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
Description
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