Відео

Amazing. Thanks very much!!

Thx man ! it works great.

useless guide

Hace you thought About rag for images?

hello, just wondering if you got a chance to update the workflow? :)

Thank you so much for sharing! Brilliant workflow. However, some remarks not only for this specific video> IF-AI is very hard to get running. In general, almost every comfyui workflow is followed by the repeated install of 5 different versions of pytorchxformersollamawhatever and half day is gone trying to get the environment to work with 90% of workflows unusable with only manager installs etc.I would suggest to really standardize ComfyUI environments or provide yaml files to download e.g. conda env configs directly. Otherwise a good setup tutorial would be very appreciated.

very cool, is this workflow to download? to try it?

Thank you. gracias. IT WORKED

Well, and what about simple way to use this model? Code in github is difficult, is there example with using something like pipelines?

How does this stand up to Tripo?

Thanks a lot. Lots of useful tips here. Managed to fix loads of error with this video 😄

¿Qué specs tienes?

Looks like this extension not works with Forge + Memory alert for video card.. Can you fix it? Maybe switch to CPU generation..

how can i use this without second control net options? i wanna just use random promts

the manager doesnt fix the missing nodes :(

Would you be able to add batch for image captioning? That would be amazing for datasets, especially with the tag functionality to have the model edit the entire dataset caption files once output with consistent keywords across the dataset

How do you make the files point to that folder ?

works great!...thank You for the instructions*

hello again, i dont see a field for passing documents in the IF Chat Prompt. The extension is up to date

You are awesome.

i got same thin lips model everytime i use musetalk. how to change the lips model like yours?

I'll be honest. I see no use for this. It seem like there are simpler tools to achieve the same thing

very informative except the anime character jerking off the whole time

thx ... error ?! Error occurred when executing CRMPoseSampler: The shape of the 2D attn_mask is torch.Size([77, 77]), but should be (1, 1). File "F:\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_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_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_windows_portable\ComfyUI\custom_nodes\ComfyUI-Flowty-CRMOLD\__init__.py", line 81, in sample self.initialized_poser = get_obj_from_str(stage1_sampler_config.target)( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Flowty-CRMOLD\crmlib\libs\sample.py", line 32, in __init__ uc = model.get_learned_conditioning([neg_texts]).to(device) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Flowty-CRMOLD\crmlib\imagedream\ldm\interface.py", line 183, in get_learned_conditioning return self.clip_model(prompts) ^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch n\modules\module.py", line 1532, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch n\modules\module.py", line 1541, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Flowty-CRMOLD\crmlib\imagedream\ldm\modules\encoders\modules.py", line 218, in forward z = self.encode_with_transformer(tokens.to(self.device)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Flowty-CRMOLD\crmlib\imagedream\ldm\modules\encoders\modules.py", line 282, in encode_with_transformer x = self.text_transformer_forward(x, attn_mask=self.model.attn_mask) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Flowty-CRMOLD\crmlib\imagedream\ldm\modules\encoders\modules.py", line 297, in text_transformer_forward x = r(x, attn_mask=attn_mask) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch n\modules\module.py", line 1532, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch n\modules\module.py", line 1541, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\open_clip\transformer.py", line 263, in forward x = q_x + self.ls_1(self.attention(q_x=self.ln_1(q_x), k_x=k_x, v_x=v_x, attn_mask=attn_mask)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\open_clip\transformer.py", line 250, in attention return self.attn( ^^^^^^^^^^ File "F:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch n\modules\module.py", line 1532, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch n\modules\module.py", line 1541, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch n\modules\activation.py", line 1266, in forward attn_output, attn_output_weights = F.multi_head_attention_forward( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch n\functional.py", line 5382, in multi_head_attention_forward raise RuntimeError(f"The shape of the 2D attn_mask is {attn_mask.shape}, but should be {correct_2d_size}.")

Hello I get this error : Error occurred when executing CRMPoseSampler: on the pixel sampler anyway to fix it? I have the correct pixel model

The UI of the huggingface demo is way simpler and easier to understand. Is there any way to download and use that UI instead of comfyui?

Hello there, i was wondering if this RAG system could work for captioning dataset images for training with a personal caption style (specific terms I will later use in prompting). I can see your tool allows the use of a txt file to guide inference). Bot sure how to implement batching for all the images in the dataset to be processed

cool , sir!

hi the IF_ChatPrompt node is not showing

Running Omost from Ollama is much faster, thanks for great work! And I didn't catch yet all difference between those 4 versions of output in right, would you please share the workflow?

Great info!

Awesome, I really wanted to try this one but did not have the time to install it...this is the waaaay easier method now! 🤗 Is it really producing better results, or do you think that regular prompting gives the same quality?

Cool addition! Eager to get home and test it!

hey man! thanks for the info! unfortunately, I have been unable to get any textures? I mean everything inside comfyui is fine but for some reason, I can't export textures out of comfyui. any solutions or guide? am I missing something?

how do you see in comparison with idm-Vton in terms of performance?

I keep getting error messages on preview image... "'str' object has no attribute 'shape'"

I am currently using alltalk to create bio's for characters in a guild and for story telling, I have wav and mp3 files of those speech files. I also have an image for what the narrator looks like. Am i right in thinking i can plug that into the dreamtalk node to have it create the avatar speaking the words ? if so, can it change the emotion on the face based on the current line (most audio is around 5 minutes long, so one emotion may look strange). Reluctant to install and try as currently i have a llm node so wondering if thier will be clashes (I used Plush-for-comfy as i can feed the instruction in as text which helps guide what i expect from the prompt.) On a side note, i didnt realise whisper could be used to generate speech, as i say i use alltalk for that, but its interesting.

To install MMlab packages and resolve the "The OSError: [WinError 126] The specified module could not be found" error,

i have NVIDIA GeForce RTX 3070 Ti Laptop GPU..... will it work for me? even if its slow?

Thank you! ) That was I searching ! )

Thanks for this integration, it works great.

SICK~!!

Thanks for making comfy ui better, really game changer nodes

Can I use this to animate just the face on a existing video instead of a still like wav2lip? If not do you have other recommendations better than wav2lip?

Hi bro. how can i apply his if im working from runpod enviroment? can you please help. would appreciate.

How to run Higging Face Download node. I create and fill it and what next?

i´m using the portable version of ComfyUI and it gives me the following error pls help! When loading the graph, the following node types were not found: IF_DreamTalk Nodes that have failed to load will show as red on the graph