Others

For those who are unable to set up a GPU environment, you can run it through the following link. You can run a powerful Webui tool.

https://colab.research.google.com/github/todhm/easy-stable-diffusion/blob/civit/notebooks/easy_stable_diffusion.ipynb

I have also created a feed feature where you can share photos with others. If you want to run it together, please feel free to use it. https://github.com/todhm/sd_feed.git

A collection of ComfyUI custom nodes to help streamline workflows and reduce total node count.

Github Repo: https://github.com/LucianoCirino/efficiency-nodes-comfyui

Currently Available Nodes:

Ksampler (Efficient)

• A modded KSampler with the ability to preview and output images.

• Re-outputs key inputs which helps promote a cleaner and more streamlined workflow look for ComfyUI.

• Can force hold all of its outputs without regenerating by setting its state to "Hold".

• Simplifies the comparison of settings by generating clear and concise image plots.

note: when using multiple instances of this node, each instance must have a unique ID for the "Hold" state to function properly.

Efficient Loader

• A combination of common initialization nodes.

XY Plot

• A node that allows users to specify parameters for the KSampler (Efficient) to plot on a grid.

Image Overlay

• Node that allows for flexible image overlaying.

Evaluate Integers

• 3 integer input node that gives the user ability to write their own python expression for a INT/FLOAT type output.

Evaluate Strings

• 3 string input node that

This custom node pack provides various model-based detection nodes and a detailer node that recreates mask areas in high resolution. It also offers simple inpainting assistant functions such as a mask editor.

Please refer to the GitHub page for more detailed information.

https://github.com/ltdrdata/ComfyUI-Impact-Pack

Install guide:

• Download

• Uncompress into ComfyUI/custom_nodes

• Restart ComfyUI

Troubleshootings:

• Occasionally, when a new parameter is created in an update, the values of nodes created in the previous version can be shifted to different fields. This can result in unintended results or errors if executed as is, so it is important to check the node values. In particular, when updating from version v1.4 or earlier to version v1.5, all parameter values under guide_size will be different, so be careful when using previously created workflows.

Updates:

v1.7

• new feature: mask-points, mask-area on SAMDetectorCombined

• improve mask painting: wheel brush size, right button eraser

• SAMDetectorCombined bbox range bug fix

v1.6.1

• bug fix for DetailerForEachDebug

v1.6

• MaskPainter, EmptySEGS node added

• bug fix for MaskToSEGS

v1.5

• guide_size_for parameter added

• more predictable upscale size patch

• crop_factor on ONNXDetectorForEach node

v1.4

• guide_size bug fix

• ONNXLoader, ONNXDetectorForEach nodes added

v1.3

• MaskToSEGS node added.
  

v1.2

• Support external_seed for Seed node of WAS node suite.
  

v1.1

• Fixed a package dependency issue with pycocotools on Windows.

• Resolved an issue where the software was unable to recognize the "ComfyUI" folder in certain cases.

I'm not sure if mods will decide to remove this, as it has nothing to do with image generation. I'm just uploading here to share what I've been working on lately.

I've discovered that you can train musical instruments with so-vits-svc to make them talk and possibly even transform other instruments.

https://github.com/34j/so-vits-svc-fork