MeiGen-AI ORG

​​Unlimited-length talking video generation​​ that supports image-to-video and video-to-video generation

[NeurIPS 2025] Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation

[ICLR2026] Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework

LLIA - Enabling Low-Latency Interactive Avatars: Real-Time Audio-Driven Portrait Video Generation with Diffusion Models

The homepage of LongCat-Video-Avatar

On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators

[CVPR2026] PosterOmni: One model for poster creation—unifying local edits and global design for generalized multi-task image/poster-to-poster generation.

[ICML 2026] | Scaling Interactive World Models to 1000-Frame Horizons via Pose-Free Hierarchical Memory

Homepage of LongCat-Video-Avatar 1.5

Self-Evolving Image Generation Agents via Tool-Orchestrated Visual Experience Distillation

[CVPR2026] PosterReward: Unlocking Accurate Evaluation for High-Quality Graphic Design Generation

Chat-Driven Video Editing Agent with Real-Time Rendering

Failure makes the agent stronger: Enhancing Accuracy through Structured Reflection for Reliable Tool Interactions

[CVPR2026] PositionIC: Unified Position and Identity Consistency for Image Customization

No description.

No description.