Official Implementation of Video-T1: Test-Time Scaling for Video Generation

TTS Towards Human-Sounding Speech

Code of LHM: Large Animatable Human Reconstruction Model for Single Image to 3D in Seconds

🔥 InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity

Unleashing Vecset Diffusion Model for Fast Shape Generation within 1 Second.

This is the official repo for the paper "LLM-FE"

Official Implementation of Rectified Flow (ICLR2023 Spotlight)

The official implementation of "Neighboring Autoregressive Modeling for Efficient Visual Generation"

[ARXIV'25] ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

Autoregressive Image Generation with Randomized Parallel Decoding

Distilling Diversity and Control in Diffusion Models

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

The official implementation of our paper "CoRe^2: Collect, Reflect and Refine to Generate Better and Faster".

Thera: Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fields

A Conversational Speech Generation Model

High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.

Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

An Efficient Text-to-Image Generation Pretrain Pipeline

Extend OpenRLHF to support LMM RL training for reproduction of DeepSeek-R1 on multimodal tasks.

Model Context Protocol Servers

zero-shot voice conversion & singing voice conversion, with real-time support

YOLOE: Real-Time Seeing Anything

This is the first paper to explore how to effectively use RL for MLLMs and introduce Vision-R1, a reasoning MLLM that leverages cold-start initialization and RL training to incentivize reasoning ca…

A series of technical report on Slow Thinking with LLM

Explore the Multimodal “Aha Moment” on 2B Model