Mickmumpitz patreon

[NEW VIDEO + WORKFLOWS] Make your own ANIME with this new mind-blowing AI TOOL!

🕑 Added 2024-06-19 11:16:48 +0000 UTC

Comments

T G

I was thinking the same thing, There are way to many dependencies that conflict with other nodes. I have been using Cursor to fix issues and get the Workflows working but that takes way to much time. I think I'm going to work on a packaging system for my own sanity.

Brandon Fowler

Man, I must say the couple of workflows I've tried so far don't work at all. I'm a 20 year veteran developer too (I'm no rookie) I'm a web developer with Chat GPT, and I believe these days with these AI workflows, the only way too do it almost is to package up an entire implementation of the version of ComfyUI, probably a Docker or some kind of containerized workflow. Because this has been days of trying to get your 3d Workflow to work. I meant to post this on the 3D Workflow. What a pain this has been. Lol, I only just yesterday got the nims to work from NVIDIA, and I'm running a 5090with 256 RAM. I tried launching it in the AI Workbench, and no go. I literally had to maneuver my way around workbench an do my own installation without it. I swear, AI models and workflows are way too new. It's like, a month after you publish something the whole entire environment is obsolete. That's why very few people are adopting it.

Mutant52

It would be great to get a version of these anime workflows updated similar to the consistent character ones. Currently it is a bit of a nightmare making anime in the other and this one doesn't have an image input for those of use with reference images.

m_sil

hello, I have this error when trying to run this workflow seems so close : FaceDetailer Could not run 'torchvision::nms' with arguments from the 'CUDA' backend. This could be because the operator doesn't exist for this backend, or was omitted during the selective/custom build process (if using custom build). If you are a Facebook employee using PyTorch on mobile, please visit https://fburl.com/ptmfixes for possible resolutions. 'torchvision::nms' is only available for these backends: [CPU, Meta, QuantizedCPU, BackendSelect, Python, FuncTorchDynamicLayerBackMode, Functionalize, Named, Conjugate, Negative, ZeroTensor, ADInplaceOrView, AutogradOther, AutogradCPU, AutogradCUDA, AutogradXLA, AutogradMPS, AutogradXPU, AutogradHPU, AutogradLazy, AutogradMeta, Tracer, AutocastCPU, AutocastXPU, AutocastMPS, AutocastCUDA, FuncTorchBatched, BatchedNestedTensor, FuncTorchVmapMode, Batched, VmapMode, FuncTorchGradWrapper, PythonTLSSnapshot, FuncTorchDynamicLayerFrontMode, PreDispatch, PythonDispatcher]. CPU: registered at C:\actions-runner\_work\vision\vision\pytorch\vision\torchvision\csrc\ops\cpu\nms_kernel.cpp:112 [kernel] Meta: registered at /dev/null:184 [kernel] QuantizedCPU: registered at C:\actions-runner\_work\vision\vision\pytorch\vision\torchvision\csrc\ops\quantized\cpu\qnms_kernel.cpp:124 [kernel] BackendSelect: fallthrough registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\core\BackendSelectFallbackKernel.cpp:3 [backend fallback] Python: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\core\PythonFallbackKernel.cpp:153 [backend fallback] FuncTorchDynamicLayerBackMode: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\functorch\DynamicLayer.cpp:497 [backend fallback] Functionalize: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\FunctionalizeFallbackKernel.cpp:349 [backend fallback] Named: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\core\NamedRegistrations.cpp:7 [backend fallback] Conjugate: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\ConjugateFallback.cpp:17 [backend fallback] Negative: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\NegateFallback.cpp:18 [backend fallback] ZeroTensor: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\ZeroTensorFallback.cpp:86 [backend fallback] ADInplaceOrView: fallthrough registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\core\VariableFallbackKernel.cpp:96 [backend fallback] AutogradOther: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\core\VariableFallbackKernel.cpp:63 [backend fallback] AutogradCPU: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\core\VariableFallbackKernel.cpp:67 [backend fallback] AutogradCUDA: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\core\VariableFallbackKernel.cpp:75 [backend fallback] AutogradXLA: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\core\VariableFallbackKernel.cpp:79 [backend fallback] AutogradMPS: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\core\VariableFallbackKernel.cpp:87 [backend fallback] AutogradXPU: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\core\VariableFallbackKernel.cpp:71 [backend fallback] AutogradHPU: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\core\VariableFallbackKernel.cpp:100 [backend fallback] AutogradLazy: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\core\VariableFallbackKernel.cpp:83 [backend fallback] AutogradMeta: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\core\VariableFallbackKernel.cpp:91 [backend fallback] Tracer: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\torch\csrc\autograd\TraceTypeManual.cpp:294 [backend fallback] AutocastCPU: registered at C:\actions-runner\_work\vision\vision\pytorch\vision\torchvision\csrc\ops\autocast\nms_kernel.cpp:34 [kernel] AutocastXPU: registered at C:\actions-runner\_work\vision\vision\pytorch\vision\torchvision\csrc\ops\autocast\nms_kernel.cpp:41 [kernel] AutocastMPS: fallthrough registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\autocast_mode.cpp:209 [backend fallback] AutocastCUDA: registered at C:\actions-runner\_work\vision\vision\pytorch\vision\torchvision\csrc\ops\autocast\nms_kernel.cpp:27 [kernel] FuncTorchBatched: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\functorch\LegacyBatchingRegistrations.cpp:731 [backend fallback] BatchedNestedTensor: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\functorch\LegacyBatchingRegistrations.cpp:758 [backend fallback] FuncTorchVmapMode: fallthrough registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\functorch\VmapModeRegistrations.cpp:27 [backend fallback] Batched: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\LegacyBatchingRegistrations.cpp:1075 [backend fallback] VmapMode: fallthrough registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\VmapModeRegistrations.cpp:33 [backend fallback] FuncTorchGradWrapper: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\functorch\TensorWrapper.cpp:207 [backend fallback] PythonTLSSnapshot: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\core\PythonFallbackKernel.cpp:161 [backend fallback] FuncTorchDynamicLayerFrontMode: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\functorch\DynamicLayer.cpp:493 [backend fallback] PreDispatch: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\core\PythonFallbackKernel.cpp:165 [backend fallback] PythonDispatcher: registered at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\core\PythonFallbackKernel.cpp:157 [backend fallback]

Justin Kelly

From some reason I'm unable to get past the Upscale Face+Pix section. Anyone else having the same issue?

trav land

After reading the install for comfyui, I got stuck on the 2nd step for Tooncrafter "Paste in python_embeded\python.exe -m pip install xformers --no-deps and hit enter. Wait until it's done. " I am running Windows 11... I kept getting an error saying it could not find Python.h file... and yes it is not there... the workaround I found was from here: https://github.com/comfyanonymous/ComfyUI/issues/4870 so instead of the above I used the command: python_embeded\python.exe -m pip install -U xformers --index-url https://download.pytorch.org/whl/cu124 Havent gotten all the way through the setup yet but it appears to load xformers when I start up ComfyUI so I wanted to share ....

Bladimir Salazar

Hello, is it possible to install Xformers on a M1 Mac?

Mick Mahler

Can you try installing "ComfyUI Essentials" via the ComfyUI manager and testing it again?

Tom Saloschnig

Hey I have a problem with the pose workflow, I get this error: Error occurred when executing IPAdapterUnifiedLoader: ClipVision model not found. File "D:\Comfy\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Comfy\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:\Comfy\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 "D:\Comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_IPAdapter_plus\IPAdapterPlus.py", line 511, in load_models raise Exception("ClipVision model not found.")

Oded Farber

fixed the issue. thx

Tom Suski

in comfy ui update folder - click update_comfyui_and_python_dependencies.bat that fixed it for me. Also it is good to have nvidia cuda installed on your system

OctonionPrime

it completely ignores any pose I upload and just goes with the one from the initial character input, no matter what I do

Oded Farber

hi while folowing the tutorial and WF's, I'm running into an error `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 what should I do? (reinstalled xformers and even pytorch)

Amanueal Hailu

Hey bro, I just joined but can’t seem to find the discord link And also why is the path for some of the models missing like the folder location for “ComfyUI-AnimateDiff-Evolved\models” In the ai render workflow is missing on my comfy ui I created the missing folders my self but it seems it doesn’t work

John Brennan

I think I’m mistaken. Apparently clip vision might just see model sheet or contact sheet lacking the right resolution to go further and we have to control the turn around reference ourselves:(

John Brennan

Would I mistaken for thinking that ipadapter could just take a very robust and thorough model sheet as an input and ‘know the character’ and its many angles just from that image?:) we currently have to pick one angle at a time? I was hoping for the former for some of my animation tests! ‘and thank you🙏

Mick Mahler

The model sheets were originally intended for a completely different workflow, which I'll be making a video about soon! But having all these different poses also helps with the ipAdapter workflow. For example, you could load the side view of your character if you want to generate one in side view. Or you could load in a different emotion from the close ups if you can't get far enough with the prompt. I also like the idea of having lots of different images to train Loras with and it looks cool ;)

John Brennan

Hey mick ! Why do you bother to generate these large character model sheets but never use them in a workflow? I would expect to see one such sheet being used by an ipadapter node but instead I notice it’s just a single shot of face or body