Image randomizer from directory, Image Captioning saver.
Image randomizer: - A load image directory node that allows you to pull images either in sequence (Per que render) or at random (also per que render)
b2442bae-a708-47f4-9de4-845abed491e2.mp4
It uses a dummy int value that you attach a seed to to enure that it will continue to pull new images from your directory even if the seed is fixed. In order to do this right click the node and turn the run trigger into an input and connect a seed generator of your choice set to random.
interesting uses for this
-loading up a directory and letting it cycle through all your images in order
-connecting this node to something like IPAdapter, while being set to random, allowing you to cycle through styles via images
-batch processing of any kind on large amounts of images
Image Captioning saver: - takes an input image (single or batch) and saves a matching .txt file with the image with desired captioning.
Both files will be over written for continuous experimentation. Required to have an output attached for monitoring. Will overwrite images and text on each run. Built this node to save Lora captions from my Dataset Creator
Dimension Display: - Simply shows the dimension of an image in a string for monitoring. No need for INTS.
current implementation requires you to break batches into a list and back into a batch if you want to use it on video. for VRAM management.
other nodes that are a work in progress take the sliced audio/bpm/fps and hold an image for the duration. There is also a VHS converter node that allows you to load audio into the VHS video combine for audio insertion on the fly!
Directory Crawler: - Simple node that loads all images in a directory and any subdirectories as well
Raw Code Node: - Simple node that loads Python and allows you to dev inside comfy without having to reload the instance every time
Great for developing ideas and writing custom stuff quickly
Slices up your image or video to make a glitching feel
Ripples your video or image
CAUTION: This node is a very heavy operation. It takes 5-10 seconds per frame. (WIP)
This one is really fun. It masks your image and video in slices, but thats not all! Each slice acts as its own video or image when you start rotating and messing with the parameters.
This one allows for a TON of different styles. This node also works with Alt Codes like this: alt+3 = ♥ or alt+219 = █ If you play with the spacing of 219 you can actually get a pixel art effect. ALSO, the last character in the list will always be applied to the highest luminance areas of the image. This is useful because you can do silly things like leave the last character as a blank space, allowing for negative space to be applied to light areas.
The default font list is populated from the fonts located within the extension/fonts folder. You can add more fonts to this location and when ComfyUI is started it will load those fonts into the list.
You also have the option to use system fonts. You can set the env var:
SET FL_USE_SYSTEM_FONTS=true (default: false)
And the dropdown will populate with all the available system ttf and otf fonts.
Great for iterating through a lot of prompts or randomizing a list of things you already know works.
Has a lot of uses where you want numbers randomized, but you need them in a specific range for error purposes.
Lots of fun with this one. Get interesting effects on both images and video.
20240715-0444-48.9763955.mp4
SD Ultimate Slice Calculator: - Allows you to select a multiplier, and a slice pattern and automatically calculates dimensions so you don't have to do the math. The image output returns the original images as a pass-through.
