Mmdisco: Multi-modal Discriminator-guided Cooperative Diffusion For Joint Audio And Video Generation

Abstract

This study aims to construct an audio-video generative model with minimal computational cost by leveraging pre-trained single-modal generative models for audio and video. To achieve this, we propose a novel method that guides single-modal models to cooperatively generate well-aligned samples across modalities. Specifically, given two pre-trained base diffusion models, we train a lightweight joint guidance module to adjust scores separately estimated by the base models to match the score of joint distribution over audio and video. We show that this guidance can be computed using the gradient of the optimal discriminator, which distinguishes real audio-video pairs from fake ones independently generated by the base models. Based on this analysis, we construct a joint guidance module by training this discriminator. Additionally, we adopt a loss function to stabilize the discriminator's gradient and make it work as a noise estimator, as in standard diffusion models. Empirical evaluations on

Stats

• citations0
• S2 citations—
• github stars8
• HF likes0
• heat score1.91
• arxiv keyhayakawa2024mmdisco

Related papers

• A Simple But Strong Baseline For Sounding Video Generation: Effective Adaptation Of Audio And Video Diffusion Models For Joint Generation (2024)3.58
• Collaborative Learning To Generate Audio-video Jointly (2021)7.16
• Diffusion-based Generative Modeling With Discriminative Guidance For Streamable Speech Enhancement (2024)7.16
• Diff-foley: Synchronized Video-to-audio Synthesis With Latent Diffusion Models (2023)0.00
• Diffgap: A Lightweight Diffusion Module In Contrastive Space For Bridging Cross-model Gap (2025)3.58
• 3mdit: Unified Tri-modal Diffusion Transformer For Text-driven Synchronized Audio-video Generation (2025)0.00
• Audiomog: Guiding Audio Generation With Mixture-of-guidance (2025)0.00
• Adversarial Training Of Denoising Diffusion Model Using Dual Discriminators For High-fidelity Multi-speaker TTS (2023)2.26