I' would try it Thanks!

If you use
my generated images for your workflow, thats OK... BUT you should and
could !! have asked BEFORE !! using instead of just doing it and adding a
lame disclaimer to avoid trouble. Bye now. END.

Hi there, i would love to try out this workflow but it keeps give me same error Error occurred when executing StyleModelApply: Sizes of tensors must match except in dimension 1. Expected size 1280 but got size 1024 for tensor number 1 in the list.  Im sorry for this newb question but, how can i fix it?

   x = torch.cat([x, style_embedding], dim=1)

RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 1280 but got size 1024 for tensor number 1 in the lis

t.

Prompt executed in 5.38 seconds

Prompt executed in 5.38 seconds

Holy moly, this is some crazy comfy magic! Amazing work friend!

I also encountered a "Sizes of tensors……" error, but when I removed the relevant modules such as “apply style model ”from the workflow and re-enabled IPAdapter, it worked correctly.

So I created a new workflow and applied the relevant modules such as“ apply style model ”to the most basic txt2img. It's still not working.

I switched to a few more cloud environments to run the simplest txt2img workflow with “style model”. It still doesn't work.

As you can see, the error is in the "apply style model" node.

Is there any chance you could, or have, develop a similar outpainting workflow for SDXL checkpoints? Those are what I like to work with most often. Thank you

Hi, Amazing workflow, sometimes the colors next to the edges doesn't follow them. is there a setting to increase value to follow more those edge pixels

PS nyone else is loading the workflow and is set in other language?? how can i fix this without remaking all the nodes and switching them?

I have this error with "timestep_kf' with the apply control net, do you know where it comes from ?

work great and fast, thanks bro!

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

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

why error?

Error occurred when executing StyleModelApply: Sizes of tensors must match except in dimension 1. Expected size 1280 but got size 1024 for tensor number 1 in the list. File "F:\Blender_ComfyUI\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "F:\Blender_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 "F:\Blender_ComfyUI\ComfyUI\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) File "F:\Blender_ComfyUI\ComfyUI\nodes.py", line 937, in apply_stylemodel cond = style_model.get_cond(clip_vision_output).flatten(start_dim=0, end_dim=1).unsqueeze(dim=0) File "F:\Blender_ComfyUI\ComfyUI\comfy\sd.py", line 341, in get_cond return self.model(input.last_hidden_state) File "F:\Blender_ComfyUI\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "F:\Blender_ComfyUI\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl return forward_call(*args, **kwargs) File "F:\Blender_ComfyUI\ComfyUI\comfy\t2i_adapter\adapter.py", line 214, in forward x = torch.cat([x, style_embedding], dim=1)

where i can download control_v11p_sd15_inpaint.pth file?

repair edges group not active and preview of that not show anything have anyone this problem?

have any sugesstion?

ipadapter has updated ，Apply IPAdapter node not work

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

• IPAdapterTilesMasked

working. It's a bit flawed, but I love it!

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

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

Only one side using the coadapter-Style version is available and the other side reports an error, which is hard for people with OCD.

Error prompted:Error occurred when executing ACN_AdvancedControlNetApply: AdvancedControlNetApply.apply_controlnet() got an unexpected keyword argument 'timestep_kf' File "D:\program files\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\program files\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:\program files\ComfyUI_windows_portable\ComfyUI\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

Apply Style Model error