ComfyUI Node
APNext H3 Music Video (Minimal)
The one-box music video: song + lyrics + a cinematic look + three sliders (performance, pace, wildness) - the model invents the concept and the performer and writes the whole video. Attach reference images to fix the performer's face. The full H3 Music Video Writer runs underneath with sensible defaults; use that node when you need cast, locks, briefs or the masked-audio path.
APNext H3 Music Video (Minimal)
- audio
- llm
- image_1
- image_2
- image_3
- image_4
- image_5
- image_6
- image_7
- image_8
- image_9
- scenes
- durations
- lengths
- audio_segments
- scenes_text
- session_id
- info
- image_1
- image_2
- image_3
- image_4
- image_5
- image_6
- image_7
- image_8
- image_9
- clip_starts
◄lyrics►
◄visual_styleLive-action, 35mm cinematic film aesthetic►
◄performance80►
◄pace30►
◄wildness45►
◄modelsonnet►
◄seed-1►
Categorycomfyui_dagthomas/H3
Inputs (18)
| Name | Type | Default | Description |
|---|---|---|---|
| audio | AUDIO | The song. It is cut into pieces on the music and every piece becomes one clip. | |
| lyrics | STRING | Lyrics, one line per line. Timestamps make the sync exact: `[0:15] line` (or LRC `[00:15.20] line`); section tags like [Chorus] are kept; untimed lines are spread evenly. Empty = instrumental video. The imagery of every scene is staged from its lyric lines. | |
| visual_style | COMBO | Live-action, 35mm cinematic film aesthetic | The look of the whole video - the curated cinematic looks (35mm, Wes Anderson, neon noir, ...) each fix style, camera, lenses and colour. Auto lets the model pick one to fit the song. |
| performance | INT | 800–100 | How much the singer is on camera. 0-33 = Narrative (story visuals, nobody sings on camera), 34-66 = Mixed (performance and story alternate), 67-100 = Performance (the singer lip-syncs the lyrics on camera). |
| pace | INT | 300–100 | How fast the video cuts. 0 = long, slow pieces (up to ~15 s per clip), 100 = quick cuts (pieces down to ~6 s). The song is still cut ON the music inside that range. |
| wildness | INT | 450–100 | 0 = grounded performance video, 100 = fully surreal. Above 40 seeds surreal events. |
| model | COMBO | sonnet | Who writes the prompt. sonnet / opus / haiku / fable / default are Claude Code aliases (`default` = whatever the CLI is configured for). `codex` is the OpenAI Codex CLI with its configured model (shown when installed; `codex:<model-id>` in an H3 LLM Backend picks a specific one). ollama: / lmstudio: / local: entries are whatever your local servers were serving when the page loaded; pick one to run fully offline. Anything not listed goes in model_override. |
| seed | INT | -1-1–18446744073709550000 | Seeds the surreal picks and controls caching. -1 re-runs every queue. |
| llmopt | APNEXT_LLM | Optional. Connect an APNext H3 LLM Backend node to write with Ollama, LM Studio, another OpenAI-compatible server or an API model instead of Claude Code. Overrides the model dropdown while connected. | |
| image_1opt | IMAGE | Reference image 1: <Picture 1> in the prompt. Connect the same image to image_1 on the MiniMax H3 Reference to Video node, or use this node's image_1 output. | |
| image_2opt | IMAGE | Reference image 2: <Picture 2> in the prompt. Connect the same image to image_2 on the MiniMax H3 Reference to Video node, or use this node's image_2 output. | |
| image_3opt | IMAGE | Reference image 3: <Picture 3> in the prompt. Connect the same image to image_3 on the MiniMax H3 Reference to Video node, or use this node's image_3 output. | |
| image_4opt | IMAGE | Reference image 4: <Picture 4> in the prompt. Connect the same image to image_4 on the MiniMax H3 Reference to Video node, or use this node's image_4 output. | |
| image_5opt | IMAGE | Reference image 5: <Picture 5> in the prompt. Connect the same image to image_5 on the MiniMax H3 Reference to Video node, or use this node's image_5 output. | |
| image_6opt | IMAGE | Reference image 6: <Picture 6> in the prompt. Connect the same image to image_6 on the MiniMax H3 Reference to Video node, or use this node's image_6 output. | |
| image_7opt | IMAGE | Reference image 7: <Picture 7> in the prompt. Connect the same image to image_7 on the MiniMax H3 Reference to Video node, or use this node's image_7 output. | |
| image_8opt | IMAGE | Reference image 8: <Picture 8> in the prompt. Connect the same image to image_8 on the MiniMax H3 Reference to Video node, or use this node's image_8 output. | |
| image_9opt | IMAGE | Reference image 9: <Picture 9> in the prompt. Connect the same image to image_9 on the MiniMax H3 Reference to Video node, or use this node's image_9 output. |
Outputs (17)
| Name | Type | Description |
|---|---|---|
| scenes | STRING | — |
| durations | FLOAT | — |
| lengths | INT | — |
| audio_segments | AUDIO | — |
| scenes_text | STRING | — |
| session_id | STRING | — |
| info | STRING | — |
| image_1 | IMAGE | — |
| image_2 | IMAGE | — |
| image_3 | IMAGE | — |
| image_4 | IMAGE | — |
| image_5 | IMAGE | — |
| image_6 | IMAGE | — |
| image_7 | IMAGE | — |
| image_8 | IMAGE | — |
| image_9 | IMAGE | — |
| clip_starts | FLOAT | — |