RunningHub workflow page: https://www.runninghub.ai/zh-cn/post/2108580258148929538?inviteCode=rh-v1111
Bilibili tutorial video: https://www.bilibili.com/video/BV1SEJm6PE22/
# MiniMax H3 — Audio Latents and Two Output Routes
## Purpose and audience
Combine a reference image with manually encoded vocal latents while separately routing selected source audio to output. Intended for users who can resolve matching custom nodes, inspect media permissions, and verify actual outputs. This is a workflow resource, not a tested model release.
## Required asset references
`qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors`, `minimax_h3_video_vae_fp16.safetensors`, `minimax_h3_audio_vae_fp32.safetensors`, `minimax_h3_latent_upscaler_3d_fp16.safetensors`, `minimax_h3_fl2va_pruned_int8_convrot.safetensors`.
The VDN composers reference OpenVDN/vdn-minimax-h3 and stage_dmd_8nfe; refinement plans store4. These describe two-pass intent, not measured evaluation counts, a twelve-step ordinary sampler, or a verified distilled-LoRA filename. Reconcile/audio-audit settings are requested policies, not passed tests. Resolve exact node versions and assets before queueing; no installation, GPU, speed, lip-sync, voice-preservation, or license verification is included.
## Saved configuration
44 nodes/80 links. Uploaded audio feeds a window whose duration comes from the loader-reported length. Separated vocals are encoded and given a zero noise mask. The LOW template is split before concatenating its video latent with the injected audio.
## How to prepare
Replace the image/audio selections and inspect the actual window. Selector47 supplies544×736, overriding stale960/544 labels. The ×2 upscale suggests portrait HIGH controls around1088×1472, not a fixed landscape canvas. Inspect both LOW and HIGH decode/trim/save chains; both saves are active and share a prefix.
## Known limitations
Decoded generated-audio outputs are unconnected; selected original audio supplies both trims. This routing does not prove bit-exact passthrough, lip sync, voice preservation, or successful temporal fitting. Check actual dimensions, duration, and output filenames.
Inspect actual output dimensions, duration, sound, input alignment, and unintended edits. Do not turn a node title, saved preview, or audit setting into a claim of a successful render.
## Files and version note
- 02: [Workflow JSON]() · [Selected cover]()
Historical VHS video-preview metadata is omitted from distribution copies. Other data is retained, including point-editor images where present: inspect their contents and rights before any publication. Source originals are unchanged. Selected covers are not verified inference results. Input media, model weights, and VDN artifacts are not bundled.
This is new local descriptive copy, not a remote publication or an announcement of a model upgrade. Source discrepancies are documented, not silently corrected.
## Tutorial, attribution, and rights
[Source-provided tutorial](https://www.youtube.com/watch?v=WdAaPq2Xa0I), not live-verified here. The workflows are supplied through AI-KSK. Verify workflow, node, model, source-video, image, voice, and artwork rights separately; no universal commercial permission is asserted.
Source-listed resources
Additional entry points listed by the episode source. Some contain referral/affiliate codes; no bonus, price, quota, or speed is asserted here.
- RunningHub registration (international, invite code rh-v1111): https://www.runninghub.ai/?inviteCode=rh-v1111
- RunningHub registration (China-site mirror, same invite code): https://www.runninghub.cn/?inviteCode=rh-v1111
- AI-KSK workflow catalog on the international site: https://www.runninghub.ai/zh-cn/user-center/1846601088051884033/userPost?inviteCode=rh-v1111
- Quick-create entry (international site): https://www.runninghub.ai/ai-generator/2046514150500524034?inviteCode=rh-v1111
- VIP rights entry (international site): https://www.runninghub.ai/vip-rights/3?inviteCode=rh-v1111
- Workflow model files (Quark netdisk, China): https://pan.quark.cn/s/9ec095b95838
- Cloud GPU signup (Compshare; referral code in the link): https://passport.compshare.cn/register?referral_code=A7fTQUYY9lCDFJwA6MMvoq
- Cloud image index for Compshare (Notion): https://www.notion.so/2b72459a3ac6808f8282f2c687ed8f52
- Support the channel (Ko-fi): https://ko-fi.com/aiksk
Description
RunningHub workflow page: https://www.runninghub.ai/zh-cn/post/2108580258148929538?inviteCode=rh-v1111
Bilibili tutorial video: https://www.bilibili.com/video/BV1SEJm6PE22/
# MiniMax H3 — Audio Latents and Two Output Routes
## Purpose and audience
Combine a reference image with manually encoded vocal latents while separately routing selected source audio to output. Intended for users who can resolve matching custom nodes, inspect media permissions, and verify actual outputs. This is a workflow resource, not a tested model release.
## Required asset references
`qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors`, `minimax_h3_video_vae_fp16.safetensors`, `minimax_h3_audio_vae_fp32.safetensors`, `minimax_h3_latent_upscaler_3d_fp16.safetensors`, `minimax_h3_fl2va_pruned_int8_convrot.safetensors`.
The VDN composers reference OpenVDN/vdn-minimax-h3 and stage_dmd_8nfe; refinement plans store4. These describe two-pass intent, not measured evaluation counts, a twelve-step ordinary sampler, or a verified distilled-LoRA filename. Reconcile/audio-audit settings are requested policies, not passed tests. Resolve exact node versions and assets before queueing; no installation, GPU, speed, lip-sync, voice-preservation, or license verification is included.
## Saved configuration
44 nodes/80 links. Uploaded audio feeds a window whose duration comes from the loader-reported length. Separated vocals are encoded and given a zero noise mask. The LOW template is split before concatenating its video latent with the injected audio.
## How to prepare
Replace the image/audio selections and inspect the actual window. Selector47 supplies544×736, overriding stale960/544 labels. The ×2 upscale suggests portrait HIGH controls around1088×1472, not a fixed landscape canvas. Inspect both LOW and HIGH decode/trim/save chains; both saves are active and share a prefix.
## Known limitations
Decoded generated-audio outputs are unconnected; selected original audio supplies both trims. This routing does not prove bit-exact passthrough, lip sync, voice preservation, or successful temporal fitting. Check actual dimensions, duration, and output filenames.
Inspect actual output dimensions, duration, sound, input alignment, and unintended edits. Do not turn a node title, saved preview, or audit setting into a claim of a successful render.
## Files and version note
- 02: [Workflow JSON]() · [Selected cover]()
Historical VHS video-preview metadata is omitted from distribution copies. Other data is retained, including point-editor images where present: inspect their contents and rights before any publication. Source originals are unchanged. Selected covers are not verified inference results. Input media, model weights, and VDN artifacts are not bundled.
This is new local descriptive copy, not a remote publication or an announcement of a model upgrade. Source discrepancies are documented, not silently corrected.
## Tutorial, attribution, and rights
[Source-provided tutorial](https://www.youtube.com/watch?v=WdAaPq2Xa0I), not live-verified here. The workflows are supplied through AI-KSK. Verify workflow, node, model, source-video, image, voice, and artwork rights separately; no universal commercial permission is asserted.
Source-listed resourcesAdditional entry points listed by the episode source. Some contain referral/affiliate codes; no bonus, price, quota, or speed is asserted here.
- RunningHub registration (international, invite code rh-v1111): https://www.runninghub.ai/?inviteCode=rh-v1111
- RunningHub registration (China-site mirror, same invite code): https://www.runninghub.cn/?inviteCode=rh-v1111
- AI-KSK workflow catalog on the international site: https://www.runninghub.ai/zh-cn/user-center/1846601088051884033/userPost?inviteCode=rh-v1111
- Quick-create entry (international site): https://www.runninghub.ai/ai-generator/2046514150500524034?inviteCode=rh-v1111
- VIP rights entry (international site): https://www.runninghub.ai/vip-rights/3?inviteCode=rh-v1111
- Workflow model files (Quark netdisk, China): https://pan.quark.cn/s/9ec095b95838
- Cloud GPU signup (Compshare; referral code in the link): https://passport.compshare.cn/register?referral_code=A7fTQUYY9lCDFJwA6MMvoq
- Cloud image index for Compshare (Notion): https://www.notion.so/2b72459a3ac6808f8282f2c687ed8f52
- Support the channel (Ko-fi): https://ko-fi.com/aiksk