#
Lists (1)
Starred repositories
OmniVinci is an omni-modal LLM for joint understanding of vision, audio, and language.
A character-level discrete diffusion transformer trained on Tiny Shakespeare
A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.
ElevenLabs UI is a component library and custom registry built on top of shadcn/ui to help you build multimodal agents faster.
LNbits, free and open-source Lightning wallet and accounts system.
Discrete Flow Matching implemented in PyTorch
[ICCV 2025] Inpaint4Drag: Repurposing Inpainting Models for Drag-Based Image Editing via Bidirectional Warping
[Preprint 2025] Ditto: Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset
Easy-to-use chat interface for running and testing Aquiles AI models locally. Supports medical reasoning (Asclepio-8B) and image-to-code generation (Qwen2.5-VL).
Implements harmful/harmless refusal removal using pure HF Transformers
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
Lumina-DiMOO - An Open-Sourced Multi-Modal Large Diffusion Language Model
An extremely fast Python type checker and language server, written in Rust.
This is a demo implementation of a serverless hosting platform built with: Docker, FastAPI and Next.js
Wan: Open and Advanced Large-Scale Video Generative Models
基于多智能体LLM的中文金融交易框架 - TradingAgents中文增强版
Secure and fast microVMs for serverless computing.
Post-training with Tinker
A minimal implementation of DeepMind's Genie world model
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory…
Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation
Creating an ASGI server and its minimalist web framework from scratch
Train transformer language models with reinforcement learning.