Starred repositories
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
FantasyPortrait: Enhancing Multi-Character Portrait Animation with Expression-Augmented Diffusion Transformers
Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation"
Fast, Sharp & Reliable Agentic Intelligence
[ICLR 2026] UniVideo: Unified Understanding, Generation, and Editing for Videos
Step3-VL-10B: A compact yet frontier multimodal model achieving SOTA performance at the 10B scale, matching open-source models 10-20x its size.
GLM-Image: Auto-regressive for Dense-knowledge and High-fidelity Image Generation.
A framework for efficient model inference with omni-modality models
This project is the official implementation of "UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation"
FlatNCE: A Novel Contrastive Representation Learning Objective
PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)
HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
The homepage of LongCat-Video-Avatar
Exploring Multimodal Diffusion Transformers for Enhanced Prompt-based Image Editing
[ICML2025] An 8-step inversion and 8-step editing process works effectively with the FLUX-dev model. (3x speedup with results that are comparable or even superior to baseline methods)
Official inference repo for FLUX.2 models
Scalable data pre processing and curation toolkit for LLMs
HunyuanVideo-1.5: A leading lightweight video generation model
The repository provides code for running inference with the SAM 3D Body Model (3DB), links for downloading the trained model checkpoints and datasets, and example notebooks that show how to use the…
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…
Official Pytorch Implementation for "Time-to-Move: Training-Free Motion Controlled Video Generation via Dual-Clock Denoising"
MotionStream: Real-Time Video Generation with Interactive Motion Controls