ComfyUI Node
H3 Motion Context Clip Stitcher /noEmbryo
Final assembly for NikoDemon80's H3 Motion Context AV clip archives. Loads numbered h3_motion_context_av_v1 files, decodes one clip at a time, dissolves the overlap between adjacent clips (video + synchronized audio), and concatenates them to a final video and audio stream.
H3 Motion Context Clip Stitcher /noEmbryo
- video_vae
- audio_vae
- latent
- images
- audio
- frame_count
- report
◄folderh3_context►
◄patternclip_*.safetensors►
◄first_clip1►
◄last_clip0►
◄context_length22►
◄fps24.000►
Categoryvideo/minimax
Inputs (9)
| Name | Type | Default | Description |
|---|---|---|---|
| folder | STRING | h3_context | Folder containing clip_00001.safetensors, clip_00002.safetensors, etc. Absolute paths and paths relative to ComfyUI/output are accepted. |
| pattern | STRING | clip_*.safetensors | Filename glob. The final five-digit number is treated as the clip index. |
| first_clip | INT | 11–9999 | First approved clip to include. |
| last_clip | INT | 00–9999 | Last clip to include. 0 = every clip from first_clip onward. |
| context_length | COMBO | 22 | Number of decoded frames to crossfade at each clip boundary. The normal setting is 22 frames. This is the overlap length that is dissolved between adjacent clips. 5, 22, 39 or 56 are the lengths that are a whole number of latent steps, which is why other numbers aren't offered. |
| fps | FLOAT | 24.0001–240 | H3 native output rate. Keep this at 24 unless your workflow deliberately changes it. |
| video_vaeopt | VAE | MiniMax H3 video VAE (FP16 or INT8 ConvRot). | |
| audio_vaeopt | VAE | MiniMax H3 audio VAE FP32. Required for the AUDIO output. | |
| latentopt | LATENT | Optional: the currently-generated AV latent (from your H3 sampler), used in place of the highest-numbered file on disk. |
Outputs (4)
| Name | Type | Description |
|---|---|---|
| images | IMAGE | — |
| audio | AUDIO | — |
| frame_count | INT | — |
| report | STRING | — |