-
ZheJiang University
- HangZhou
- https://abyssgaze.github.io
Starred repositories
A unified framework for 3D content generation.
Open-Sora: Democratizing Efficient Video Production for All
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
Official implementation of SEED-LLaMA (ICLR 2024).
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation
π¦π Build context-aware reasoning applications
Code for 3D-LLM: Injecting the 3D World into Large Language Models
An open source implementation of CLIP.
Official implementations for paper: Anydoor: zero-shot object-level image customization
[CVPR 2024] MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model
π€ Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.
Code repository for the CVPR2023 publication "HoloDiffusion: Training a 3D diffusion model using 2D Images"
[CVPR2024, Highlight] Official code for DragDiffusion
Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)
mPLUG-Owl: The Powerful Multi-modal Large Language Model Family
ONNX-compatible DeDoDe πΆ Detect, Don't Describe - Describe, Don't Detect, for Local Feature Matching. Supports TensorRT π
π€ image matching toolbox webui
Generative Agents: Interactive Simulacra of Human Behavior
[NeurIPS 2023] Official code of "One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization"
Generate 3D objects conditioned on text or images
GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)
Implementation of Toolformer, Language Models That Can Use Tools, by MetaAI
[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.
[3DV 2024 Oral] DeDoDe πΆ Detect, Don't Describe --- Describe, Don't Detect, for Local Feature Matching
LightGlue: Local Feature Matching at Light Speed (ICCV 2023)