ZhenbangDu

Reliable_AD

llama-classification

Text classification with Foundation Language Model LLaMA

unidiffuser

Code and models for the paper "One Transformer Fits All Distributions in Multi-Modal Diffusion"

DMD2

SimPO

SimPO: Simple Preference Optimization with a Reference-Free Reward

clip-interrogator

Image to prompt with BLIP and CLIP

Awesome-Text-to-Image

(ෆ`꒳´ෆ) A Survey on Text-to-Image Generation/Synthesis.

DiffPIR

"Denoising Diffusion Models for Plug-and-Play Image Restoration", Yuanzhi Zhu, Kai Zhang, Jingyun Liang, Jiezhang Cao, Bihan Wen, Radu Timofte, Luc Van Gool.

ragflow

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

latent-consistency-model

Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference

consistency_models

Official repo for consistency models.

TransformerCompression

For releasing code related to compression methods for transformers, accompanying our publications

tomesd

Speed up Stable Diffusion with this one simple trick!

edm

Elucidating the Design Space of Diffusion-Based Generative Models (EDM)

self-llm

《开源大模型食用指南》基于Linux环境快速部署开源大模型，更适合**宝宝的部署教程

trl

Train transformer language models with reinforcement learning.

HA-DPO

Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization

Diff-Pruning

[NeurIPS 2023] Structural Pruning for Diffusion Models

diffusion

Denoising Diffusion Probabilistic Models

Early-Bird-Tickets

[ICLR 2020] Drawing Early-Bird Tickets: Toward More Efficient Training of Deep Networks

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

Conditional_Diffusion_MNIST

Conditional diffusion model to generate MNIST. Minimal script. Based on 'Classifier-Free Diffusion Guidance'.

Social-Reward

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

MDT

Masked Diffusion Transformer is the SOTA for image synthesis. (ICCV 2023)

nerfies.github.io

torch-fidelity

High-fidelity performance metrics for generative models in PyTorch

FQ-ViT

[IJCAI 2022] FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer

academicpages.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

MiniGPT-4

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)