DeepEP: an efficient expert-parallel communication library

HunyuanVideo: A Systematic Framework For Large Video Generation Model

Accepted as [NeurIPS 2024] Spotlight Presentation Paper

Official repository for the paper PLLaVA

Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.

[NeurIPS 2024] Official implementation of "Faster Diffusion: Rethinking the Role of UNet Encoder in Diffusion Models"

PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

Official Repo for the Paper: CHATANYTHING: FACETIME CHAT WITH LLM-ENHANCED PERSONAS

[CVPR'24 Highlight] Official PyTorch implementation of CoDeF: Content Deformation Fields for Temporally Consistent Video Processing

Implementation of GigaGAN, new SOTA GAN out of Adobe. Culmination of nearly a decade of research into GANs

[ICCV2023] Dataset Quantization

[CVPR 2023] DepGraph: Towards Any Structural Pruning

Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)

A curated list of recent diffusion models for video generation, editing, and various other applications.

Home of StarCoder: fine-tuning & inference!

BuboGPT: Enabling Visual Grounding in Multi-Modal LLMs

Generative Models by Stability AI

Nightly release of ControlNet 1.1

ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation (NeurIPS 2023 Spotlight)

[CVPR 2023 Highlight] Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatars

InternGPT (iGPT) is an open source demo platform where you can easily showcase your AI models. Now it supports DragGAN, ChatGPT, ImageBind, multimodal chat like GPT-4, SAM, interactive image editin…

Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc. (ACM MM)

本人的科研经验

[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything