一个基于 ChatGPT、帮助更多的人维护自身权益的 AI 律师

An open-source framework for training large multimodal models.

Fast and memory-efficient exact attention

A collection of diffusion models based on MindSpore

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。

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,…

fast-stable-diffusion + DreamBooth

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

An open source implementation of CLIP.

A unified framework for 3D content generation.

links and status of cool gradio demos

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

A PyTorch Library for Accelerating 3D Deep Learning Research

Code for "Coin Sampling: Gradient-Based Bayesian Inference without Learning Rates" (ICML 2023)

[SIGGRAPH'22] StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets

[ICME-2023] Official implementation for "Accelerating Diffusion Sampling with Classifier-based Feature Distillation".

Code accompanying the paper "Neural Markov Jump Processes" published at ICML 2023.

Code for Cross-Modal 3D Shape Generation and Manipulation (ECCV 2022)

3D generation on ImageNet [ICLR 2023]

DALL·E Mini - Generate images from a text prompt

Generate 3D objects conditioned on text or images

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

Official repo for Discriminator Guidance for ImageNet256.

Official repo for Discriminator Guidance.

Code for "Particle algorithms for maximum likelihood training of latent variable models" (Kuntz, Lim, Johansen, AISTATS, 2023).

Official repo for consistency models.

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