This started as a test workflow to test hand fixing... I just dont know when to stop sometimes. I needed a break from the videos workflow.
Tips :
Each pose is not limited to one person, 2 people, or a crowd per pose works, lowering the image ref helps in this case.
Background people can be picked up and included sometimes.
Slightly overlapping subjects is possible, can produce interactions.
V1 works entirely different from beta. I think both have uses so beta can stay up
Image Composer v1
Features
- Poses generated from your images
- Combine 3 poses into one image.
- Select Ip refs for each pose
- Openpose/lineart and aux (densepose/segs/etc) pose generations
Description
Features
- Poses generated from your images
- Combine 3 poses into one image.
- Select Ip refs for each pose
- Openpose/lineart and aux (densepose/segs/etc) pose generations
FAQ
Comments (2)
Didn't load the flow, and cant see the screen grabs well enough, but just maybe you want to resample the whole image with light denoise to make your subjects look more integrated and less pasted.
is there any solution to this error?
Error occurred when executing ApplyCLIPSeg+: tuple index out of range File "C:\AI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\execution.py", line 152, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\AI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\execution.py", line 82, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\AI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\execution.py", line 75, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\AI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_essentials\segmentation.py", line 64, in execute outputs = T.functional.gaussian_blur(outputs, smooth) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\AI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torchvision\transforms\v2\functional\_misc.py", line 83, in gaussian_blur return kernel(inpt, kernel_size=kernel_size, sigma=sigma) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\AI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torchvision\transforms\v2\functional\_misc.py", line 148, in gaussian_blur_image kernel = kernel.expand(shape[-3], 1, kernel.shape[0], kernel.shape[1]) ~~~~~^^^^
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.