We present Object Images (Omages): An homage to the classic Geometry Images.

Text-to-video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

From anything to mesh like human artists. Official impl. of "MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization"

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

Implementation of MeshGPT, SOTA Mesh generation using Attention, in Pytorch

From anything to mesh like human artists. Official impl. of "MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers"

ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment

Official implementation of L-MAGIC

Official code for paper: Text-to-Image Rectified Flow as Plug-and-Play Priors

MeshXL: Neural Coordinate Field for Generative 3D Foundation Models, a 3D fundamental model for mesh generation

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

Optimal Transport in the Big Data Era

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

[GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly …

🎓 Path to a free self-taught education in Computer Science!

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

FreeAskInternet is a completely free, PRIVATE and LOCALLY running search aggregator & answer generate using MULTI LLMs, without GPU needed. The user can ask a question and the system will make a mu…

Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

Official implementation of AnimateDiff.

在原版的基础上修改了显示 VLESS 配置信息转换为订阅内容。使用该脚本，你可以方便地将 VLESS 配置信息使用在线配置转换到 Clash 或 Singbox 等工具中。

The official PyTorch implementation of Google's Gemma models

Mobile-Agent: The Powerful Mobile Device Operation Assistant Family

Autonomous Agents (LLMs) research papers. Updated Daily.

A curated list of papers, code and resources pertaining to image composition/compositing or object insertion, which aims to generate realistic composite image.

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

[CVPR2024 Highlight] VBench - We Evaluate Video Generation

Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models, a no lighting baked texture generative model