy/model_management.py", line 451, in cleanup_models
x.model_unload()
File "/root/autodl-tmp/ComfyUI/comfy/model_management.py", line 312, in model_unload
self.model.unpatch_model(self.model.offload_device, unpatch_weights=unpatch_weights)
TypeError: ModelPatcherAndInjector.unpatch_model() got an unexpected keyword argument 'unpatch_weights'
from comfyui.
It seems to be working now for me, thanks for the fast fix :)
from comfyui.
After trying to update comfyUI and animatediff it finally worked now! No more error yay!
from comfyui.
@semaster the error you're getting is actually a bug in ComfyUI with one of the recent updates. LCM + latent batch of greater than 1 no longer works (AKA, AnimateDiff LCM will not work). comfy has been alerted to the issue, so there should hopefully be a ComfyUI update soon to fix it.
from comfyui.
@semaster the error you're getting is actually a bug in ComfyUI with one of the recent updates. LCM + latent batch of greater than 1 no longer works (AKA, AnimateDiff LCM will not work). comfy has been alerted to the issue, so there should hopefully be a ComfyUI update soon to fix it.
I get that error too, when I switch off LCM Animatediff works fine, hope I'll fix it soon.
from comfyui.
Error occurred when executing KSampler:
ModelPatcherAndInjector.unpatch_model() got an unexpected keyword argument 'unpatch_weights'
what's wrong? thankU
from comfyui.
Traceback (most recent call last):
File "/content/drive/MyDrive/ComfyUI/execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "/content/drive/MyDrive/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 "/content/drive/MyDrive/ComfyUI/execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "/content/drive/MyDrive/ComfyUI/nodes.py", line 1403, in sample
return common_ksampler(model, noise_seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise, disable_noise=disable_noise, start_step=start_at_step, last_step=end_at_step, force_full_denoise=force_full_denoise)
File "/content/drive/MyDrive/ComfyUI/nodes.py", line 1339, in common_ksampler
samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
File "/content/drive/MyDrive/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 "/content/drive/MyDrive/ComfyUI/custom_nodes/ComfyUI-AnimateDiff-Evolved (1)/animatediff/sampling.py", line 346, in motion_sample
latents = wrap_function_to_inject_xformers_bug_info(orig_comfy_sample)(model, noise, *args, **kwargs)
File "/content/drive/MyDrive/ComfyUI/custom_nodes/ComfyUI-AnimateDiff-Evolved (1)/animatediff/utils_model.py", line 360, in wrapped_function
return function_to_wrap(*args, **kwargs)
File "/content/drive/MyDrive/ComfyUI/custom_nodes/ComfyUI-AnimateDiff-Evolved/animatediff/sampling.py", line 267, in motion_sample
return orig_comfy_sample(model, noise, *args, **kwargs)
File "/content/drive/MyDrive/ComfyUI/comfy/sample.py", line 93, in sample
real_model, positive_copy, negative_copy, noise_mask, models = prepare_sampling(model, noise.shape, positive, negative, noise_mask)
File "/content/drive/MyDrive/ComfyUI/comfy/sample.py", line 86, in prepare_sampling
comfy.model_management.load_models_gpu([model] + models, model.memory_required([noise_shape[0] * 2] + list(noise_shape[1:])) + inference_memory)
File "/content/drive/MyDrive/ComfyUI/comfy/model_management.py", line 436, in load_models_gpu
cur_loaded_model = loaded_model.model_load(lowvram_model_memory)
File "/content/drive/MyDrive/ComfyUI/comfy/model_management.py", line 302, in model_load
self.model_unload()
File "/content/drive/MyDrive/ComfyUI/comfy/model_management.py", line 312, in model_unload
self.model.unpatch_model(self.model.offload_device, unpatch_weights=unpatch_weights)
TypeError: ModelPatcherAndInjector.unpatch_model() got an unexpected keyword argument 'unpatch_weights'
I have the newest version of Comfy and Animatediff on Colab
from comfyui.
@wordbrew uninstall ComfyUI-AnimateLCM. AnimateDiff-Evolved already supports LCM, and that repo is a copy of my code, including class names, which is why it conflicts with AnimateDiff-Evolved.
from comfyui.
I'm facing the same issue, and it has to be with the fact we are using vram state set to LOW_VRAM
but solved (for now) by cloning the repo in a new empty folder and then revert it to the last working commit (eda8704)
like this:
git clone https://github.com/comfyanonymous/ComfyUI
cd ComfyUI
git reset --hard eda8704
Then if you are using the ComfyUI_windows_portable version (like me) copy and replace the files in the "ComfyUI" folder inside "ComfyUI_windows_portable" with all the files just downloaded.
And don't update ComfyUI until issue is closed.
from comfyui.
Got the same issue, but unfortunately I cannot go back to the older version as suggested by @ernestleft because then I get the following:
Kosinkadink/ComfyUI-Advanced-ControlNet#84
from comfyui.
I am also getting this error:
executing KSamplerAdvanced:
ModelPatcherAndInjector.patch_model() got an unexpected keyword argument 'patch_weights'
File "D:\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:\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:\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:\New\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1403, in sample
return common_ksampler(model, noise_seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise, disable_noise=disable_noise, start_step=start_at_step, last_step=end_at_step, force_full_denoise=force_full_denoise)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\New\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1339, in common_ksampler
samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\New\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-AnimateDiff-Evolved\animatediff\sampling.py", line 346, in motion_sample
latents = wrap_function_to_inject_xformers_bug_info(orig_comfy_sample)(model, noise, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\New\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-AnimateDiff-Evolved\animatediff\utils_model.py", line 360, in wrapped_function
return function_to_wrap(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\New\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\comfy\sample.py", line 93, in sample
real_model, positive_copy, negative_copy, noise_mask, models = prepare_sampling(model, noise.shape, positive, negative, noise_mask)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\New\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\comfy\sample.py", line 86, in prepare_sampling
comfy.model_management.load_models_gpu([model] + models, model.memory_required([noise_shape[0] * 2] + list(noise_shape[1:])) + inference_memory)
File "D:\New\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\comfy\model_management.py", line 407, in load_models_gpu
cur_loaded_model = loaded_model.model_load(lowvram_model_memory)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\New\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\comfy\model_management.py", line 300, in model_load
raise e
File "D:\New\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\comfy\model_management.py", line 294, in model_load
self.real_model = self.model.patch_model_lowvram(device_to=patch_model_to, lowvram_model_memory=lowvram_model_memory)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\New\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\comfy\model_patcher.py", line 225, in patch_model_lowvram
self.patch_model(device_to, patch_weights=False)
I tried going into the file and changing the patch_weights to True and then to false and tested both but still kept getting errors
from comfyui.
ModelPatcherAndInjector is an AnimateDiff-Evolved thing, not native to ComfyUI. Based on your error logs, it looks like a change is needed to work with patch_model_lowvram.
I didn't see this until kust now after I noticed Kaszana referencing the issue in Advanced-ControlNet. I didnt get any report about lowvram not working after the ComfyUI changes, so I assumed there were none. I'll look into it this week.
from comfyui.
Works now! Thank you!
from comfyui.
Can you please advise a newbie and how to upgrade on windows? Just in the folder with ComfyUI use git pull?
Or apparently use update_comfyui.bat
from comfyui.
Can you please advise a newbie and how to upgrade on windows? Just in the folder with ComfyUI use git pull? Or apparently use update_comfyui.bat
You can update it via the manager
from comfyui.
Looks like ComfyUI had a new update 12 hours ago that I will need to make changes to account for, which is why you got the unpatch_weights missing thing.
To update a node pack, you can do so the easiest by using the Manager, or git pulling inside the directory of the specific custom_nodes subfolder.
from comfyui.
RuntimeError: The size of tensor a (67) must match the size of tensor b (12) at non-singleton dimension 3
from comfyui.
I don't think the error you're getting there is relevant to the changes above - the changes don't affect tensor sizes.
from comfyui.
sry it was just last line. Full error is like:
Traceback (most recent call last):
File "d:\ComfyUI_containers\ComfyUI_cu121\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "d:\ComfyUI_containers\ComfyUI_cu121\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_containers\ComfyUI_cu121\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "d:\ComfyUI_containers\ComfyUI_cu121\ComfyUI\nodes.py", line 1403, in sample
return common_ksampler(model, noise_seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise, disable_noise=disable_noise, start_step=start_at_step, last_step=end_at_step, force_full_denoise=force_full_denoise)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "d:\ComfyUI_containers\ComfyUI_cu121\ComfyUI\nodes.py", line 1339, in common_ksampler
samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_containers\ComfyUI_cu121\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\sample_error_enhancer.py", line 22, in informative_sample
raise e
File "D:\ComfyUI_containers\ComfyUI_cu121\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:\ComfyUI_containers\ComfyUI_cu121\ComfyUI\custom_nodes\ComfyUI-AnimateDiff-Evolved\animatediff\sampling.py", line 365, in motion_sample
latents = wrap_function_to_inject_xformers_bug_info(orig_comfy_sample)(model, noise, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_containers\ComfyUI_cu121\ComfyUI\custom_nodes\ComfyUI-AnimateDiff-Evolved\animatediff\utils_model.py", line 377, in wrapped_function
return function_to_wrap(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "d:\ComfyUI_containers\ComfyUI_cu121\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 "d:\ComfyUI_containers\ComfyUI_cu121\ComfyUI\comfy\samplers.py", line 704, 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:\ComfyUI_containers\ComfyUI_cu121\ComfyUI\comfy\samplers.py", line 609, in sample
samples = sampler.sample(model_wrap, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "d:\ComfyUI_containers\ComfyUI_cu121\ComfyUI\comfy\samplers.py", line 548, 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:\ComfyUI_containers\ComfyUI_cu121\python_embeded\Lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "d:\ComfyUI_containers\ComfyUI_cu121\ComfyUI\comfy\k_diffusion\sampling.py", line 751, in sample_lcm
x = model.inner_model.inner_model.model_sampling.noise_scaling(sigmas[i + 1] * s_in, noise_sampler(sigmas[i], sigmas[i + 1]), x)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "d:\ComfyUI_containers\ComfyUI_cu121\ComfyUI\comfy\model_sampling.py", line 18, in noise_scaling
noise = noise * sigma
~~~~~~^~~~~~~
RuntimeError: The size of tensor a (67) must match the size of tensor b (12) at non-singleton dimension 3
from comfyui.
This error is entirely unrelated to the one mentioned here. You can open up a new issue on AnimateDiff-Evolved, where you can also post a screenshot of your workflow.
from comfyui.
@Uemuet your AnimateDiff-Evolved is still outdated
from comfyui.
Error occurred when executing KSampler:
ModelPatcherAndInjector.unpatch_model() got an unexpected keyword argument 'unpatch_weights'
what's wrong? thankU
same issue here when running segsdetailerforAnimatediff.
of Detected SEGS: 1
model_type EPS
Using xformers attention in VAE
Using xformers attention in VAE
clip missing: ['clip_l.logit_scale', 'clip_l.transformer.text_projection.weight']
loaded straight to GPU
Requested to load BaseModel
Loading 1 new model
[AnimateDiffEvo] - INFO - Loading motion module v3_sd15_mm.ckpt
Using xformers attention in VAE
Using xformers attention in VAE
Requested to load SD1ClipModel
Loading 1 new model
Detailer: segment upscale for ((172, 234)) | crop region (516, 702) x 1.094894413258487 -> (564, 768)
Requested to load AutoencoderKL
Loading 1 new model
[AnimateDiffEvo] - INFO - Sliding context window activated - latents passed in (45) greater than context_length 16.
[AnimateDiffEvo] - INFO - Using motion module v3_sd15_mm.ckpt:v3.
Requested to load BaseModel
Requested to load AnimateDiffModel
Loading 2 new models
!!! Exception during processing !!!
Traceback (most recent call last):
File "C:\Downloads\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\comfy\model_management.py", line 299, in model_load
self.real_model = self.model.patch_model(device_to=patch_model_to, patch_weights=load_weights)
TypeError: ModelPatcherAndInjector.patch_model() got an unexpected keyword argument 'patch_weights'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "C:\Downloads\ComfyUI_windows_portable_nvidia_cu118_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 "C:\Downloads\ComfyUI_windows_portable_nvidia_cu118_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 "C:\Downloads\ComfyUI_windows_portable_nvidia_cu118_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 "C:\Downloads\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\animatediff_nodes.py", line 92, in doit
segs, cnet_images = SEGSDetailerForAnimateDiff.do_detail(image_frames, segs, guide_size, guide_size_for, max_size, seed, steps, cfg, sampler_name,
File "C:\Downloads\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\animatediff_nodes.py", line 69, in do_detail
enhanced_image_tensor, cnet_images = core.enhance_detail_for_animatediff(cropped_image_frames, model, clip, vae, guide_size, guide_size_for, max_size,
File "C:\Downloads\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\core.py", line 407, in enhance_detail_for_animatediff
refined_latent = impact_sampling.ksampler_wrapper(model, seed, steps, cfg, sampler_name, scheduler, positive, negative,
File "C:\Downloads\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\impact_sampling.py", line 125, in ksampler_wrapper
refined_latent = nodes.KSampler().sample(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise * sigma_factor)[0]
File "C:\Downloads\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1369, in sample
return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
File "C:\Downloads\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1339, in common_ksampler
samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
File "C:\Downloads\ComfyUI_windows_portable_nvidia_cu118_or_cpu\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 "C:\Downloads\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-AnimateLCM\animatediff\sampling.py", line 334, in motion_sample
latents = wrap_function_to_inject_xformers_bug_info(orig_comfy_sample)(model, noise, *args, **kwargs)
File "C:\Downloads\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-AnimateLCM\animatediff\utils_model.py", line 272, in wrapped_function
return function_to_wrap(*args, **kwargs)
File "C:\Downloads\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-AnimateDiff-Evolved\animatediff\sampling.py", line 267, in motion_sample
return orig_comfy_sample(model, noise, *args, **kwargs)
File "C:\Downloads\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\comfy\sample.py", line 93, in sample
real_model, positive_copy, negative_copy, noise_mask, models = prepare_sampling(model, noise.shape, positive, negative, noise_mask)
File "C:\Downloads\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\comfy\sample.py", line 86, in prepare_sampling
comfy.model_management.load_models_gpu([model] + models, model.memory_required([noise_shape[0] * 2] + list(noise_shape[1:])) + inference_memory)
File "C:\Downloads\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\comfy\model_management.py", line 436, in load_models_gpu
cur_loaded_model = loaded_model.model_load(lowvram_model_memory)
File "C:\Downloads\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\comfy\model_management.py", line 302, in model_load
self.model_unload()
File "C:\Downloads\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\comfy\model_management.py", line 312, in model_unload
self.model.unpatch_model(self.model.offload_device, unpatch_weights=unpatch_weights)
TypeError: ModelPatcherAndInjector.unpatch_model() got an unexpected keyword argument 'unpatch_weights'
from comfyui.
I'm getting the error now as well. Fresh Comfy install too. Less than a week. Went in and foolishly updated custom nodes today and now this:
Error occurred when executing KSampler Adv. (Efficient): ModelPatcherAndInjector.unpatch_model() got an unexpected keyword argument 'unpatch_weights' File "C:\SD\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\SD\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:\SD\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:\SD\ComfyUI_windows_portable\ComfyUI\custom_nodes\efficiency-nodes-comfyui\efficiency_nodes.py", line 2206, in sample_adv return super().sample(model, noise_seed, steps, cfg, sampler_name, scheduler, positive, negative, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\SD\ComfyUI_windows_portable\ComfyUI\custom_nodes\efficiency-nodes-comfyui\efficiency_nodes.py", line 713, in sample samples, images, gifs, preview = process_latent_image(model, seed, steps, cfg, sampler_name, scheduler, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\SD\ComfyUI_windows_portable\ComfyUI\custom_nodes\efficiency-nodes-comfyui\efficiency_nodes.py", line 537, in process_latent_image samples = KSamplerAdvanced().sample(model, add_noise, seed, steps, cfg, sampler_name, scheduler, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\SD\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1403, in sample return common_ksampler(model, noise_seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise, disable_noise=disable_noise, start_step=start_at_step, last_step=end_at_step, force_full_denoise=force_full_denoise) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\SD\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1339, in common_ksampler samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\SD\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 "C:\SD\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-AnimateLCM\animatediff\sampling.py", line 334, in motion_sample latents = wrap_function_to_inject_xformers_bug_info(orig_comfy_sample)(model, noise, *args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\SD\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-AnimateLCM\animatediff\utils_model.py", line 272, in wrapped_function return function_to_wrap(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\SD\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-AnimateDiff-Evolved\animatediff\sampling.py", line 267, in motion_sample return orig_comfy_sample(model, noise, *args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\SD\ComfyUI_windows_portable\ComfyUI\comfy\sample.py", line 93, in sample real_model, positive_copy, negative_copy, noise_mask, models = prepare_sampling(model, noise.shape, positive, negative, noise_mask) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\SD\ComfyUI_windows_portable\ComfyUI\comfy\sample.py", line 86, in prepare_sampling comfy.model_management.load_models_gpu([model] + models, model.memory_required([noise_shape[0] * 2] + list(noise_shape[1:])) + inference_memory) File "C:\SD\ComfyUI_windows_portable\ComfyUI\comfy\model_management.py", line 443, in load_models_gpu cur_loaded_model = loaded_model.model_load(lowvram_model_memory) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\SD\ComfyUI_windows_portable\ComfyUI\comfy\model_management.py", line 302, in model_load self.model_unload() File "C:\SD\ComfyUI_windows_portable\ComfyUI\comfy\model_management.py", line 312, in model_unload self.model.unpatch_model(self.model.offload_device, unpatch_weights=unpatch_weights)
from comfyui.
A few seconds ago I pushed an update that should fix it - see if it works now. The change in ComfyUI code meant that any time a model containing AD would get unloaded, it didn't have the code to accept a new keyword parameter that ComfyUI does now when it unpatches and it would throw that error.
Hi. Did ComfyUi do another update that broke this again? Was literally working for me last night and I updated nodes today and now am getting the error.
from comfyui.
Thank you, that did it! Too many nodes installed!
from comfyui.
Related Issues (20)
- Error when combining more than 2 models in fp8 HOT 2
- An error occurred while trying to execute the workflow:Node Type:** DWPreprocessor HOT 1
- Cuda error
- All Nodes Invisible, plus UI Froze when zooming out HOT 8
- CUDA ERROR HOT 2
- where is the dual text encoders of hunyuandit ? HOT 1
- If I add a checkpoint loader node and output only its clip output, will the unused parts take RAM/VRAM? HOT 2
- ComfyUI_Portable "Onnxruntime not found or doesn't come with acceleration providers" HOT 4
- A recent update causes OOM HOT 10
- DownloadAndLoadFlorence2Model cannot import name 'AutoConfig' from 'transformers' HOT 1
- Generating absurd amounts of the same over and over. [AFTER NEW UPDATE] HOT 2
- Error occurred when executing IPAdapterUnifiedLoader: ClipVision model not found HOT 7
- Add Option to Make Nodes Translucent HOT 2
- [Errno 2] No such file or directory
- CatVTONWrapper HOT 1
- Better Model Matching with SHA256 HOT 3
- Diffusers deprecated. ComfyUI doesn't auto-upgrade. MANY NODES CANNOT WORK HOT 1
- Random crashes using Latent2RGB preview method HOT 9
- cuda path error HOT 2
- CatVTONWrapper - Torch not compiled with CUDA enabled on Mac mini M2 Pro 32GB HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from comfyui.