Official Implementation of weights2weights

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

A lightweight library for portable low-level GPU computation using WebGPU.

Official PyTorch Implementation of "Giving a Hand to Diffusion Models: a Two-Stage Approach to Improving Conditional Human Image Generation"

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

Official Pytorch Implementation for "MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation" presenting "MultiDiffusion" (ICML 2023)

Repo is required for the code of our research paper on micro-budget training of large scale diffusion model.

Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.

The memory layer for Personalized AI

Kolors的ComfyUI原生采样器实现(Kolors ComfyUI Native Sampler Implementation)

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

Fast and memory-efficient exact attention

Understand Human Behavior to Align True Needs

StyleShot: A SnapShot on Any Style. 一款可以迁移任意风格到任意内容的模型，无需针对图片微调，即能生成高质量的个性风格化图片!

ControlNet++: All-in-one ControlNet for image generations and editing!

Kolors Team

Node.js API for Chrome

[ECCV 2024] official code for "Long-CLIP: Unlocking the Long-Text Capability of CLIP"

Code of the paper "Listening to the Noise: Blind Denoising with Gibbs Diffusion"

4M: Massively Multimodal Masked Modeling

A framework for prompt tuning using Intent-based Prompt Calibration

Integrate cutting-edge LLM technology quickly and easily into your apps

UNet diffusion model in pure CUDA

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

Distributed Task Queue (development branch)