zhangshushu15

ollama

Get up and running with Llama 3, Mistral, Gemma, and other large language models.

InstantID

InstantID : Zero-shot Identity-Preserving Generation in Seconds 🔥

magic-animate

[CVPR 2024] MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model

LAVIS

LAVIS - A One-stop Library for Language-Vision Intelligence

PhotoMaker

PhotoMaker

tutorials

PyTorch tutorials.

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

gemma.cpp

lightweight, standalone C++ inference engine for Google's Gemma models.

DiT

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

Amphion

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.

highway

Performance-portable, length-agnostic SIMD with runtime dispatch

WhisperSpeech

An Open Source text-to-speech system built by inverting Whisper.

T2I-Adapter

T2I-Adapter

Moore-AnimateAnyone

Character Animation (AnimateAnyone, Face Reenactment)

DeepDanbooru

AI based multi-label girl image classification system, implemented by using TensorFlow.

swift-coreml-diffusers

Swift app demonstrating Core ML Stable Diffusion

mixtral-offloading

Run Mixtral-8x7B models in Colab or consumer desktops

gemma

Open weights LLM from Google DeepMind.

direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)

RPG-DiffusionMaster

[ICML 2024] Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs (PRG)

FreeU

FreeU: Free Lunch in Diffusion U-Net (CVPR2024 Oral)

lectures

Material for cuda-mode lectures

MOSS-RLHF

MOSS-RLHF

summarize-from-feedback

Code for "Learning to summarize from human feedback"

improved-aesthetic-predictor

CLIP+MLP Aesthetic Score Predictor

megablocks

tutel

Tutel MoE: An Optimized Mixture-of-Experts Implementation

StyleSelectorXL

This repository contains a Automatic1111 Extension allows users to select and apply different styles to their inputs using SDXL 1.0.

aesthetic-predictor

A linear estimator on top of clip to predict the aesthetic quality of pictures

ava_downloader

:arrow_double_down: Download AVA dataset (A Large-Scale Database for Aesthetic Visual Analysis)