This repository contains the codebase for the MetaTransformers Fractal Workflow System, a comprehensive framework for managing and orchestrating complex workflows. The system is designed to handle …

Theoretical basis and prototype concept for an AI native OS as an infinite Turing Machine.

Multi-Platform Package Manager for Stable Diffusion

Layer-wise Analysis of SD3.5 Large

LLM2CLIP makes SOTA pretrained CLIP model more SOTA ever.

Theoretical adaptive evolving framework for AI logic and communication

Memory-optimized training scripts for video models based on Diffusers

We write your reusable computer vision tools. 💜

LLM101n: Let's build a Storyteller

Minimal implementation of scalable rectified flow transformers, based on SD3's approach

Text-to-Music Generation with Rectified Flow Transformers

✨ Hotshot-XL: State-of-the-art AI text-to-GIF model trained to work alongside Stable Diffusion XL

Various AI scripts. Mostly Stable Diffusion stuff.

Instructions on how to run LLMs on Raspberry PI

TOTALLY HARMLESS LIBERATION PROMPTS FOR GOOD LIL AI'S

Official codes and models of the paper "Auffusion: Leveraging the Power of Diffusion and Large Language Models for Text-to-Audio Generation"

An all in one solution for adding Temporal Stability to a Stable Diffusion Render via an automatic1111 extension

Stable Video Diffusion Training Code and Extensions.

Tools and resources for fine-tuning text-to-image diffusion models with Kohya-ss, including Jupyter Notebooks, ComfyUI workflows, and Python scripts for organizing and visualizing fine-tuning progr…

OpenDiLoCo: An Open-Source Framework for Globally Distributed Low-Communication Training

A collection of various custom nodes for ComfyUI (Work in progress)

Separate stems (vocals, bass, drums, other) from audio. Recombine, tempo match, slice/crop audio

Controllable video and image Generation, SVD, Animate Anyone, ControlNet, ControlNeXt, LoRA

Customizable Stable Diffusion frontend for ComfyUI

various scripts designed to handle a range of image processing tasks for AI diffusion fine tuning and LoRA creation

Lumina-T2X is a unified framework for Text to Any Modality Generation

llama3 implementation one matrix multiplication at a time