RunningHub workflow page: https://www.runninghub.ai/zh-cn/post/2108582772978110465?inviteCode=rh-v1111
Bilibili tutorial video: https://www.bilibili.com/video/BV1SEJm6PE22/
# MiniMax H3 — Segmentation-Assisted Local Editing
## Purpose and audience
Inspect source-video and segmentation-mask routing in a three-clone local-edit graph. 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_hybrid_fl2va_ref2va_b25-49-int8.safetensors`, `minimax_h3_fun_controlnet_union_pruned_int8_convrot.safetensors`, `minimax_h3_fun_controlnet_union_2.0_pruned_int8_convrot.safetensors`, `SeC-4B-bf16.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
184 nodes/306 links. The middle main branch is active; outer branches are bypassed. Active MODE175=2 selects inpaint inputs and gates off structural control. AIO stores Canny768 despite stale Depth labels. Source106 skips24 frames and requests a four-second scene through the planner.
## How to prepare
Replace the active video and refresh SeC positive/negative points against actual frames. Grown mask and source video enter Union. Native video-reference ports are unlinked, and image loaders feeding the active reference nodes are bypassed. LOW uses the Union-processed model, HIGH the selected base-loader path directly.
## Known limitations
Three clones are not three verified successful outputs. Cached canvas coordinates and preview images do not prove tracking or mask alignment. Generated audio feeds the active trim/save route; extra bypassed saves and an unconnected SaveImage are not finished artifacts. The active patch filename lacks _2.0 while outer clones select it.
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
- 04: [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/2108582772978110465?inviteCode=rh-v1111
Bilibili tutorial video: https://www.bilibili.com/video/BV1SEJm6PE22/
# MiniMax H3 — Segmentation-Assisted Local Editing
## Purpose and audience
Inspect source-video and segmentation-mask routing in a three-clone local-edit graph. 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_hybrid_fl2va_ref2va_b25-49-int8.safetensors`, `minimax_h3_fun_controlnet_union_pruned_int8_convrot.safetensors`, `minimax_h3_fun_controlnet_union_2.0_pruned_int8_convrot.safetensors`, `SeC-4B-bf16.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
184 nodes/306 links. The middle main branch is active; outer branches are bypassed. Active MODE175=2 selects inpaint inputs and gates off structural control. AIO stores Canny768 despite stale Depth labels. Source106 skips24 frames and requests a four-second scene through the planner.
## How to prepare
Replace the active video and refresh SeC positive/negative points against actual frames. Grown mask and source video enter Union. Native video-reference ports are unlinked, and image loaders feeding the active reference nodes are bypassed. LOW uses the Union-processed model, HIGH the selected base-loader path directly.
## Known limitations
Three clones are not three verified successful outputs. Cached canvas coordinates and preview images do not prove tracking or mask alignment. Generated audio feeds the active trim/save route; extra bypassed saves and an unconnected SaveImage are not finished artifacts. The active patch filename lacks _2.0 while outer clones select it.
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
- 04: [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