[NeurIPS 2025 Spotlight] Demo implementation of MoCha Towards Movie-Grade Talking Character Synthesis

Wan: Open and Advanced Large-Scale Video Generative Models

Open-source unified multimodal model

Code for: "Long-Context Autoregressive Video Modeling with Next-Frame Prediction"

Official inference repo for FLUX.1 models

Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation

"Effective Whole-body Pose Estimation with Two-stages Distillation" (ICCV 2023, CV4Metaverse Workshop)

A generative world for general-purpose robotics & embodied AI learning.

HunyuanVideo: A Systematic Framework For Large Video Generation Model

Code for [CVPR 2025] ROICtrl: Boosting Instance Control for Visual Generation

[ICCV2025] UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image Personalization

Multimodal Models in Real World

Allegro is a powerful text-to-video model that generates high-quality videos up to 6 seconds at 15 FPS and 720p resolution from simple text input.

[ICLR 2025] AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark

Next-Token Prediction is All You Need

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.

StoryMaker: Towards consistent characters in text-to-image generation

MoVQGAN - model for the image encoding and reconstruction

[ICLR2025] Kolmogorov-Arnold Transformer

SEED-Story: Multimodal Long Story Generation with Large Language Model

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

Official Pytorch implementation of StreamV2V.

Extract frames and motion vectors from H.264 and MPEG-4 encoded video.

A collection of resources on controllable generation with text-to-image diffusion models.

[T-PAMI 2025] V3D: Video Diffusion Models are Effective 3D Generators

Open-Sora: Democratizing Efficient Video Production for All

InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥

[ECCV 2024] DragAnything: Motion Control for Anything using Entity Representation

[ECCV 2024] Single Image to 3D Textured Mesh in 10 seconds with Convolutional Reconstruction Model.