T

Typed Recourse nodes.
Check - priority inputs, auto detect model data from input, output flag and first live per type
+/- (Polarity) - 6 inputs, two sets of three conditionings, output the first live of each set
Image - 4 inputs, output first live

Fork -  multi-output Model, determine live output based on number. Meant to be automated by Check.

ForkClip - Same as above but for clip

Unite - Input several latents and use a numerical value to select the live input. Meant to be automated by Check.

2024-06-18 10:07:25 -04:00

.github/workflows

chore(publish): Add Github Action for Publishing to Comfy Registry

2024-06-14 06:59:58 +00:00

__init__.py

Add files via upload

2024-05-28 00:15:13 -04:00

LICENSE

Initial commit

2024-05-24 18:08:12 -04:00

pyproject.toml

Added nodes

2024-06-18 10:07:25 -04:00

README.md

Update README.md

2024-06-04 02:14:55 -04:00

selector.py

Added nodes

2024-06-18 10:07:25 -04:00

README.md

comfyui-selector

Quick and dirty nodes for ComfyUI

The nodes will be listed under images/utils, or you can type . to find it in search/double-click menu on the grid.

Note

git clone https://github.com/exdysa/comfyui-selector/ or place the .py file inside custom_nodes.

"Recourse" node - building from pythongoss/ltdrdata. If the input has been muted/bypassed/deleted, it uses the alternative input in 'fallback'. There is an additional boolean out that you can use for logic mayhem as well. You probably want to make sure input, fallback and output types match...

"Selector" node - Generates simple parameters to use in other nodes

Data output todo :

~~SD 3.0 resolutions~~

~~sampler options~~

~~support for Pixart alpha/sigma, playground, kandinsky, etc...~~

~~upscale dimensions and factors~~

~~multiple steps~~

~~multiple cfgs~~

~~refiner steps~~

~~multiple denoises~~

~~...toast??~~

Initial plans I will likely not attempt :

custom values

multiple seeds

nested menus for model types