ComfyUI Inpainting workflow #comfyui #controlnet #ipadapter #workflow

Comfy-UI Workflow for inpainting

This workflow allows you to change clothes or objects in an existing image
If you know the required style, you can work with the IP-Adapter and upload a reference image
And if you want to get new ideas or directions for design, you can create a large amount of variations in a process that is mostly automatic

Here is used:
ControlNet
Segment Anything
IP-Adapter
Image Composite masked
masks
and more..

#comfyui #stablediffusion #ipadapter #mask #controlnet #segment

workflow

Segment anything

was-node-suite-comfyui

juggernaut model

IP-Adapter GitHub

Prompt Styler SDXL

[WiLDeveD]

Thanks very much for such a useful content. God Bless You bro. ❤💯

[fk]

A short and exciting tutorial, and more importantly, you also shared the workflow. Well done, thank you very much for sharing

[SoSpecters]

I cannot get enough of how clear and concise your way of explaining all this stuff is. I just get it. And the workflows are exceptional. Thank you for what you do.

[mrrohitjadhav]

hi, amazing tutorial, Please make a video on how to transfer style, color grading, and tone from one portrait to another

[Amithyst-MAL]

Thank you for this helpful video on Segment Anything. If you are still taking questions on this, I have found that the Preview Bridge (image) node works the opposite way for me; I can only remove parts of the mask that I don't want and never add areas that are missing when using the Mask editor. Anything thoughts? Thanks!

[justthinkaboutit]

Liked your workflow. Correct me if I am wrong, this workflow is optimized to replacing one set of clothes defined by the size of the mask with another. I would like to know how to for example given an image of woman wearing a dress and an image of a specific bikini how that can work because the mask for the dress is much larger than the bikini, and the inpaint has to fill in the exposed body parts while using the exact style of bikini. I have found this to be much harder to do. There are various workflows with clothes swapping I have tried but none seem to be able to handle this scenario very well.

[SuperSSystem]

This video really takes you from 0 to hero, thanks for the good work.
I have installed all the links that you provided, got latest Py and Git and all those missing nodes.. just one thing

Error occurred when executing MaskBlur+:
object of type 'float' has no len()

ControlNet works with lora256, I can see the depth mask.
In the Mask Refinement Section, the Preview Bridge and the Image Preview are working.
IpAdepter Nodes are faded.
SegAny section is also OK.
The end (Preview)Images are showing, but the dress in both is marked with gray.

any suggestions..

[satyajitroutray]

great video, One question, If there are multiple subjects wearing jacket, This tend to mask all the jackets and i get al of them wearing same jacket in the output photo, How can i erase out the subject's jacket which i dont want to stylize?

[ss]

Is it possible to route those connection lines of nodes? Those bezier curves from node to node make it a mess to read the graph.

[BibhatsuKuiri]

thank you. can you suggest a way, so that i can backup comfyui (nodes, model files etc, that are used in a workflow to save it in some external HDD. because whenever i update, some or the other workflow dont work. basically any smart way to backup comfy. ?

[KINGLIFERISM]

This just changes the color of the clothes. I have a work flow I want you to share to your followers... It auto changes the clothing with a outfit you pick. It needs work but I really want the community to have it.

[fememystic]

When launching, i get "When loading the graph, the following node types were not found:
DifferentialDiffusion 🔗
Nodes that have failed to load will show as red on the graph." How do i install it? Thank you for video!

[jasondulin]

I haven't been able to get Derfuu Mixed Nodes to work in any setting. It's installed. I can see it, but Comfy can't. Anyone else having this issue?

[wrath-viks]

i want to use this in a video but i end up with lots of flickering. is there a way for it?

[ShubzGhuman]

Error occurred when executing MaskBlur+:

object of type 'float' has no len()

File "C:\Users\shub4\Downloads\ComfyUI_WORKING\ComfyUI\execution.py", line 152, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)

File "C:\Users\shub4\Downloads\ComfyUI_WORKING\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:\Users\shub4\Downloads\ComfyUI_WORKING\ComfyUI\execution.py", line 75, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))

File "C:\Users\shub4\Downloads\ComfyUI_WORKING\ComfyUI\custom_nodes\ComfyUI_essentials\mask.py", line 44, in execute
mask = T.functional.gaussian_blur(mask.unsqueeze(1), amount).squeeze(1)

File "C:\Users\shub4\Downloads\ComfyUI_WORKING\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:\Users\shub4\Downloads\ComfyUI_WORKING\python_embeded\Lib\site-packages\torchvision\transforms\v2\functional\_misc.py", line 110, in gaussian_blur_image
elif len(kernel_size) != 2:


got this error at the end, using win 11, i5 13th, 6gb vram nvidia,