YTEP-ZHI

InstantID

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

StableCascade

Official Code for Stable Cascade

alphageometry

Vim

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

RPG-DiffusionMaster

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

RAG-Survey

onediff

OneDiff: An out-of-the-box acceleration library for diffusion models.

hallucination-leaderboard

Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents

OpenLRM

An open-source impl. of Large Reconstruction Models

Awesome-Robotics-Foundation-Models

ml-aim

This repository provides the code and model checkpoints of the research paper: Scalable Pre-training of Large Autoregressive Image Models

Bunny

A family of lightweight multimodal models.

gaussian_splatting_notes

A detailed formulae explanation on gaussian splatting

LaVIT

LaVIT: Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization

local-attention

An implementation of local windowed attention for language modeling

FreeNoise

[ICLR 2024] Code for FreeNoise based on VideoCrafter

DCNv4

[CVPR 2024] Deformable Convolution v4

InfoBatch

Lossless Training Speed Up by Unbiased Dynamic Data Pruning

VIRL

Code for V-IRL: Grounding Virtual Intelligence in Real Life

particle-sfm

ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild. ECCV 2022.

MMVP

Forge_VFM4AD

A comprehensive survey of forging vision foundation models for autonomous driving, including challenges, methodologies, and opportunities.

JourneyDB

iclr2024-openreview-submissions

ICLR 2024 OpenReivew Submission Data

ZeroShape

Code repository for "ZeroShape: Regression-based Zero-shot Shape Reconstruction".

clip_prs

official implementation of "Interpreting CLIP's Image Representation via Text-Based Decomposition"

EvalCrafter

[CVPR 2024] EvalCrafter: Benchmarking and Evaluating Large Video Generation Models

360DVD

[CVPR2024] 360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model

POP3D

Source code for NeurIPS paper "POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images"

Optix

Memory Efficient Training Framework for Large Video Generation Model