KenSchae
/
wyrde-comfyui-workflows
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
some wyrde workflows for comfyUI
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
343 Commits
2 Branches
0 Tags
592 MiB
 
Tree: 0924119652
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '0924119652'
${ noResults }
wyrde-comfyui-workflows/why-oh-why/random-prompt-hrf-20img-output
wyrde 89a292c067
added version numbers and updated 		2 years ago
..
img new workflow added 2 years ago
README.md Update README.md 2 years ago
workflow large.png images 2 years ago
workflow smaller.png images 2 years ago
wyrde multi random v1.0 WAS lora x3 HRF x10 landscape x10 portrait x10.json added version numbers and updated 2 years ago
wyrde multi random v1.0 WAS lora x3 HRF x10 landscape x10 portrait x10.svg added version numbers and updated 2 years ago
wyrde multi random v1.2 WAS lora x3 HRF x10 landscape x10 portrait x10.json added version numbers and updated 2 years ago

README.md

wyrde's terribly complicated multi latent fixing and fiddling

Makes extensive use of WAS nodes.

  • Install WAS suit and avoid a mess of red boxes.

The goal of this workflow was three-fold

  • generate a bunch of series of images which SD repeatedly samples.
    • they tend to improve slowly, but sometimes have wild changes
  • Use a prompt with a high degree of randomness
    • figure, hair, ears, & clothing. More elements can be randomized with these as examples.
  • have the complete prompt be sharable with a resulting image
    • In comfyui, words in {curly braces | separated by | pipes are | used to | generate} random results. Due to the way comfyui functions, an image's workflow will contain only the items in the prompt which were evaluated for the image. Other random elements will be dropped.

The workflow

  • Generates a text prompt from several randomized lists
  • the sections are concated together
  • the prompt is sampled
  • sampled again
  • and again -- 10 times
  • switches aspect ratio
  • and does all that again.
  • total output is 20 images

The big box at the end has spare nodes for easy copy pasting

Includes some lora. There's also a places where moving noodles changes the generation.

Example Results

  • Portrait Row

  • Landscape Row

resources

Model

Lora

Embeds

[back] [home]