Extraltodeus's repositories
ComfyUI-AutomaticCFG
If your image was a pizza and the CFG the temperature of your oven: this is a thermostat that ensures it is always cooked like you want. Also adds a 30% speed increase. For ComfyUI / StableDiffusion
Skimmed_CFG
A powerful anti-burn allowing much higher CFG scales for latent diffusion models (for ComfyUI)
test_my_prompt
This script is to test your prompts with the AUTOMATIC1111 webui
Vector_Sculptor_ComfyUI
Gather similar vectors within the CLIP weights and use them to redirect the original weights
sigmas_tools_and_the_golden_scheduler
A few nodes to mix sigmas and a custom scheduler that uses phi
LoadLoraWithTags
Save/Load trigger words for loras from a json and auto fetch them on civitai if they are missing. Optional prompt input to auto append them (togglable). Actual alphabetical order and print trigger words to terminal. Also bypass toggle to disable without aiming the sliders at 0.
pre_cfg_comfy_nodes_for_ComfyUI
A set of nodes to prepare the noise predictions before the CFG function
Uncond-Zero-for-ComfyUI
Allows to sample without generating any uncond with Stable Diffusion!
Stable-Diffusion-temperature-settings
Provides the ability to set the temperature for both UNET and CLIP. For ComfyUI. Has for side effect to improve non-native resolutions.
DistanceSampler
Heuristic modification of the Heun sampler using normalized distances.
noise_latent_perlinpinpin
This allows to create latent spaces filled with perlin-based noise that can actually be used by the samplers.
Conditioning-token-experiments-for-ComfyUI
A few experimental nodes about the conditioning and the next closest tokens. For ComfyUI.
koreader-autorotate
A simple plugin for Koreader to automatically rotate the page to landscape if it's a double page (only tested with CBZ files on a pocketbook)
Negative-attention-for-ComfyUI-
Takes the difference in between the positive and negative conditioning at the attention.
comfyui-animatediff
AnimateDiff for ComfyUI
Game-of-life-on-GPU
pytorch implementation of the game of life using a convolution kernel
problem-solver
problem_solver
abliterator
Simple Python library/structure to ablate features in LLMs which are supported by TransformerLens
ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
ComfyUI-APG_ImYourCFGNow
ComfyUI implementation of the paper https://arxiv.org/pdf/2410.02416 "APG".
custom-sd-upscale
a simple script to upscale images with a model of your choice and other parameters
ELLA
ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment
llama3.np
llama3.np is pure NumPy implementation for Llama 3 model.
sd-perturbed-attention
Perturbed-Attention Guidance for ComfyUI and SD Forge
text-to-video-synthesis-colab
Text To Video Synthesis Colab