lxtGH

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

llama3

The official Meta Llama 3 GitHub site

llm.c

LLM training in simple, raw C/CUDA

InstantID

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

AniPortrait

AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation

VAR

[GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

MGM

Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"

xtuner

An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)

nerfies.github.io

Lumina-T2X

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

OMG-Seg

[CVPR-2024] One Model For Image/Video/Instractive/Open-Vocabulary Segmentation

EdgeSAM

Official PyTorch implementation of "EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM"

Awesome-Open-Vocabulary

(TPAMI 2024) A Survey on Open Vocabulary Learning

Entity

EntitySeg Toolbox: Towards Open-World and High-Quality Image Segmentation

ovsam

[arXiv preprint] The official code of paper "Open-Vocabulary SAM".

Awesome-Segmentation-With-Transformer

[Arxiv-04-2023] Transformer-Based Visual Segmentation: A Survey

RADIO

Official repository for "AM-RADIO: Reduce All Domains Into One"

Mira

RAP-SAM

mmdit

Implementation of a single layer of the MMDiT, proposed in Stable Diffusion 3, in Pytorch

CLIPSelf

[ICLR2024 Spotlight] Code Release of CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction

Awesome-LLMs-meet-Multimodal-Generation

🔥🔥🔥 A curated list of papers on LLMs-based multimodal generation (image, video, 3D and audio).

ADer

ADer is an open source visual anomaly detection toolbox based on PyTorch, which supports multiple popular AD datasets and approaches.

MambaAD

Official implementation of MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection.

betrayed-by-captions

(ICCV 2023) Betrayed by Captions: Joint Caption Grounding and Generation for Open Vocabulary Instance Segmentation

PointCloudMamba

Point Cloud Mamba: Point Cloud Learning via State Space Model

ml-rpm-bench

VG4D

Implementation of the paper: VG4D: Vision-Language Model Goes 4D Video Recognition（ICRA 2024）

DAQ-VS

Code For Our Work: DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries

BA-SAM

Official code for BA-SAM:Scalable Bias-Mode Attention Mask for Segment Anything Model