Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models

A Comprehensive Toolkit for High-Quality PDF Content Extraction

GaussianDreamerPro: Text to Manipulable 3D Gaussians with Highly Enhanced Quality

🎉CUDA/C++ 笔记 / 大模型手撕CUDA / 技术博客，更新随缘: flash_attn、sgemm、sgemv、warp reduce、block reduce、dot product、elementwise、softmax、layernorm、rmsnorm、hist etc.

[ECCV'24] GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image

SEED-Story: Multimodal Long Story Generation with Large Language Model

a research paper for generative cartoon interpolation

This repository contains demos I made with the Transformers library by HuggingFace.

A modular differential gaussian rasterization library.

The official implementation of "CityDreamer: Compositional Generative Model of Unbounded 3D Cities". (Xie et al., CVPR 2024)

[CVPR 2024] Code release for "InstanceDiffusion: Instance-level Control for Image Generation"

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

Singing synthesis from MIDI file

AI based tool to convert vocals lyrics and pitch from music to autogenerate Ultrastar Deluxe, Midi and notes. It automatic tapping, adding text, pitch vocals and creates karaoke files.

Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

Implementation of CVPR'20 Oral: Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image

ViewDiff generates high-quality, multi-view consistent images of a real-world 3D object in authentic surroundings. (CVPR2024).

[SIGGRAPH 2024] Coin3D: Controllable and Interactive 3D Assets Generation with Proxy-Guided Conditioning

Compose multimodal datasets 🎹

Vector Neurons: A General Framework for SO(3)-Equivariant Networks

Official code for "Style Aligned Image Generation via Shared Attention"

All NeRF&3DGS-related papers at CVPR

😎 A list of awesome scene understanding papers.

A sd-webui extension for utilizing DanTagGen to "upsample prompts".

InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

[CVPR 2024] Official implementation of "DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations"

[ICCV 2023] Consistent Image Synthesis and Editing