<div data-youtube-video="https://youtu.be/WdAaPq2Xa0I"><iframe src="https://www.youtube.com/embed/WdAaPq2Xa0I" width="853" height="480" allowfullscreen></iframe></div> 
 
MiniMax H3 + ControlNet Union 2.0 video control, local repaint and audio-driven digital human in one pipeline (VDN 12-step HD edition). The most complete build of this batch: everything of the MODE 123 editor plus a fixed audio-driven digital human branch. 
 
Main features: 
- Single 24fps source video (VHS force_rate=24) simultaneously drives the AIO control_video, audio extraction, SeC tracking mask and inpaint source 
- MODE switch: 1 = pure structural control, 2 = pure local repaint, 3 = control + repaint 
- Digital human branch: vocals are encoded by the LTXV audio VAE and injected with a latent noise mask; the audio T-axis is auto-fit by concatenating the full LOW AV latent (fixes the manual-vocals T=206 mismatch) 
- ControlNet Union 2.0 patch (minimax_h3_fun_controlnet_union_pruned_int8_convrot) + SeC mask with GrowMask and mask preview 
- OpenVDN DMD8 two-pass: 8NFE base, learned latent x2 upscale to 1920x1088, 4NFE refine; 16:9 or 9:16 
- Native audio AV output, 24fps, approx 1080P safe save 
 
Suggested workflow: 
1. Load one source video; the graph standardizes it to 24fps for control, tracking, inpaint and audio 
2. Pick MODE and the AIO preprocessor; for the digital human output the vocals track from the same video is used automatically 
3. Run the graph and export the safe AV save (approx 1080P, 24fps) 
 
Dependencies: 
- minimax_h3_fl2va_pruned_int8_convrot.safetensors (H3 base UNET) 
- minimax_h3_fun_controlnet_union_pruned_int8_convrot.safetensors (Union 2.0 patch) 
- qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors (CLIP), video/audio VAEs, LTXV audio VAE encoder 
- minimax_h3_latent_upscaler_3d_fp16.safetensors (learned latent x2) 
- OpenVDN/vdn-minimax-h3 (DMD8 stage), KSK T8 custom nodes, SeC model 
 
RunningHub workflow page: https://www.runninghub.ai/zh-cn/post/2108575214790520833?inviteCode=rh-v1111 
Bilibili tutorial video: https://www.bilibili.com/video/BV1pTph6EEUv/ 
RunningHub registration with invite code rh-v1111 (1000 RH coins): https://www.runninghub.ai/?inviteCode=rh-v1111

MiniMax H3 CN2 Control & Digital Human

<div data-youtube-video="https://youtu.be/WdAaPq2Xa0I"></div> 
 
MiniMax H3 + ControlNet Union 2.0 video control, local repaint and audio-driven digital human in one pipeline (VDN 12-step HD edition). The most complete build of this batch: everything of the MODE 123 editor plus a fixed audio-driven digital human branch. 
 
Main features: 
- Single 24fps source video (VHS force_rate=24) simultaneously drives the AIO control_video, audio extraction, SeC tracking mask and inpaint source 
- MODE switch: 1 = pure structural control, 2 = pure local repaint, 3 = control + repaint 
- Digital human branch: vocals are encoded by the LTXV audio VAE and injected with a latent noise mask; the audio T-axis is auto-fit by concatenating the full LOW AV latent (fixes the manual-vocals T=206 mismatch) 
- ControlNet Union 2.0 patch (minimax_h3_fun_controlnet_union_pruned_int8_convrot) + SeC mask with GrowMask and mask preview 
- OpenVDN DMD8 two-pass: 8NFE base, learned latent x2 upscale to 1920x1088, 4NFE refine; 16:9 or 9:16 
- Native audio AV output, 24fps, approx 1080P safe save 
 
Suggested workflow: 
1. Load one source video; the graph standardizes it to 24fps for control, tracking, inpaint and audio 
2. Pick MODE and the AIO preprocessor; for the digital human output the vocals track from the same video is used automatically 
3. Run the graph and export the safe AV save (approx 1080P, 24fps) 
 
Dependencies: 
- minimax_h3_fl2va_pruned_int8_convrot.safetensors (H3 base UNET) 
- minimax_h3_fun_controlnet_union_pruned_int8_convrot.safetensors (Union 2.0 patch) 
- qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors (CLIP), video/audio VAEs, LTXV audio VAE encoder 
- minimax_h3_latent_upscaler_3d_fp16.safetensors (learned latent x2) 
- OpenVDN/vdn-minimax-h3 (DMD8 stage), KSK T8 custom nodes, SeC model 
 
RunningHub workflow page: https://www.runninghub.ai/zh-cn/post/2108575214790520833?inviteCode=rh-v1111 
Bilibili tutorial video: https://www.bilibili.com/video/BV1pTph6EEUv/ 
RunningHub registration with invite code rh-v1111 (1000 RH coins): https://www.runninghub.ai/?inviteCode=rh-v1111

05_minimax-h3-cn2-control-digital-human.json

v1.0

<div data-youtube-video="https://youtu.be/WdAaPq2Xa0I"><iframe src="https://www.youtube.com/embed/WdAaPq2Xa0I" width="853" height="480" allowfullscreen></iframe></div> 
 
RunningHub workflow page: https://www.runninghub.ai/zh-cn/post/2108575214790520833?inviteCode=rh-v1111Bilibili tutorial video: https://www.bilibili.com/video/BV1SEJm6PE22/
# MiniMax H3 — Structural Control and Manual Audio Latents## Purpose and audienceCombine structural video control with manually injected vocal latents and a separately selected output-audio path. 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`, `minimax_h3_fun_controlnet_union_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 configuration66 nodes/99 links. MODE70=1 selects structure only. Toggle32=false selects video audio rather than the separate audio file. A five-second audio window is requested, but the video loader has no matching frame cap. DepthAnythingV2 at512 supplies the structural preprocessing path.## How to prepareCheck source footage, selected audio, and window alignment. Vocals are encoded and masked; unlike02, the complete LOW template enters the concatenation node without a separate split node. LOW receives Union processing; HIGH uses the clean loader path. Native reference-image/video/audio sockets are unlinked. Inspect final trim/save audio from the selected source.## Known limitationsHistorical notes describe intended temporal fitting, not a verified correction. Mask preview remains connected even with inpaint model inputs off. Saved point coordinates require review. Actual patch selection omits _2.0 while title/download metadata includes it; this is an unresolved asset-reference mismatch, not proof of weight contents.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- 05: [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.<h2>Source-listed resources</h2>Additional entry points listed by the episode source. Some contain referral/affiliate codes; no bonus, price, quota, or speed is asserted here.<ul><li>RunningHub registration (international, invite code rh-v1111): <a href="https://www.runninghub.ai/?inviteCode=rh-v1111" rel="ugc">https://www.runninghub.ai/?inviteCode=rh-v1111</a></li><li>RunningHub registration (China-site mirror, same invite code): <a href="https://www.runninghub.cn/?inviteCode=rh-v1111" rel="ugc">https://www.runninghub.cn/?inviteCode=rh-v1111</a></li><li>AI-KSK workflow catalog on the international site: <a href="https://www.runninghub.ai/zh-cn/user-center/1846601088051884033/userPost?inviteCode=rh-v1111" rel="ugc">https://www.runninghub.ai/zh-cn/user-center/1846601088051884033/userPost?inviteCode=rh-v1111</a></li><li>Quick-create entry (international site): <a href="https://www.runninghub.ai/ai-generator/2046514150500524034?inviteCode=rh-v1111" rel="ugc">https://www.runninghub.ai/ai-generator/2046514150500524034?inviteCode=rh-v1111</a></li><li>VIP rights entry (international site): <a href="https://www.runninghub.ai/vip-rights/3?inviteCode=rh-v1111" rel="ugc">https://www.runninghub.ai/vip-rights/3?inviteCode=rh-v1111</a></li><li>Workflow model files (Quark netdisk, China): <a href="https://pan.quark.cn/s/9ec095b95838" rel="ugc">https://pan.quark.cn/s/9ec095b95838</a></li><li>Cloud GPU signup (Compshare; referral code in the link): <a href="https://passport.compshare.cn/register?referral_code=A7fTQUYY9lCDFJwA6MMvoq" rel="ugc">https://passport.compshare.cn/register?referral_code=A7fTQUYY9lCDFJwA6MMvoq</a></li><li>Cloud image index for Compshare (Notion): <a href="https://www.notion.so/2b72459a3ac6808f8282f2c687ed8f52" rel="ugc">https://www.notion.so/2b72459a3ac6808f8282f2c687ed8f52</a></li><li>Support the channel (Ko-fi): <a href="https://ko-fi.com/aiksk" rel="ugc">https://ko-fi.com/aiksk</a></li></ul>

MiniMax H3 ControlNet Union 2.0 Video Control with Audio Avatar (VDN 12-Step)

<div data-youtube-video="https://youtu.be/WdAaPq2Xa0I"></div> 
 
RunningHub workflow page: https://www.runninghub.ai/zh-cn/post/2108575214790520833?inviteCode=rh-v1111Bilibili tutorial video: https://www.bilibili.com/video/BV1SEJm6PE22/
# MiniMax H3 — Structural Control and Manual Audio Latents## Purpose and audienceCombine structural video control with manually injected vocal latents and a separately selected output-audio path. 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`, `minimax_h3_fun_controlnet_union_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 configuration66 nodes/99 links. MODE70=1 selects structure only. Toggle32=false selects video audio rather than the separate audio file. A five-second audio window is requested, but the video loader has no matching frame cap. DepthAnythingV2 at512 supplies the structural preprocessing path.## How to prepareCheck source footage, selected audio, and window alignment. Vocals are encoded and masked; unlike02, the complete LOW template enters the concatenation node without a separate split node. LOW receives Union processing; HIGH uses the clean loader path. Native reference-image/video/audio sockets are unlinked. Inspect final trim/save audio from the selected source.## Known limitationsHistorical notes describe intended temporal fitting, not a verified correction. Mask preview remains connected even with inpaint model inputs off. Saved point coordinates require review. Actual patch selection omits _2.0 while title/download metadata includes it; this is an unresolved asset-reference mismatch, not proof of weight contents.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- 05: [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.<ul><li>RunningHub registration (international, invite code rh-v1111): <a href="https://www.runninghub.ai/?inviteCode=rh-v1111" rel="ugc">https://www.runninghub.ai/?inviteCode=rh-v1111</a></li><li>RunningHub registration (China-site mirror, same invite code): <a href="https://www.runninghub.cn/?inviteCode=rh-v1111" rel="ugc">https://www.runninghub.cn/?inviteCode=rh-v1111</a></li><li>AI-KSK workflow catalog on the international site: <a href="https://www.runninghub.ai/zh-cn/user-center/1846601088051884033/userPost?inviteCode=rh-v1111" rel="ugc">https://www.runninghub.ai/zh-cn/user-center/1846601088051884033/userPost?inviteCode=rh-v1111</a></li><li>Quick-create entry (international site): <a href="https://www.runninghub.ai/ai-generator/2046514150500524034?inviteCode=rh-v1111" rel="ugc">https://www.runninghub.ai/ai-generator/2046514150500524034?inviteCode=rh-v1111</a></li><li>VIP rights entry (international site): <a href="https://www.runninghub.ai/vip-rights/3?inviteCode=rh-v1111" rel="ugc">https://www.runninghub.ai/vip-rights/3?inviteCode=rh-v1111</a></li><li>Workflow model files (Quark netdisk, China): <a href="https://pan.quark.cn/s/9ec095b95838" rel="ugc">https://pan.quark.cn/s/9ec095b95838</a></li><li>Cloud GPU signup (Compshare; referral code in the link): <a href="https://passport.compshare.cn/register?referral_code=A7fTQUYY9lCDFJwA6MMvoq" rel="ugc">https://passport.compshare.cn/register?referral_code=A7fTQUYY9lCDFJwA6MMvoq</a></li><li>Cloud image index for Compshare (Notion): <a href="https://www.notion.so/2b72459a3ac6808f8282f2c687ed8f52" rel="ugc">https://www.notion.so/2b72459a3ac6808f8282f2c687ed8f52</a></li><li>Support the channel (Ko-fi): <a href="https://ko-fi.com/aiksk" rel="ugc">https://ko-fi.com/aiksk</a></li></ul>

Files with SHA256: 5a5da10f7adf3c100571b3da6f1cd9f1e193b6a612d8f0e56501ac95b096ffb7