AnimateDiff ControlNet non-flickering workflow with Face Swap
Added 2023-11-06 11:12:19 +0000 UTCNew ComfyUI Workflow video are going to live in Youtube.
I have update the current workflow for AnimateDiff ControlNet non-flickering workflow.
It added features for Face swap and it works for multiple character as well.
Check it out,
Full Article :
https://thefuturethinker.org/easily-perform-faceswaps-in-animations-with-stable-diffusion-comfyui/
Attached file for ReActor Face Swap with AnimateDiff Workflow.
Cheers.
Comments
Yes try the previous version workflow, and add the ReActor FaceSwap manually
Benjamin Law
2023-11-07 17:59:22 +0000 UTCi did... https://github.com/comfyanonymous/ComfyUI/releases same problem... guess i have to go back to your previous workflow ;-)
Marc
2023-11-07 17:25:03 +0000 UTCtry pytorch update
Benjamin Law
2023-11-07 07:38:45 +0000 UTCHere we go... thanx so far for your kind support. It's late.... tomorrow i have to figure out what this means: Error occurred when executing IPAdapterModelLoader: Weights only load failed. Re-running `torch.load` with `weights_only` set to `False` will likely succeed, but it can result in arbitrary code execution.Do it only if you get the file from a trusted source. WeightsUnpickler error: Unsupported operand 60 File "F:\ComfyUI_windows_portable\ComfyUI\execution.py", line 153, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUI_windows_portable\ComfyUI\execution.py", line 83, 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 76, 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_IPAdapter_plus\IPAdapterPlus.py", line 253, in load_ipadapter_model model = comfy.utils.load_torch_file(ckpt_path, safe_load=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUI_windows_portable\ComfyUI\comfy\utils.py", line 20, in load_torch_file pl_sd = torch.load(ckpt, map_location=device, weights_only=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\serialization.py", line 1027, in load raise pickle.UnpicklingError(UNSAFE_MESSAGE + str(e)) from None
Marc
2023-11-06 22:37:29 +0000 UTCoh this is from ComfyUI_IPAdapter_plus download this one : https://huggingface.co/h94/IP-Adapter/resolve/main/models/image_encoder/model.safetensors
Benjamin Law
2023-11-06 22:10:23 +0000 UTCAhh okay... I think I expressed myself wrong :/ I have the loader... but the corresponding model sd1.5 model.safetensors is not found... btw - amazing response time ;-)
Marc
2023-11-06 21:52:47 +0000 UTCHello Marc, Thank you for joining us :) The Clip Vision Loader should be by default in ComfyUI system. You can click on the diagram and select menu > Nodes > Loader> and select Clip Vison Loader. Please find the screenshot link below : https://drive.google.com/file/d/1PUZCRCNXFDLYikuALociiXGeEIleAfIH/view?usp=sharing Hope this help :)
Benjamin Law
2023-11-06 21:39:20 +0000 UTCHi :-) first - thanx for your amazing work and videos... So far I have gained a lot of experience with A1111 and have focused on creating images. I have had less experience with Comyui so far because the image quality doesn't seem to be that good to me. But maybe I'm making a mistake ;-) I have provided the workflow with the appropriate nodes, but I can't find anything to activate the "CLIPVisionLoader". Can you please help? :-)
Marc
2023-11-06 21:31:35 +0000 UTC
