lu-m13

EMO

Emote Portrait Alive: Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions

web-stable-diffusion

Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.

Awesome-LLM-Inference

📖A curated list of Awesome LLM Inference Paper with codes, TensorRT-LLM, vLLM, streaming-llm, AWQ, SmoothQuant, WINT8/4, Continuous Batching, FlashAttention, PagedAttention etc.

MetaTransformer

Meta-Transformer for Unified Multimodal Learning

LayerDiffusion

Transparent Image Layer Diffusion using Latent Transparency

coyo-dataset

COYO-700M: Large-scale Image-Text Pair Dataset

minisora

MiniSora: A community aims to explore the implementation path and future development direction of Sora.

OpenDiT

OpenDiT: An Easy, Fast and Memory-Efficient System for DiT Training and Inference

conditional-flow-matching

TorchCFM: a Conditional Flow Matching library

VILA

VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)

Efficient-LLMs-Survey

[TMLR 2024] Efficient Large Language Models: A Survey

Bunny

A family of lightweight multimodal models.

Qwen-TensorRT-LLM

SoraReview

The official GitHub page for the review paper "Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models".

ring-flash-attention

Ring attention implementation with flash attention

RoMa

[CVPR 2024] RoMa: Robust Dense Feature Matching; RoMa is the robust dense feature matcher capable of estimating pixel-dense warps and reliable certainties for almost any image pair.

DoLa

Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"

PaintMixing

gaussian-splatting-blender-addon

PointMamba

PointMamba: A Simple State Space Model for Point Cloud Analysis

VDT

[ICLR2024] The official implementation of paper "VDT: General-purpose Video Diffusion Transformers via Mask Modeling", by Haoyu Lu, Guoxing Yang, Nanyi Fei, Yuqi Huo, Zhiwu Lu, Ping Luo, Mingyu Ding.

Symphonies

[CVPR 2024] Symphonies (Scene-from-Insts): Symphonize 3D Semantic Scene Completion with Contextual Instance Queries

web-splat

3D Gaussian Splatting Renderer implemented in WebGPU (WGPU) and Rust

T-Stitch

Official PyTorch implmentation of paper "T-Stitch: Accelerating Sampling in Pre-trained Diffusion Models with Trajectory Stitching"

emote-portrait-alive

massive-activations

Code accompanying the paper "Massive Activations in Large Language Models"

Sora-Generates-Videos-with-Stunning-Geometrical-Consistency

Sora Generates Videos with Stunning Geometrical Consistency

SmartText

Code for the paper "Harmonious Textual Layout Generation over Natural Images via Deep Aesthetics Learning" (TMM 2021)

alignmif

Dense_Reward_T2I

Source code for "A Dense Reward View on Aligning Text-to-Image Diffusion with Preference" (ICML'24).