Hey, can you help me? i'm having this problem with ipa unified loader "IPAdapterUnifiedLoader IPAdapter model not found." and i use comfyui manager, and instaled the clips from there, but still with this error.
im getting "Exception during processing!!! Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!" but i got 4060ti / 32gb ram... what can i do???
Easy to follow and greatly explained. However my question is: in this case you got a picture and a sketch combined, so the IPadapter only resulted in a merge of both. What if I don't load any picture as reference and I only want the model to interpret the prompts and the sketch? Would that work, or do I need a secondary image as a reference? In addition, can I load loras from the prompts directly into the generation?
hi, amazing tutorial, Please make a video on how to transfer style, color grading, and tone from one portrait to another without changing subject (person)
Honestly, In my workflow I couldn't really work well with these images and the IPAdapter, it was all working correctly but I couldn't really understand what the second image was doing, when I bypassed that part it was still kinda of the same image. However, the scribbles controlnet was a really good thing to find out, I thought the best controlnet for me would be the anime lineart or something similiar to help me with drawing but the scribbles does it 100x times better. Thank you so much!
Wait, Load advanced controlnet model will find whatever model you put in models/controlnet/ no matter the name, it is IPAdapterUnifiedLoader that needs you to rename the models you put in models\ipadapter!
@@DreamingAIChannel gotcha, I did end up getting the correct files I believe, I got openpose and scribble, but I now run into another error when trying to use control net Any ideas?? "Error occurred when executing KSampler: mat1 and mat2 shapes cannot be multiplied (154x2048 and 768x320) File "D:\Program Files\SDXL\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
![Coding an Anime Chatbot: A Journey with LLaMA 3 [Ollama + Chat Interface]](http://i.ytimg.com/vi/z8khiyUxxPU/mqdefault.jpg)
![Coding an Anime Chatbot: A Journey with LLaMA 3 [Ollama + Chat Interface]](/img/tr.png)
![[Full Episode] The Restaurant War Thailand ศึกพ่อค้าซ่าแม่ค้าแซ่บ Episode 2 | 29 ก.ย. 67](http://i.ytimg.com/vi/r3lfLNH6Ke4/mqdefault.jpg)
Hey, can you help me? i'm having this problem with ipa unified loader "IPAdapterUnifiedLoader
IPAdapter model not found." and i use comfyui manager, and instaled the clips from there, but still with this error.
Amazing tutorial as usual! Thanks!
im getting "Exception during processing!!! Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!"
but i got 4060ti / 32gb ram... what can i do???
Easy to follow and greatly explained. However my question is: in this case you got a picture and a sketch combined, so the IPadapter only resulted in a merge of both. What if I don't load any picture as reference and I only want the model to interpret the prompts and the sketch? Would that work, or do I need a secondary image as a reference? In addition, can I load loras from the prompts directly into the generation?
Do you offer workflows with your membership? I would love a workflow with this setup but with a flux model
i couldnt make this ipadapter model works = ( for some reason, it doent find the, for example, plus high strengh
How to install that searching menu? i can't find a node well.
thank you
Thx
hi, amazing tutorial, Please make a video on how to transfer style, color grading, and tone from one portrait to another without changing subject (person)
Cool.what is that node browser extension you have on the left side?
Hi! It's my new ComfyUI extension, you can download it here github.com/Nuked88/ComfyUI-N-Sidebar
@@DreamingAIChannel thanks, that's a great extension!
Thank you ❤️
@@DreamingAIChannel You should submit that to Comfy UI Manager!
@HumanGamer It's already there! :P
Really good workflows!!
Honestly, In my workflow I couldn't really work well with these images and the IPAdapter, it was all working correctly but I couldn't really understand what the second image was doing, when I bypassed that part it was still kinda of the same image.
However, the scribbles controlnet was a really good thing to find out, I thought the best controlnet for me would be the anime lineart or something similiar to help me with drawing but the scribbles does it 100x times better. Thank you so much!
For the first time I was able to understand a full ConfyUI tutorial. Thank you.
I renamed the clip visions but for some reason load advanced controlnet model doesnt find them
Wait, Load advanced controlnet model will find whatever model you put in models/controlnet/ no matter the name, it is IPAdapterUnifiedLoader that needs you to rename the models you put in models\ipadapter!
@@DreamingAIChannel gotcha, I did end up getting the correct files I believe, I got openpose and scribble, but I now run into another error when trying to use control net
Any ideas??
"Error occurred when executing KSampler:
mat1 and mat2 shapes cannot be multiplied (154x2048 and 768x320)
File "D:\Program Files\SDXL\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^