TypeError: DoubleStreamBlock.forward() got an unexpected keyword argument 'attn_mask'

[pendave]

0%| | 0/20 [00:11<?, ?it/s]
!!! Exception during processing !!! DoubleStreamBlock.forward() got an unexpected keyword argument 'attn_mask'
Traceback (most recent call last):
File "E:\ComfyUI_Portable\ComfyUI\execution.py", line 328, in execute
output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, p
re_execute_cb=pre_execute_cb)
File "E:\ComfyUI_Portable\ComfyUI\execution.py", line 203, in get_output_data
return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=exec
ution_block_cb, pre_execute_cb=pre_execute_cb)
File "E:\ComfyUI_Portable\ComfyUI\execution.py", line 174, in map_node_over_list
process_inputs(input_dict, i)
File "E:\ComfyUI_Portable\ComfyUI\execution.py", line 163, in process_inputs
results.append(getattr(obj, func)(**inputs))
File "E:\ComfyUI_Portable\ComfyUI\nodes.py", line 1503, in sample
return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=d
enoise)
File "E:\ComfyUI_Portable\ComfyUI\nodes.py", line 1470, in common_ksampler
samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
File "E:\ComfyUI_Portable\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, disabl
e_pbar=disable_pbar, seed=seed)
File "E:\ComfyUI_Portable\ComfyUI\comfy\samplers.py", line 1013, in sample
return sample(self.model, noise, positive, negative, cfg, self.device, sampler, sigmas, self.model_options, latent_i
mage=latent_image, denoise_mask=denoise_mask, callback=callback, disable_pbar=disable_pbar, seed=seed)
File "E:\ComfyUI_Portable\ComfyUI\comfy\samplers.py", line 911, in sample
return cfg_guider.sample(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed)
File "E:\ComfyUI_Portable\ComfyUI\comfy\samplers.py", line 897, in sample
output = executor.execute(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed)
File "E:\ComfyUI_Portable\ComfyUI\comfy\patcher_extension.py", line 110, in execute
return self.original(*args, **kwargs)
File "E:\ComfyUI_Portable\ComfyUI\comfy\samplers.py", line 866, in outer_sample
output = self.inner_sample(noise, latent_image, device, sampler, sigmas, denoise_mask, callback, disable_pbar, seed)

File "E:\ComfyUI_Portable\ComfyUI\comfy\samplers.py", line 850, in inner_sample
samples = executor.execute(self, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
File "E:\ComfyUI_Portable\ComfyUI\comfy\patcher_extension.py", line 110, in execute
return self.original(*args, **kwargs)
File "E:\ComfyUI_Portable\ComfyUI\comfy\samplers.py", line 707, in sample
samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_
pbar, **self.extra_options)
File "E:\ComfyUI_Portable\python_embeded\Lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "E:\ComfyUI_Portable\ComfyUI\comfy\k_diffusion\sampling.py", line 155, in sample_euler
denoised = model(x, sigma_hat * s_in, **extra_args)
File "E:\ComfyUI_Portable\ComfyUI\comfy\samplers.py", line 379, in call
out = self.inner_model(x, sigma, model_options=model_options, seed=seed)
File "E:\ComfyUI_Portable\ComfyUI\comfy\samplers.py", line 832, in call
return self.predict_noise(*args, **kwargs)
File "E:\ComfyUI_Portable\ComfyUI\comfy\samplers.py", line 835, 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 "E:\ComfyUI_Portable\ComfyUI\comfy\samplers.py", line 359, in sampling_function
out = calc_cond_batch(model, conds, x, timestep, model_options)
File "E:\ComfyUI_Portable\ComfyUI\comfy\samplers.py", line 195, in calc_cond_batch
return executor.execute(model, conds, x_in, timestep, model_options)
File "E:\ComfyUI_Portable\ComfyUI\comfy\patcher_extension.py", line 110, in execute
return self.original(*args, **kwargs)
File "E:\ComfyUI_Portable\ComfyUI\comfy\samplers.py", line 308, in calc_cond_batch
output = model.apply_model(input_x, timestep, **c).chunk(batch_chunks)
File "E:\ComfyUI_Portable\ComfyUI\comfy\model_base.py", line 129, in apply_model
return comfy.patcher_extension.WrapperExecutor.new_class_executor(
File "E:\ComfyUI_Portable\ComfyUI\comfy\patcher_extension.py", line 110, in execute
return self.original(*args, **kwargs)
File "E:\ComfyUI_Portable\ComfyUI\comfy\model_base.py", line 158, in _apply_model
model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options
, **extra_conds).float()
File "E:\ComfyUI_Portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_im
pl
return self._call_impl(*args, **kwargs)
File "E:\ComfyUI_Portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "E:\ComfyUI_Portable\ComfyUI\comfy\ldm\flux\model.py", line 204, in forward
out = self.forward_orig(img, img_ids, context, txt_ids, timestep, y, guidance, control, transformer_options, attn_ma
sk=kwargs.get("attention_mask", None))
File "E:\ComfyUI_Portable\ComfyUI\comfy\ldm\flux\model.py", line 143, in forward_orig
img, txt = block(img=img,
File "E:\ComfyUI_Portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_im
pl
return self._call_impl(*args, **kwargs)
File "E:\ComfyUI_Portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
TypeError: DoubleStreamBlock.forward() got an unexpected keyword argument 'attn_mask'

[craftogrammer]

I am also getting the same issue.

!!! Exception during processing !!! DoubleStreamBlock.forward() got an unexpected keyword argument 'attn_mask' Traceback (most recent call last): File "D:\ComfyUI\execution.py", line 328, 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 "D:\ComfyUI\execution.py", line 203, in get_output_data return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\execution.py", line 174, in _map_node_over_list process_inputs(input_dict, i) File "D:\ComfyUI\execution.py", line 163, in process_inputs results.append(getattr(obj, func)(**inputs)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\comfy_extras\nodes_custom_sampler.py", line 633, in sample samples = guider.sample(noise.generate_noise(latent), latent_image, sampler, sigmas, denoise_mask=noise_mask, callback=callback, disable_pbar=disable_pbar, seed=noise.seed) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\comfy\samplers.py", line 897, in sample output = executor.execute(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\comfy\patcher_extension.py", line 110, in execute return self.original(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\comfy\samplers.py", line 866, in outer_sample output = self.inner_sample(noise, latent_image, device, sampler, sigmas, denoise_mask, callback, disable_pbar, seed) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\comfy\samplers.py", line 850, in inner_sample samples = executor.execute(self, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\comfy\patcher_extension.py", line 110, in execute return self.original(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\comfy\samplers.py", line 707, 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\venv\Lib\site-packages\torch\utils\_contextlib.py", line 116, in decorate_context return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\comfy\k_diffusion\sampling.py", line 1098, in sample_deis denoised = model(x_cur, t_cur * s_in, **extra_args) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\comfy\samplers.py", line 379, in __call__ out = self.inner_model(x, sigma, model_options=model_options, seed=seed) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\comfy\samplers.py", line 832, in __call__ return self.predict_noise(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\comfy\samplers.py", line 835, 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:\ComfyUI\comfy\samplers.py", line 359, in sampling_function out = calc_cond_batch(model, conds, x, timestep, model_options) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\comfy\samplers.py", line 195, in calc_cond_batch return executor.execute(model, conds, x_in, timestep, model_options) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\comfy\patcher_extension.py", line 110, in execute return self.original(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\comfy\samplers.py", line 308, in _calc_cond_batch output = model.apply_model(input_x, timestep_, **c).chunk(batch_chunks) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\comfy\model_base.py", line 130, in apply_model return comfy.patcher_extension.WrapperExecutor.new_class_executor( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\comfy\patcher_extension.py", line 110, in execute return self.original(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\comfy\model_base.py", line 159, in _apply_model model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds).float() ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\venv\Lib\site-packages\torch\nn\modules\module.py", line 1739, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\venv\Lib\site-packages\torch\nn\modules\module.py", line 1750, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\venv\Lib\site-packages\torch\_dynamo\eval_frame.py", line 576, in _fn return fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\venv\Lib\site-packages\torch\nn\modules\module.py", line 1739, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\venv\Lib\site-packages\torch\nn\modules\module.py", line 1750, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\comfy\ldm\flux\model.py", line 189, in forward def forward(self, x, timestep, context, y, guidance, control=None, transformer_options={}, **kwargs): File "D:\ComfyUI\comfy\ldm\flux\model.py", line 143, in forward_orig img, txt = block(img=img, ^^^^^^^^^^^^^^ File "D:\ComfyUI\venv\Lib\site-packages\torch\nn\modules\module.py", line 1739, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI\venv\Lib\site-packages\torch\nn\modules\module.py", line 1750, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ TypeError: DoubleStreamBlock.forward() got an unexpected keyword argument 'attn_mask'

[rollingcookies]

Same problem! Recently updated Comfy, maybe it is connected with it?

[Moxie1776]

Following, same.

[h3clikejava]

same

[vmasrani]

same

[africa1207]

same here

[dxdpxl]

exactly the same

[dxdpxl]

A reset to ComfyUI v.3.0.7 with "git checkout v0.3.7" inside the lower comfyui folder and we can continue using x-flux. Thanks to the guys who posted the solution in a ComfyUI-PuLID-Flux-Enhanced issue thread. Hope they will fix it soon!

[mayo-Z]

same

[adgbit]

@dxdpxl Thanks Man for Share

[amirabbbbas]

Here's the option in the comfyui for downgrading to 0.3.7 which solved the problem

[pendave]

Here's the option in the comfyui for downgrading to 0.3.7 which solved the problem

How could I let "Switch ComfyUI" displayed?

[dxdpxl]

How could I let "Switch ComfyUI" displayed?

I don't know about your question, maybe this future is only available in the latest version of comfyui...

but to get you to downgrade comyfui, do the following:
fully close comfyui and go into your lower comfyui folder "X:\ComfyUI\ComfyUI" (while X is the drive where you installed it), now left-click into the adressbar of the ComfyUI folder and write "cmd" and press enter (without quotation marks), in the following opened cmd window enter "git checkout v0.3.7" (again without quotation marks) and press enter, wait until its finished, voila comfyui is downgraded.

[pendave]

How could I let "Switch ComfyUI" displayed?

I don't know about your question, maybe this future is only available in the latest version of comfyui...

but to get you to downgrade comyfui, do the following: fully close comfyui and go into your lower comfyui folder (note lowercase letters), left-click into the adressbar of the comfyui folder and write "cmd" and press enter (without quotation marks), in the following opened cmd window enter "git checkout v0.3.7" (again without quotation marks) and press enter, wait until its finished, voila comfyui is downgraded.

Actually I updated ComfyUI version to the latest:

Loading: ComfyUI-Manager (V2.55.4)

ComfyUI Version: v0.3.10-35-g916d1e1 | Released on '2025-01-06'

But I can't find the lower comfyui folder, you can see that above.

[dxdpxl]

You are already in the right folder "E:\ComfyUI\ComfyUI"

Sorry for the confusion, mine is only lowercase, I don't know why, but I will correct my advice.

[pendave]

You are already in the right folder "E:\ComfyUI\ComfyUI"

Sorry for the confusion, mine is only lowercase, I don't know why, but I will correct my advice.

I always execute CMD that way. But

E:\ComfyUI_Portable\ComfyUI>git checkout v0.3.7
error: Your local changes to the following files would be overwritten by checkout:
folder_paths.py
Please commit your changes or stash them before you switch branches.
Aborting

E:\ComfyUI_Portable\ComfyUI>

Maybe I could download V0.3.7 from ComfyUI Release https://github.com/comfyanonymous/ComfyUI/releases and put it another path, then mklink and share the models etc. resources from the E:\ComfyUI_Portable one. Hope the coder fixes the bug in the future.

[dxdpxl]

I always execute CMD that way.

Sorry then i can't help, I don't know anything about this error. I attached a photo of what it should look like...

[amirabbbbas]

Here's the option in the comfyui for downgrading to 0.3.7 which solved the problem

How could I let "Switch ComfyUI" displayed?

First Update all and choose every update option that you see , restart and then the option will appear for you

[dxdpxl]

I always execute CMD that way.

Did you edited/changed anything inside the folder_paths.py?

Maybe try to delete (backup!) the problematic file...
Then cmd run git reset --hard and after that the checkout again

[Aloukik21]

any good solution yet?

[ryujongsu]

I did Update ComplyUI and it was solved.

[rollingcookies]

I did Update ComplyUI and it was solved.

What version/commit did you upgrade to?

[dxdpxl]

I did Update ComplyUI and it was solved.

No it's not solved! It happens with every version above 0.3.7! I update daily to test it.

Seems like this Git is dead and won't get any updates...

[adgbit]

Sorry so much I know this is GitHub no Twitter but....... Generally, it's virtually impossible to be productive with UncomfyUI. As an artist, I understand that programs like HoudiniFX, Maya, Nuke, and Flame are complex, but this UncomfyUI nightmare makes no sense. There are too many technical hurdles to overcome just to create a single image; something is always broken. Most artists rely on a tech-savvy person to set up the workflow. No matter what you do with cfgs, Denoise, IPAdapter, ControlNet, or how well you think you understand it, you'll spend countless hours and days trying to achieve anything. It's completely illogical.

[rollingcookies]

Sorry so much I know this is GitHub no Twitter but....... Generally, it's virtually impossible to be productive with UncomfyUI. As an artist, I understand that programs like HoudiniFX, Maya, Nuke, and Flame are complex, but this UncomfyUI nightmare makes no sense. There are too many technical hurdles to overcome just to create a single image; something is always broken. Most artists rely on a tech-savvy person to set up the workflow. No matter what you do with cfgs, Denoise, IPAdapter, ControlNet, or how well you think you understand it, you'll spend countless hours and days trying to achieve anything. It's completely illogical.

Another fighter has given up :')