You can download from ComfyUI from here: github.com/comfyanonymous/ComfyUI And extension from here: github.com/ltdrdata/ComfyUI-Impact-Pack Workflow: (you can drag drop this image): github.com/ltdrdata/ComfyUI-extension-tutorials/blob/Main/ComfyUI-Impact-Pack/workflow/MakeTileSEGS_upscale_AnimateDiff_ControlNet.png
Hello! I have a question regarding this workflow. When using the Simple Detector, I encountered an issue where the segmentation was static and not moving. To resolve this, I switched the source images to a [List] format and then input them into the Detector, which allowed the segmentations to move as I expected. However, I cannot figure out how to use them with Detailer. If I input them to Detailer, it shows me broken noise images. Could you provide any advice or insights on how to proceed? Thank you!
Thanks for all the tutorials @drltdata. by the way your videos has sound, I mean you are talking? I can not hear anything, it would be good to hear your voice sir.
Hi Dr. I always get an the error below when using detailer for animatediff or SEGSPaste, I tried all the ways I can find on google but got nothing helpful.Would you please give some help? Thank you! Error occurred when executing SEGSPaste: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! File "D:\Program Files\Blender_ComfyUI\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "D:\Program Files\Blender_ComfyUI\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:\Program Files\Blender_ComfyUI\ComfyUI\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) File "D:\Program Files\Blender_ComfyUI\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\segs_nodes.py", line 180, in doit tensor_paste(image_i, ref_image, (x, y), mask) File "D:\Program Files\Blender_ComfyUI\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\utils.py", line 202, in tensor_paste (1 - mask) * image1[:, y:y+h, x:x+w, :] +