RunningHub workflow page: https://www.runninghub.ai/zh-cn/post/2106048566154698754?inviteCode=rh-v1111
Bilibili tutorial video: https://www.bilibili.com/video/BV1VjaD6jEU3/
# MiniMax H3 — Editing Without Manual Audio Injection
## Purpose and audience
Inspect the file labeled silent while distinguishing disabled audio conditioning from output soundtrack connections. Intended for users who can inspect matching ComfyUI dependencies and actual output media. This is a workflow resource, not a tested model release.
## Asset references
`minimax_h3_hybrid_fl2va_ref2va_zs05_b25-49_int8.safetensors`, `qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors`, `minimax_h3_video_vae_int8_convrot.safetensors`, `minimax_h3_audio_vae_fp32.safetensors`, `video_depth_anything_vits.pth`.
The main VDN composers reference OpenVDN/vdn-minimax-h3 and stage_dmd_8nfe. These are configuration references, not measured NFE, timing, memory, or compatibility results. Resolve matching SeC, VideoDepthAnything, H3 conditioning/VDN, audiovisual latent, mask, and save-node implementations. The SeC loader’s bfloat16 selection does not establish a checkpoint filename. Weights and selected input media are not bundled.
## Saved setup
38 nodes/54 links. Five manual audio-latent nodes are bypassed; planner and sampler take the conditioning template directly. RGB/depth composite21 and appearance image801 feed reference conditioning. A roughly0.9MP branch supplies requested dimensions; loaded-video metadata supplies frame count/fps.
## How to prepare
Replace source footage and the reference image, refresh segmentation points, and inspect the hybrid reference. Check actual loaded count under the 124-frame cap at requested24fps. Both CreateVideo nodes still take source audio; explicitly configure and test output sound if muted delivery is required.
## Known limitations
Silent is a source label, not proof of a muted MP4. The graph has no AudioMix or Face Refine chain despite inherited notes referring to them. Hybrid RGB/depth is a conditioning input, not final original-background restoration. No motion, identity, scene, or timing preservation is verified.
The RGB/depth blend is an input reference. Prompts asking for unchanged motion, identity or scenery do not prove preservation. Refresh points and inspect actual results, audio and filenames after a small run. No new inference, performance, visual/audio, or license verification is included.
## Files and version note
- 02: [Workflow JSON]() · [Selected cover]()
Historical VHS input-preview metadata is removed from distribution copies. Point-editor state, including embedded source imagery, is retained pending content/rights review. All other data is unchanged; originals are preserved. Selected covers are not independently verified inference samples.
This descriptive copy is not a remote release, model upgrade or passed benchmark.
## Tutorial and rights
[Source-provided tutorial](https://www.youtube.com/watch?v=UespHFT9cjc), not live-verified. The workflows are supplied through AI-KSK; confirm permissions for code, weights, nodes, source footage, identities, reference/editor images, covers and audio separately. No blanket commercial license is asserted.