Add Realistic Audio to AI Video! ComfyUI MMAudio Workflow — v1.0

This ComfyUI MMAudio workflow is for adding realistic audio to AI video: it takes a video path, loads MMAudio features and models, samples and previews audio, and provides a video-combine output stage.

The stages cover video loading and video information, MMAudio feature and model loading, audio sampling, audio preview, and video combining.

VHS_LoadVideoPath loads the video path, and VHS_VideoInfo provides video information.

MMAudioFeatureUtilsLoader and MMAudioModelLoader load features and models, while MMAudioSampler samples audio.

PreviewAudio previews the audio, and VHS_VideoCombine provides the video-combine output stage.

The workflow is published on Civitai by Lordcaocao2025 at https://civitai.com/models/2367459.

The model files are apple_DFN5B-CLIP-ViT-H-14-384_fp16.safetensors, mmaudio_large_44k_v2_fp16.safetensors, mmaudio_synchformer_fp16.safetensors, and mmaudio_vae_44k_fp16.safetensors.

The node packs are comfyui-mmaudio and comfyui-videohelpersuite.

Before use, confirm that all four model files and both node packs are available.

Vorschlag · nicht geprüft

The Civitai page has an embedded YouTube video but no distinct written description, so verify setup details before use.

Vorschlag · nicht geprüft