Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

Audio-based Lip Synchronization for Talking Head Video

Updated to OpenVoice v2: Versatile Instant Voice Cloning

A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

Fast sdxl with higher quality

Convert LLM's coding to image generation

Depth estimation with faster inference speed, fewer parameters, and higher depth accuracy.

Extended video synthesis model that generates 128 frames

CogVLM2: Visual Language Models for Image and Video Understanding

CogVLM2: Visual Language Models for Image and Video Understanding

Generating Consistent Long Depth Sequences for Open-world Videos

Finer and Faster Text-to-Image Generation via Relay Diffusion

Diffusion-based Visual Foundation Model for High-quality Dense Prediction

Sharp Monocular Metric Depth in Less Than a Second

Efficient Visual Generation with Hybrid Autoregressive Transformer

Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

Depth Any Video with Scalable Synthetic Data

DiT-based video generation model for generating high-quality videos in real-time

Minimal and Universal Control for Diffusion Transformer - demo for Subject-driven generation

High-Fidelity Single-Step Diffusion through Dynamic Adversarial Training

Autoregressive Video Generation without Vector Quantization