ComfyUI 12 Controlnet Workflow (free download)

แชร์
ฝัง
  • เผยแพร่เมื่อ 6 ม.ค. 2024
  • Controlnet is a fun way to influence Stable Diffusion image generation, based on a drawing or photo. Controlnet preprosessors are available as a custom node. Controlnet models for SD1.5 as well as SDXL can be downloaded from CivitAI.
    Download Controlnet Models:
    civitai.com/models/136070/con...
    civitai.com/models/38784/cont...
    Link to the workflows from the video:
    drive.google.com/drive/folder...
    If there's trouble with the Latent Upscale node, try this one:
    github.com/city96/SD-Latent-U...
    Link to video on ComfyUI Manager:
    • ComfyUI 03 - ComfyUI M...
    Large collection of upscalers:
    openmodeldb.info/
  • แนวปฏิบัติและการใช้ชีวิต

ความคิดเห็น • 22

  • @lakislambrianides7619
    @lakislambrianides7619 6 หลายเดือนก่อน +3

    This is the most useful tutorial and workflow that I ever watched. I use this workflow all the time now and I am very happy with it. Congratulations keep the the tutorials coming please ❤

  • @WhySoBroke
    @WhySoBroke 6 หลายเดือนก่อน

    Awesome!! Exactly what I’ve been looking for!! Very grateful for your kindness amigo! ❤️🇲🇽❤️

    • @rudyshobbychannel
      @rudyshobbychannel  6 หลายเดือนก่อน

      You're welcome. Thanks for your enthusiast feedback.

  • @korilifs
    @korilifs 4 หลายเดือนก่อน +1

    Thank you for sharing. Great content.

    • @rudyshobbychannel
      @rudyshobbychannel  4 หลายเดือนก่อน

      Have you selected a controlnet model that is consistent with your checkpoint? For SD1.5 checkpoints you need a 1.5 Controlnet model. For XL checkpoints you need an XL Controlnet model.

  • @user-vs2qr7zf6n
    @user-vs2qr7zf6n 6 หลายเดือนก่อน +1

    Thank you for this great workflows. When I open the controlnet ones I get the following error When loading the graph, the following node types were not found:
    LatentUpscaler. I have used already the manager to install missing custom nodes. i'm a newbie with comfyui, maybe there is an easy fix? thanks again for your videos and workflows

    • @coolluke1992
      @coolluke1992 6 หลายเดือนก่อน +1

      getting same thing

    • @rudyshobbychannel
      @rudyshobbychannel  6 หลายเดือนก่อน +1

      That Latent Upscaler node is part of the Effeciency Nodes, which can be installed via the Manager.

    • @user-vs2qr7zf6n
      @user-vs2qr7zf6n 6 หลายเดือนก่อน

      It worked by deleting the node and replacing it with a new one.@@rudyshobbychannel

  • @fiveuseful
    @fiveuseful 4 หลายเดือนก่อน

    When loading the graph, the following node types were not found:
    Text box
    Nodes that have failed to load will show as red on the graph.

    • @rudyshobbychannel
      @rudyshobbychannel  4 หลายเดือนก่อน

      That probably is the 'Filename' node. It belongs to the 'Derfuu ComfyUI ModdedNodes': github.com/Derfuu/Derfuu_ComfyUI_ModdedNodes
      If you can't get it working then you can simply delete the node and convert all the filename inputs of the nodes it was connected to, to a widget.

    • @fiveuseful
      @fiveuseful 4 หลายเดือนก่อน

      I'm still totally stuck. I am not able to get it out by removing that node@@rudyshobbychannel

    • @rudyshobbychannel
      @rudyshobbychannel  4 หลายเดือนก่อน

      What? The node can't be deleted? I probably misunderstand you.
      This is the link to the newest set of workflows, that node is not in those anymore, can you try?
      drive.google.com/drive/folders/1C4hnb__HQB2Pkig9pH7NWxQ05LJYBd7D?usp=drive_link

  • @helloRick618
    @helloRick618 4 หลายเดือนก่อน

    Error occurred when executing ttN pipeKSampler:
    mat1 and mat2 shapes cannot be multiplied (77x2048 and 768x320)
    How can I solve this problem?

    • @rudyshobbychannel
      @rudyshobbychannel  4 หลายเดือนก่อน +1

      It sounds like possibly the Checkpoint and the Controlnet model are of different size? Boyh need to be SD1.5 models or XL models.

    • @helloRick618
      @helloRick618 4 หลายเดือนก่อน

      @@rudyshobbychannel Thank you so much, problem solved, I used wrong controlnet model(sd1.5) .

  • @phalcon23
    @phalcon23 2 หลายเดือนก่อน

    whats the side bar on the left side with the image that pop up?

    • @rudyshobbychannel
      @rudyshobbychannel  2 หลายเดือนก่อน +2

      You get that when you install the Pythongosssss custom nodes.

    • @phalcon23
      @phalcon23 2 หลายเดือนก่อน

      @@rudyshobbychannel more specifically
      pythongosssss/ComfyUI-Custom-Scripts
      i think

  • @suthamchindaudom6410
    @suthamchindaudom6410 หลายเดือนก่อน

    I've watched a lot your youTube videos and really like them. May I ask for help. I want a workflow which can convert a real portrait photo to a painterly image or watercolor or anime without distortion of facial features of a person. Can you recommend me anyone to contact? What else internet service can I ask for building such a workflow such as patreon ?
    Thanks for helping me.

    • @rudyshobbychannel
      @rudyshobbychannel  หลายเดือนก่อน

      There already is a workflow that can help you out, the combined Controlnet en IPAdapter workflow: th-cam.com/video/WD0EmOE4boc/w-d-xo.html

  • @jameshastie3864
    @jameshastie3864 5 หลายเดือนก่อน +1

    error checkpoint does not contain controlnet or t2i adapter data C:\Program Files\ComfyUI_windows_portable\ComfyUI\models\controlnet\controlnetxlCNXL_bdsqlszDepth.safetensors
    ERROR:root:!!! Exception during processing !!!
    ERROR:root:Traceback (most recent call last):
    File "C:\Program Files\ComfyUI_windows_portable\ComfyUI\execution.py", line 155, in recursive_execute
    output_data, output_ui = get_output_data(obj, input_data_all)
    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
    File "C:\Program Files\ComfyUI_windows_portable\ComfyUI\execution.py", line 85, in get_output_data
    return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
    File "C:\Program Files\ComfyUI_windows_portable\ComfyUI\execution.py", line 78, in map_node_over_list
    results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
    File "C:\Program Files\ComfyUI_windows_portable\ComfyUI
    odes.py", line 762, in apply_controlnet
    c_net = control_net.copy().set_cond_hint(control_hint, strength)
    ^^^^^^^^^^^^^^^^
    AttributeError: 'NoneType' object has no attribute 'copy'