Brilliant idea

牛的。

Pretty fun stuff.

Could you upload the face2.mp4 to let me try the Live Portrait‘s result?

能不能一次只生成一张图，生成4张会爆显存，批次设置成1后会报错，怎么修改？

多年前追的网黄开始进军openart，感动

老板口中的“给我打印一张gif图”

face2.m p4   ？

太帮了，我跑的效果很好

Unfortunately, I don't understand what I have to connect to the single version.

!!! Exception during processing!!! Sizes of tensors must match except in dimension 2. Expected size 120 but got size 109 for tensor number 1 in the list.

Traceback (most recent call last):

 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\ComfyUI-KJNodes\nodes\image_nodes.py", line 1288, in combine

   image, = ImageConcanate.concanate(self, image, new_image, direction, match_image_size, first_image_shape=first_image_shape)

 File "D:\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-KJNodes\nodes\image_nodes.py", line 257, in concanate

   concatenated_image = torch.cat((image1, image2_resized), dim=2)  # Concatenate along width

RuntimeError: Sizes of tensors must match except in dimension 2. Expected size 120 but got size 109 for tensor number 1 in the list.

Have you solved it? I also encountered the same problem.

!!! Exception during processing!!! Sizes of tensors must match except in dimension 2. Expected size 120 but got size 109 for tensor number 1 in the list.

为啥四张图片都是一个表情呢

为什么我跑出来的效果没办法像up一样摇头晃脑啊，只能做到眼部和嘴部的变化，自己录的视频是有的

WHAT IS THE PROBLEM?

Prompt outputs failed validation ImageConcatMulti: - Return type mismatch between linked nodes: image_1, LP_OUT != IMAGE - Return type mismatch between linked nodes: image_2, LP_OUT != IMAGE ImageConcatMulti: - Return type mismatch between linked nodes: image_1, LP_OUT != IMAGE - Return type mismatch between linked nodes: image_2, LP_OUT != IMAGE

WITH : PULID-CPU

Error occurred when executing ApplyPulid: No operator found for `memory_efficient_attention_forward` with inputs: query : shape=(1, 577, 16, 64) (torch.float16) key : shape=(1, 577, 16, 64) (torch.float16) value : shape=(1, 577, 16, 64) (torch.float16) attn_bias :
p : 0.0
`decoderF` is not supported because:
xFormers wasn't build with CUDA support
attn_bias type is
operator wasn't built - see `python -m xformers.info` for more info
`flshattF@0.0.0` is not supported because:
xFormers wasn't build with CUDA support
operator wasn't built - see `python -m xformers.info` for more info
`cutlassF` is not supported because:
xFormers wasn't build with CUDA support
operator wasn't built - see `python -m xformers.info` for more info
`smallkF` is not supported because:
max(query.shape[-1] != value.shape[-1]) > 32
xFormers wasn't build with CUDA support
dtype=torch.float16 (supported: {torch.float32})
has custom scale
operator wasn't built - see `python -m xformers.info` for more info
unsupported embed per head: 64

File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 152, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\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 "D:\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 "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\PuLID_ComfyUI\pulid.py", line 383, in apply_pulid
id_cond_vit, id_vit_hidden = eva_clip(face_features_image, return_all_features=False, return_hidden=True, shuffle=False)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\PuLID_ComfyUI\eva_clip\eva_vit_model.py", line 544, in forward
x, hidden_states = self.forward_features(x, return_all_features, return_hidden, shuffle)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\PuLID_ComfyUI\eva_clip\eva_vit_model.py", line 531, in forward_features
x = blk(x, rel_pos_bias=rel_pos_bias)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\PuLID_ComfyUI\eva_clip\eva_vit_model.py", line 293, in forward
x = x + self.drop_path(self.attn(self.norm1(x), rel_pos_bias=rel_pos_bias, attn_mask=attn_mask))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\PuLID_ComfyUI\eva_clip\eva_vit_model.py", line 208, in forward
x = xops.memory_efficient_attention(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\xformers\ops\fmha\__init__.py", line 268, in memory_efficient_attention
return _memory_efficient_attention(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\xformers\ops\fmha\__init__.py", line 387, in _memory_efficient_attention
return _memory_efficient_attention_forward(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\xformers\ops\fmha\__init__.py", line 403, in _memory_efficient_attention_forward
op = _dispatch_fw(inp, False)
^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\xformers\ops\fmha\dispatch.py", line 125, in _dispatch_fw
return _run_priority_list(
^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\xformers\ops\fmha\dispatch.py", line 65, in _run_priority_list
raise NotImplementedError(msg)

WITH: PULID CUDA

return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\PuLID_ComfyUI\eva_clip\eva_vit_model.py", line 293, in forward x = x + self.drop_path(self.attn(self.norm1(x), rel_pos_bias=rel_pos_bias, attn_mask=attn_mask)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\PuLID_ComfyUI\eva_clip\eva_vit_model.py", line 208, in forward x = xops.memory_efficient_attention( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\xformers\ops\fmha\__init__.py", line 268, in memory_efficient_attention return _memory_efficient_attention( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\xformers\ops\fmha\__init__.py", line 387, in _memory_efficient_attention return _memory_efficient_attention_forward( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\xformers\ops\fmha\__init__.py", line 403, in _memory_efficient_attention_forward op = _dispatch_fw(inp, False) ^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\xformers\ops\fmha\dispatch.py", line 125, in _dispatch_fw return _run_priority_list( ^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\xformers\ops\fmha\dispatch.py", line 65, in _run_priority_list raise NotImplementedError(msg)

This is an excellent concept - but...

There is a huge amount of unnecessary nodes here.

One Huge change I made was to remove the comfyui-ollama node - this is a huge waste of resource.  I replaced it with WAS Node Suite's "BLIP Analyze Image" - it does exactly the same thing without the need to run a separate application.

Issues I found (not blaming the Dev, this was probably due to ComfyUI changes):

• No guide on how to install InstanID correctly
• No guide on how to install PuLID correctly
• The Seed input was missing - So I added a Seed Generator node
• "Use Everywhere" doesn't work.

I also think "InstantID" and "PuLID" is also unnecessary as "IPAdapter Plus" does all of this natively.  But I haven't tested this yet.

Overall quite good - but it did take over 4hrs to get working after fixing all the issues, and removing redundant and unnecessary nodes

Error occurred when executing PulidEvaClipLoader: An error happened while trying to locate the file on the Hub and we cannot find the requested files in the local cache. Please check your connection and try again or make sure your Internet connection is on. File "G:\ComfyUI-aki-v1.3\execution.py", line 152, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "G:\ComfyUI-aki-v1.3\execution.py", line 82, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) File "G:\ComfyUI-aki-v1.3\execution.py", line 70, in map_node_over_list results.append(getattr(obj, func)()) File "G:\ComfyUI-aki-v1.3\custom_nodes\PuLID_ComfyUI\pulid.py", line 259, in load_eva_clip model, _, _ = create_model_and_transforms('EVA02-CLIP-L-14-336', 'eva_clip', force_custom_clip=True) File "G:\ComfyUI-aki-v1.3\custom_nodes\PuLID_ComfyUI\eva_clip\factory.py", line 377, in create_model_and_transforms model = create_model( File "G:\ComfyUI-aki-v1.3\custom_nodes\PuLID_ComfyUI\eva_clip\factory.py", line 279, in create_model checkpoint_path = download_pretrained(pretrained_cfg, cache_dir=cache_dir) File "G:\ComfyUI-aki-v1.3\custom_nodes\PuLID_ComfyUI\eva_clip\pretrained.py", line 328, in download_pretrained target = download_pretrained_from_hf(model_id, filename=filename, cache_dir=cache_dir) File "G:\ComfyUI-aki-v1.3\custom_nodes\PuLID_ComfyUI\eva_clip\pretrained.py", line 300, in download_pretrained_from_hf cached_file = hf_hub_download(model_id, filename, revision=revision, cache_dir=cache_dir) File "G:\ComfyUI-aki-v1.3\python\lib\site-packages\huggingface_hub\utils\_validators.py", line 118, in _inner_fn return fn(*args, **kwargs) File "G:\ComfyUI-aki-v1.3\python\lib\site-packages\huggingface_hub\file_download.py", line 1371, in hf_hub_download raise LocalEntryNotFoundError(                      这个应该怎么解决啊

Error occurred when executing ApplyPulid: 'ModelPatcher' object has no attribute 'get_model_object'    求解

why my mask parts are only white or grey color?

does anyone succeed? I can not use it ,always error occurred

单人版有参考图？

How are you doing

how much vram we need ?