pkulwj1994

3DFuse

Official implementation of "Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation"

3dgp

3D generation on ImageNet [ICLR 2023]

a-nice-mc

Code for "A-NICE-MC: Adversarial Training for MCMC"

ac-gan

A tensorflow implementation of google's AC-GAN ( Auxiliary Classifier GAN ).

accelerate

🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision

ada-hessian

Easy-to-use AdaHessian optimizer (PyTorch)

adahessian

ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning

ade-code

diff_instruct

official code for Diff-Instruct algorithm for one-step diffusion distillation

diff_instruct_pp

We introduce Diff-Instruct++, a novel approach for human preference alignment of 1-step text-to-image generation.

pkulwj1994/diff_instruct

official code for Diff-Instruct algorithm for one-step diffusion distillation

pkulwj1994/awesome-demos

links and status of cool gradio demos

pkulwj1994/BLIP

PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

pkulwj1994/DGMs-for-Offline-Policy-Learning

This repository provides a survey on the applications of deep generative models for offline reinforcement learning and imitation learning. We cover multiple deep generative models, including VAEs, GANs, Normalizing Flows, Transformers, and Diffusion Models.

pkulwj1994/Diffusion_Trusted_Q_Learning

[DTQL] Diffusion Trusted Q-Learning for Offline RL — Official PyTorch Implementation

pkulwj1994/DMD2

pkulwj1994/DreamReward

[ECCV 2024] DreamReward: Text-to-3D Generation with Human Preference

pkulwj1994/ect

Consistency Models Made Easy

pkulwj1994/fast-stable-diffusion

fast-stable-diffusion + DreamBooth

pkulwj1994/Fengshenbang-LM

Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。

pkulwj1994/flash-attention

Fast and memory-efficient exact attention

pkulwj1994/GigaGAN

pkulwj1994/img2dataset

Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

pkulwj1994/kaolin

A PyTorch Library for Accelerating 3D Deep Learning Research

pkulwj1994/llm_decoding

pkulwj1994/meow

Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow

pkulwj1994/minddiffusion

A collection of diffusion models based on MindSpore

pkulwj1994/open_clip

An open source implementation of CLIP.

pkulwj1994/open_flamingo

An open-source framework for training large multimodal models.

pkulwj1994/pkulwj1994.github.io

Weijian Luo homepage

pkulwj1994/poisson-jump

Official Implementation of Paper "Learning to Jump: Thinning and Thickening Latent Counts for Generative Modeling" (ICML 2023)

pkulwj1994/pytorch-model-train-template

pytorch单精度、半精度、混合精度、单卡、多卡（DP / DDP）、FSDP、DeepSpeed模型训练代码，并对比不同方法的训练速度以及GPU内存的使用

pkulwj1994/RWKV-LM

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

pkulwj1994/S2AC-Energy-Based-RL-with-Stein-Soft-Actor-Critic

pkulwj1994/SiD

pkulwj1994/SimpleTuner

A general fine-tuning kit geared toward diffusion models.

pkulwj1994/SnapFusion

pkulwj1994/threestudio

A unified framework for 3D content generation.

pkulwj1994/VAR-CLIP

Implements VAR+CLIP for image generation

pkulwj1994/x-flux