🎬 DMAD Demo

4-step MiniMax-H3 Text-to-Audio-Video Generation

Try the Demo

DMAD (Distribution Matching as Adversarial Distillation) distills a 50-step teacher into a 4-step student model, generating high-quality videos with synchronized stereo audio in just 4 denoising steps.

🚀 Launch Live Demo

Key Features

⚡ 4-Step Generation

Distilled from 50 steps down to just 4 denoising steps for fast inference

🎵 Native Audio

Generates synchronized stereo soundtrack alongside video

🎨 High Quality

1344x768 resolution at 24fps, ~5 seconds of video

🧠 33B Model

Based on MiniMax-H3 omni-modal text-to-audio-video architecture

Resources