RunningHub workflow page: https://www.runninghub.ai/zh-cn/post/2085223972794355714?inviteCode=rh-v1111
MiniMax H3 Digital Human - Two-Character Dialogue
Purpose: a two-character (and by extension multi-character) digital-human graph. Each character gets an image and an audio clip; the two clips are trimmed, padded and concatenated into one timeline, that combined audio is locked, and MiniMax H3 generates the matching two-person performance.
Graph (as saved)
32 nodes / 38 links / 5 groups.
- Core:
MiniMaxH3ReferenceToVideoat 1344x768, length 124,ref_image_size=match;VRGDG_MiniMaxH3AudioDriveset to lock the concatenated original audio and generate picture only. - Models: UNETLoader
minimax_h3_ref2va_int8_convrot.safetensors; CLIPLoaderqwen3vl_32b_minimax_h3_int8_convrot.safetensors(type minimax); VAELoader videominimax_h3_video_vae_fp16.safetensors+ audiominimax_h3_audio_vae_fp32.safetensors. - Sampling:
SamplerCustomAdvanced+KSamplerSelectres_multistep+BasicSchedulersimple, 20 steps, denoise 1. - Inputs: three LoadImage nodes (character 1, character 2, plus a third reference slot), two LoadAudio clips with
AudioCropat 0:00-0:05 and 0:00-0:06, twoAudioConcatnodes,EmptyAudioandPreviewAudio. Prompt addresses subjects as<Picture 1>/<Picture 2>and the audio as<Audio 1>. - Output:
VHS_VideoCombine(h264 mp4, crf 19, yuv420p). Note the saved filename prefix is stillAnimateDiff— a historical leftover in the export, not a different model path.
How to use
Feed character 1 and character 2 with their own images and audio, then write the dialogue prompt in the order the graph expects. The audio crops define who speaks when: if the two clips do not line up with the planned exchange, fix the crop times first, not the prompt. The third image slot is present in the save state; check whether you need it before queueing.
Limits and not-verified items
No inference was run for this listing: no speed, VRAM, lip-sync, voice or multi-character consistency claim is made. The saved prompts, images and audio are the author's demo content. VoxCPM and the H3 checkpoints are not bundled; check their licenses separately. The cover image is a promotional still, not a frame produced by this graph.
Tutorial: YouTube · Bilibili. Workflows supplied through AI-KSK; verify workflow, node, model, audio, likeness and cover rights separately. No blanket commercial or redistribution license is asserted.
Description
RunningHub workflow page: https://www.runninghub.ai/zh-cn/post/2085223972794355714?inviteCode=rh-v1111
MiniMax H3 Digital Human - Two-Character DialoguePurpose: a two-character (and by extension multi-character) digital-human graph. Each character gets an image and an audio clip; the two clips are trimmed, padded and concatenated into one timeline, that combined audio is locked, and MiniMax H3 generates the matching two-person performance.
Graph (as saved)32 nodes / 38 links / 5 groups.
- Core:
MiniMaxH3ReferenceToVideoat 1344x768, length 124,ref_image_size=match;VRGDG_MiniMaxH3AudioDriveset to lock the concatenated original audio and generate picture only. - Models: UNETLoader
minimax_h3_ref2va_int8_convrot.safetensors; CLIPLoaderqwen3vl_32b_minimax_h3_int8_convrot.safetensors(type minimax); VAELoader videominimax_h3_video_vae_fp16.safetensors+ audiominimax_h3_audio_vae_fp32.safetensors. - Sampling:
SamplerCustomAdvanced+KSamplerSelectres_multistep+BasicSchedulersimple, 20 steps, denoise 1. - Inputs: three LoadImage nodes (character 1, character 2, plus a third reference slot), two LoadAudio clips with
AudioCropat 0:00-0:05 and 0:00-0:06, twoAudioConcatnodes,EmptyAudioandPreviewAudio. Prompt addresses subjects as<Picture 1>/<Picture 2>and the audio as<Audio 1>. - Output:
VHS_VideoCombine(h264 mp4, crf 19, yuv420p). Note the saved filename prefix is stillAnimateDiff— a historical leftover in the export, not a different model path.
Feed character 1 and character 2 with their own images and audio, then write the dialogue prompt in the order the graph expects. The audio crops define who speaks when: if the two clips do not line up with the planned exchange, fix the crop times first, not the prompt. The third image slot is present in the save state; check whether you need it before queueing.
Limits and not-verified itemsNo inference was run for this listing: no speed, VRAM, lip-sync, voice or multi-character consistency claim is made. The saved prompts, images and audio are the author's demo content. VoxCPM and the H3 checkpoints are not bundled; check their licenses separately. The cover image is a promotional still, not a frame produced by this graph.
Tutorial: YouTube · Bilibili. Workflows supplied through AI-KSK; verify workflow, node, model, audio, likeness and cover rights separately. No blanket commercial or redistribution license is asserted.